No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Methodological Framework to support Load Forecast Error Assessment in Local Energy Markets
Abstract
Due to the expansion of small-scale distributed generation, residential consumers are evolving to active participants in energy markets. Concepts like Local Energy Markets (LEM) are designed to harvest flexibility of these prosumers and contribute to a stable power system operation. However, the stochastic nature of the consumption of households increases the difficulty of accurate forecasts and can lead to erroneous bids and penalty payments. State of the art load forecasting methods can reduce this error to a certain extend. Yet, for a systematic assessment of the implications of forecast errors, a method capable of generating forecast time series with defined errors is required. With this method, measures to decrease the implications of forecast errors (e.g. aggregation of participants) can be evaluated. In this paper, we introduce such a method based on nonlinear optimization. After an analysis of typically used error metrics and achieved forecast errors in the literature, the proposed method is evaluated using German household load profiles demonstrating similar statistical properties as found in the literature. Additionally, we show the application of the method to a LEM simulation case revealing that a participation of a household without flexible assets would only be profitable for forecast errors below 30-40%.
... Furthermore, LEM research has been extended to consider multi-modal systems, especially heat [16]. Additionally, the role of uncertainty has been analyzed [17] and prosumer preferences and their impact on local market results have been investigated in [18,19]. Further research on tax and levy systems have shown their impact on local market outcomes [19][20][21]. ...
... In other work, the role of uncertainty is considered within the LEM framework, e.g. in [17] the impact of uncertainty from load forecasting errors on LEM participation is estimated. However, with perfect foresight (and no uncertainty), trading mechanisms are negligible factors for the market results as market participants can predict the other market participants' behavior and bidding. ...
The energy system decarbonization leads to a decentralization of generation and flexibility. Among the new concepts to integrate distributed flexibility are local energy markets. While a broad range of research investigates local energy markets on a distribution grid level in detail, research on their system impact has been limited. Therefore, we develop a framework to investigate different configurations of local markets as well as the operation of distributed energy resources and their interaction with the wholesale markets. This framework is applied to a pan-European case study with detailed bottom-up modeling of local energy markets in France and Germany. Additionally, transmission grid simulations are carried out to investigate the impact of local trading on grid congestions. Our results show that a direct coordination of distributed flexibility within the wholesale market is more efficient than a preference for local trading. Nonetheless, local energy markets can be used as an incentive for the expansion of distributed flexibility as well as a way to break down the complexity of coordinating millions of distributed assets in a single market. Additionally, our results show that local trading relieves the transmission grid.
... To create a forecasting model with high accuracy, Reference [21] provided a hybrid prediction model based on a feature selection method which chooses the best candidate inputs and enhanced support vector machine which fine tunes the free parameter of the forecast engine to tackle the prediction of aggregated loads of buildings and the impact of electric vehicle. Another method based on non-linear optimization was introduced in Reference [22] which supports the assessment of load forecasts in local energy markets (LEM) simulations by generating erroneous load profiles and decreases the implications of forecast errors. ...
... To demonstrate the contributions of the proposed method as compared to other state-of-the-art models, the function comparisons are summarized in Table 1. It is shown that some researchers focused on the feature selection which aims to find the good input for forecasting model to improve its ability [15,[20][21][22]27]. Some studies have applied deep learning to better deal with the non-linear mapping problem in load forecasting [25][26][27][28]. ...
Load forecasting is a complex non‐linear problem with high volatility and uncertainty. This study presents a novel load forecasting method known as deep neural network and historical data augmentation (DNN–HDA). The method utilises HDA to enhance regression by DNN for monthly load forecasting, considering that the historical data to have a high correlation with the corresponding predicted data. To make the best use of the historical data, one year's historical data is combined with the basic features to construct the input vector for a predicted load. In this way, if there is C years' historical data, one predicted load can have C input vectors to create the same number of samples. DNN–HDA increases the number of training samples and enhances the generalisation of the model to reduce the forecasting error. The proposed method is tested on daily peak loads from 2006 to 2015 of Austria, Czech and Italy. Comparisons are made between the proposed method and several state‐of‐the‐art models. DNN–HDA outperforms DNN by 44%, 38% and 63% on the three data sets, respectively.
... Recent work has highlighted that it is significantly difficult to predict accurate demand values with the existing load forecasting method [22]. Further, it is arduous to ensure the correctness of forecasts as attackers can manipulate exogenous parameters in load forecasting. ...
Utility companies are expected to leverage the flexibility in residential demand and the penetration of smart/IoT devices to implement efficient and effective residential demand response schemes with automated device scheduling. The use of distributed architectures in these systems allows adversaries to employ false data injection attacks (FDIA) to manipulate optimal decisions, as utility companies do not have complete control over the systems and data. Thus, reliable implementations are required to ensure the resilience of residential DR schemes against FDIAs.In this work, we integrate DR optimisation, anomaly detection in the context of FDIA detection, and attack impact mitigation methods to implement a resilient, automated device scheduling framework. We evaluate the implemented framework using areal-world dataset to emphasise the robustness of the framework against FDIAs.
... Forecasts can also be applied to energy markets. In recent years, in many countries, the acquisition and sale of electricity is traded in energy markets (please see Yildiz and co-workers 46 ). Accurate forecasts of the electricity demand and price are therefore a need for the participants in the energy markets. ...
This paper introduces the HEMStoEC database, which contains data recorded in the course of two research projects, NILMforIHEM, and HEMS2IEA, for more than three years. To be manageable, the dataset is divided in months, from January 2020 until February 2023. It consists in: (a) consumption electric data for four houses in a neighbourhood situated in the south of Portugal, (b) weather data for that location, (c) photovoltaic and battery data, (d) inside climate data, and (e) operation of several electric devices in one of the four houses. Raw data, sampled at 1 sec and 1 minute are available from the different sensing devices, as well as synchronous data, with a common sampling interval of 5 minutes are available. Gaps existing within the data, as well as periods where interpolation was used, are available for each month of data.
... As for forecasting LEM demand and supply, the implications of forecasting errors in P2P trading are inspected in [35]. A mechanism to support demand forecast error assessment in the LEM is proposed in [36]. Another model is developed in [37] to mitigate imbalances in the LEM through accurate forecasting. ...
Peer-to-peer (P2P) trading in a local energy market (LEM) offers various participants the opportunity to negotiate and strike energy deals among themselves using a distributed ledger technology called blockchain. In this paper, a new local model is presented using a layer-2 scalability solution for second-generation (Gen2) blockchain technology to enable P2P trading among four types of participants: consumers, prosumers with solar photovoltaic (PV) systems, prosumers with solar PV systems and battery energy storage systems (BESSs), and electric vehicles (EVs). The proposed LEM trading platform involves several critical steps, including the creation of typical forecasting profiles for load consumption, solar generation, and battery state-of-charge (SOC) through a forecasting solution. Next, the LEM participants place their pricing bids using a trading agent service, and the trading engine collects the profiles data and bid prices, which performs matchmaking in a forward-facing market. The output of the trading engine consists of dispatch signals for prices and energy values that are sent to each participant to execute actual trading. Furthermore, the trading engines store the accepted and past bidding data and energy values of P2P trades for each participant in blockchain technology, which can be retrieved and displayed on the LEM user interface screens of participants and administrators using their blockchain addresses at any time during the trading process. This study focuses on simulating proposed LEM models, incorporating functional limitations and market rules. These rules aim to reduce energy costs, enhance margins for utilities and retailers, and mitigate grid congestion through BESSs, resulting in reduced operational and capital expenditure. LEM outcomes are analysed and compared with a Business-as-usual (BAU) model. Participants’ energy trading behaviour, cost-revenue dynamics, grid impact, and blockchain implementation costs are explored. The study highlights LEM benefits in terms of reduced CO2 emissions by 984 kg CO2, increased self-sufficiency by 2.2%, and improved financial benefits of all participants by 21.6%. The use of modern blockchain technology guarantees secure data storage and rapid, cost-effective energy trading, thereby making the proposed LEM platform a viable solution in the distribution market.
... where, : number of data points : observed value ̂ : Predicted value Due to its ability to be applied to various contexts, easily understood, and dependable, MAPE is regarded as the most widely used method for measuring accuracy [14], [18]. MAPE indicates how big the error is in forecasting compared to the actual value [19], [20]. The MAPE formula can be seen in Equation 3. ...
Cancer is a disease characterized by abnormal cell growth and is not contagious, such as breast cancer which can affect both men and women. breast cancer is one of the cancer diseases that is classified as dangerous and takes many victims. However, the biggest problem in this study is that the classification method is low and the resulting accuracy is less than optimal. the purpose of this study is to improve the accuracy of breast cancer classification. Therefore, a new method is proposed, namely ensemble learning which combines logistic regression, decision tree, and random forest methods, with a voting system. This system is useful for finding the best results on each parameter that will produce the best prediction accuracy. The prediction results from this method reached an accuracy of 98.24%. The resulting accuracy rate is more optimal by using the proposed method.
... where, : number of data points : observed value ̂ : Predicted value Due to its ability to be applied to various contexts, easily understood, and dependable, MAPE is regarded as the most widely used method for measuring accuracy [32], [33]. MAPE indicates how big the error is in forecasting compared to the actual value [34], [35]. The MAPE formula can be seen in Equation 3. ...
Crude oil price fluctuations significantly affect commodity market price fluctuations, so a sudden drop in oil prices will cause a slowdown in the economy and other commodities. This is very important for Indonesia, one of the world's oil-producing countries, to gain multiple benefits from oil exports when world oil prices increase and increase economic growth. Therefore, a system is needed to predict world crude oil prices. In this case, the Particle Swarm Optimization (PSO) algorithm is applied as the optimization of the weight parameters in the Artificial Neural Network-Backpropagation (ANN-BP) method. We compared the ANN-BP–PSO and ANN-BP methods to obtain the method with the best causation value based on the MAPE and MSE results. PSO aims to find the best weight value by iterating the process of finding and increasing position, speed, Pbest, and Gbest until the iteration is complete. The results showed that the ANN-BP-PSO process was classified as very good and had a lower predictive error rate than the ANN-BP method based on the MAPE and MSE values, which is 5.02007% and 7.15827% compared to 6.28323% and 13.86345.
... On the one hand, short-term residential load forecasting can assist home energy management system to optimize operation, formulate reasonable battery charging and discharging strategies, and reduce electricity costs [3,4]. With the emergence of the local energy market, short-term residential load forecasting also provides more sensible reference for the trading behavior of resident customers in the local energy market [5,6]. On the other hand, short-term residential load forecasting plays an increasingly prominent role in a more dispersed distribution network [7]. ...
Short-term residential load forecasting is of great significance to smart grid applications. Deep learning techniques, especially recurrent neural networks, can greatly improve the performance of prediction models. However, deep neural networks usually have low interpretability, which creates obstacles for customers to deeply understand the prediction results and make quick responses. In addition, the existing deep learning prediction methods rely heavily on the centralized training of massive data. However, the transmission of data from the client to the server poses a threat to the data security of customers. In this work, we propose an interpretable deep learning framework with federated learning for short-term residential load forecasting. Specifically, we propose a new automatic relevance determination network for feature interpretation, combined with the encoder–decoder architecture to achieve interpretable multi-step load prediction. In the edge computing network, the training scheme based on federated learning does not share the original data, which can effectively protect data privacy. The introduction of iterative federated clustering algorithm can alleviate the problem of non-independent and identical distribution of data in different households. We use two real-world datasets to verify the feasibility and performance of the proposed method. Finally, we discuss in detail the feature interpretation of these two datasets.
... [5] estimates that the dayahead forecasting error for residential load and PV generation is approximately 20%, even when real-life data is used for developing the forecasting model. [6] has reviewed the current state-of-the-art load forecasting methods based on the conventional auto-regressive methods and the modern artificial neural networks. For day-ahead residential load forecasting, these methods show a median value for the mean absolute percentage error (MAPE) in the range of 45.2±14.2%. ...
... In other works, the role of uncertainty is considered within the LEM framework, e.g. in [19] the impact of uncertainty from load forecasting errors on LEM participation is estimated. However, with perfect foresight (and no uncertainty), trading mechanisms are negligible factors for the market results as market participants can predict the other market participants' behavior and bidding. ...
p>The energy system decarbonization leads to a decentralization of generation and flexibility. Among the new concepts to integrate the distributed flexibility are local energy markets. While a broad range of research investigates local energy markets on a distribution grid level in detail, research on their system impact has been limited. Therefore, we develop a framework to investigate different configurations of local markets and operation of distributed energy resources and their interaction with the wholesale markets. This framework is applied to a pan-European case study with detailed bottom-up modeling of local energy markets in France and Germany. Additionally, transmission grid simulations are carried out to investigate the impact of local trading on grid congestions. Our results show that a direct coordination of distributed flexibility within the wholesale market is more efficient than a preference of local trading. Nonetheless, local energy markets can be used as an incentive for expansion of distributed flexibility as well as a way to break down the complexity of coordinating millions of distributed assets in a single market. Additionally, our results show that local trading relieves the transmission grid. </p
... In other works, the role of uncertainty is considered within the LEM framework, e.g. in [19] the impact of uncertainty from load forecasting errors on LEM participation is estimated. However, with perfect foresight (and no uncertainty), trading mechanisms are negligible factors for the market results as market participants can predict the other market participants' behavior and bidding. ...
p>The energy system decarbonization leads to a decentralization of generation and flexibility. Among the new concepts to integrate the distributed flexibility are local energy markets. While a broad range of research investigates local energy markets on a distribution grid level in detail, research on their system impact has been limited. Therefore, we develop a framework to investigate different configurations of local markets and operation of distributed energy resources and their interaction with the wholesale markets. This framework is applied to a pan-European case study with detailed bottom-up modeling of local energy markets in France and Germany. Additionally, transmission grid simulations are carried out to investigate the impact of local trading on grid congestions. Our results show that a direct coordination of distributed flexibility within the wholesale market is more efficient than a preference of local trading. Nonetheless, local energy markets can be used as an incentive for expansion of distributed flexibility as well as a way to break down the complexity of coordinating millions of distributed assets in a single market. Additionally, our results show that local trading relieves the transmission grid. </p
... However, there is a growing concern that benefits from P2P markets can be diminished by emerging challenges [3], [4]. The inherent variability and limited controllability of renewable resources, as well as the stochastic nature of endusers consumption pose a fundamental challenge to deploy P2P markets [5]. Uncertainty in generation and demand can be translated to uncertainty in the amount of energy to trade in the market. ...
This paper proposes the novel application of call-options for financial loss mitigation in a peer-to-peer (P2P) energy market. P2P energy markets present the opportunity for end-users to trade electricity among themselves by managing their electricity usage and production capabilities. But variability characteristics of renewable resources pose a fundamental challenge to their integration into the grid as well as participating in emerging P2P energy markets. The growing penetration of renewable supply will increase the need for tools to mitigate potential energy traders' financial losses. This paper proposes and evaluates the application of call-option contracts in P2P markets to hedge against financial losses related to power shortfall in renewable supply. A case study is presented, showing that P2P traders might have to bear financial losses when they cannot meet their market obligations, and how options can be used to mitigate such losses.
... Now the final and tuned network is used to forecast price and load. 38 ...
The revolution of power grids from traditional grids to Smart Grids (SGs) requires effective Demand Side Management (DSM) and reliable Renewable Energy Sources (RESs) incorporation in order to maintain demand, supply balance and optimize energy in an environment friendly manner. Data analytics provide solutions to the emerging challenges of power systems, such as DSM, environmental pollution (due to carbon emission), fossil fuel dependency mitigation, RESs incorporation, cost curtailment, grid’s stability and security. To efficiently manage electricity and maximize the profit of power utilities several tasks are focused in this thesis, i.e., prediction of electricity load to avoid demand and generation mismatch, wind power forecasting to satisfy energy demand effectively, electricity price forecasting for regulating market operations, carbon emissions forecasting for reducing payment of carbon tax, Electricity Theft Detection (ETD) for recovering power utilities’ revenue loss caused by electricity theft. In addition to that, a wind power forecast based DSM scheme is proposed. Furthermore, impact of RESs integration level on carbon emissions, electricity price and consumption cost is quantified. Both forecasting and classification techniques are utilized for efficient energy management. Forecasting of electricity load, price, wind power and carbon emissions is performed, whereas, classification of fair and fraudulent electricity consumers is performed. To balance electricity demand and supply, electricity load forecasting is required. Three models are proposed for this purpose, i.e., Deep Long Short-Term Memory (DLSTM), Efficient Sparse Autoencoder Nonlinear Autoregressive eXogenous network (ESAENARX) and Differential Evolution Recurrent Extreme Learning Machine (DE-RELM). DLSTM utilizes univariate data and gives single result, whereas, ESAENARX and DE-RELM model multivariate data and predict electricity load and price simultaneously. Due to adaptive and automatic feature learning mechanism, DLSTM achieves accurate results for separate forecasting of electricity load and price. ESAENARX and DE-RELM models are enhanced by newly proposed efficient feature extractor and model’s parameter tuning, respectively. Real-world datasets of ISO-NE, PJM, NYISO are used for load and price forecasting. The purpose of regulating the electricity market operations is achieved by forecasting of electricity load, price, wind power and carbon emissions. Wind power generation is predicted by an efficient model named Efficient Deep Convolution Neural Network (EDCNN). Moreover, a DSM strategy is also proposed based on predicted wind power generation. Power utilities have to pay carbon emissions tax imposed by government. To pay less carbon emissions tax, carbon emissions prediction is required, which helps in encouraging electricity consumers to shift their consumption load to low carbon price time periods of the day. For accomplishing the carbon emissions forecasting task, an efficient model named as Improved Particle Swarm Optimization based Deep Neural Network (IPSO DNN) is proposed. This model is improved by tunning the parameters of DNN by newly proposed improved optimization technique named as IPSO. ISO-NE dataset is used for wind power and carbon emissions forecasting. To reduce the financial loss of power utilities ETD is very important. For this purpose four models are proposed, named as, Differential Evolution Random Under Sampling Boosting (DE-RUSBoost), Jaya-RUSBoost, RUS Ensemble CNN (RUSE-CNN) and anomaly detection based ETD. In DE-RUSBoost and Jaya-RUSBoost, the parameters of RUSBoost classifier are tunned by DE and Jaya optimization techniques, respectively. In RUSE-CNN, RUS data balancing technique is applied along with ensemble CNN to improve ETD performance. DE-RUSBoost, Jaya-RUSBoost and RUSE-CNN are supervised model that work on labeled electricity theft data. Whereas, anomaly detection based ETD model is capable of identifying electricity theft from unlabeled electricity consumption data. Real-world datasets of SGCC, UMass, PRECON, CER, EnerNOC and LCL are used for ETD. Simulation results show that all the proposed models perform significantly better on real-world dataset as compared to their state-of-the-art counterpart models. The improved feature engineering and model hyper-parameter tuning enhance the performance of the proposed models in terms of prediction and classification results.
... Now the final and tuned network is used to forecast price and load. 38 ...
The revolution of power grids from traditional grids to Smart Grids (SGs) requires effective
Demand Side Management (DSM) and reliable Renewable Energy Sources (RESs) incorporation
in order to maintain demand, supply balance and optimize energy in an environment
friendly manner. Data analytics provide solutions to the emerging challenges of power systems,
such as DSM, environmental pollution (due to carbon emission), fossil fuel dependency
mitigation, RESs incorporation, cost curtailment, grid’s stability and security. To efficiently
manage electricity and maximize the profit of power utilities several tasks are focused in
this thesis, i.e., prediction of electricity load to avoid demand and generation mismatch,
wind power forecasting to satisfy energy demand effectively, electricity price forecasting for
regulating market operations, carbon emissions forecasting for reducing payment of carbon
tax, Electricity Theft Detection (ETD) for recovering power utilities’ revenue loss caused by
electricity theft. In addition to that, a wind power forecast based DSM scheme is proposed.
Furthermore, impact of RESs integration level on carbon emissions, electricity price and
consumption cost is quantified.
Both forecasting and classification techniques are utilized for efficient energy management.
Forecasting of electricity load, price, wind power and carbon emissions is performed, whereas,
classification of fair and fraudulent electricity consumers is performed. To balance electricity
demand and supply, electricity load forecasting is required. Three models are proposed for
this purpose, i.e., Deep Long Short-Term Memory (DLSTM), Efficient Sparse Autoencoder
Nonlinear Autoregressive eXogenous network (ESAENARX) and Differential Evolution
Recurrent Extreme Learning Machine (DE-RELM). DLSTM utilizes univariate data and
gives single result, whereas, ESAENARX and DE-RELM model multivariate data and predict
electricity load and price simultaneously. Due to adaptive and automatic feature learning
mechanism, DLSTM achieves accurate results for separate forecasting of electricity load and
price. ESAENARX and DE-RELM models are enhanced by newly proposed efficient feature
extractor and model’s parameter tuning, respectively. Real-world datasets of ISO-NE, PJM,
NYISO are used for load and price forecasting. The purpose of regulating the electricity
market operations is achieved by forecasting of electricity load, price, wind power and carbon
emissions. Wind power generation is predicted by an efficient model named Efficient Deep
Convolution Neural Network (EDCNN). Moreover, a DSM strategy is also proposed based on
predicted wind power generation. Power utilities have to pay carbon emissions tax imposed
by government. To pay less carbon emissions tax, carbon emissions prediction is required,
which helps in encouraging electricity consumers to shift their consumption load to low
carbon price time periods of the day. For accomplishing the carbon emissions forecasting
task, an efficient model named as Improved Particle Swarm Optimization based Deep Neural
Network (IPSO DNN) is proposed. This model is improved by tunning the parameters of
DNN by newly proposed improved optimization technique named as IPSO. ISO-NE dataset
is used for wind power and carbon emissions forecasting. To reduce the financial loss of
power utilities ETD is very important. For this purpose four models are proposed, named as,
Differential Evolution Random Under Sampling Boosting (DE-RUSBoost), Jaya-RUSBoost,
RUS Ensemble CNN (RUSE-CNN) and anomly detection based ETD. In DE-RUSBoost
and Jaya-RUSBoost, the parameters of RUSBoost classifier are tunned by DE and Jaya
optimization techniques, respectively. In RUSE-CNN, RUS data balancing technique is
applied along with ensemble CNN to improve ETD performance. DE-RUSBoost, Jaya-
RUSBoost and RUSE-CNN are supervised model that work on labeled electricity theft data.
Whereas, anomaly detection based ETD model is capable of identifying electricity theft from
unlabeled electricity consumption data. Real-world datasets of SGCC, UMass*, PRECON,
CER, EnerNOC and LCL are used for ETD. Simulation results show that all the proposed
models perform significantly better on real-world dataset as compared to their state-of-the-art
counterpart models. The improved feature engineering and model hyper-parameter tuning
enhance the performance of the proposed models in terms of prediction and classification
results.
... [5] estimates that the dayahead forecasting error for residential load and PV generation is approximately 20%, even when real-life data is used for developing the forecasting model. [6] has reviewed the current state-of-the-art load forecasting methods based on the conventional auto-regressive methods and the modern artificial neural networks. For day-ahead residential load forecasting, these methods show a median value for the mean absolute percentage error (MAPE) in the range of 45.2±14.2%. ...
This paper develops a stochastic model predictive control (SMPC) based framework for the real-time operation of residential scale DC-coupled PV-storage systems. The proposed framework combines the use of bivariate Markov chains to build the uncertainty model of PV generation and residential load, a Bayesian approach based recursive learning of the Markov model, and a scenario-based formulation for the SMPC problem. This approach operates in real-time, thus minimizing the impact of the mismatch between the forecasted data and the actual observation on the system performance by updating the control decisions with the realization of the stochastic parameters at each time step. Load and PV generation are jointly modeled, and the interdependence between them is accounted for through bivariate Markov chains. The use of recursive learning guarantees that the uncertainty model is continuously updated to enhance its prediction capabilities for scenario generation. The numerical simulations using real-world data demonstrate the enhanced performance of the proposed approach over the conventional approaches, on a par with model predictive control with complete knowledge of the uncertainties.
... Assessing forecast quality is more straightforward and the standard approach is statistical error metrics, such as: Typically, these metrics apply some kind of loss function to individual errors and then calculate a summary statistic [2]. For example, Screck et al. [3] surveyed the literature for 681 load forecasts for the residential sector. Altogether, 15 error metrics were used, the most frequently used was mean absolute percentage error (MAPE) with 392 values. ...
When identifying and comparing forecasting models, there may be a risk that poorly selected criteria could lead to wrong conclusions. Thus, it is important to know how sensitive the results are to the selection of criteria. This contribution aims to study the sensitivity of the identification and comparison results to the choice of criteria. It compares typically applied criteria for tuning and performance assessment of load forecasting methods with estimated costs caused by the forecasting errors. The focus is on short-term forecasting of the loads of energy systems. The estimated costs comprise electricity market costs and network costs. We estimate the electricity market costs by assuming that the forecasting errors cause balancing errors and consequently balancing costs to the market actors. The forecasting errors cause network costs by overloading network components thus increasing losses and reducing the component lifetime or alternatively increase operational margins to avoid those overloads. The lifetime loss of insulators, and thus also the components, is caused by heating according to the law of Arrhenius. We also study consumer costs. The results support the assumption that there is a need to develop and use additional and case-specific performance criteria for electricity load forecasting.
The incorporation of renewable energy systems in the world energy system has been steadily increasing during the last few years. In terms of the building sector, the usual consumers are becoming increasingly prosumers, and the trend is that communities of energy, whose households share produced electricity, will increase in number in the future. Another observed tendency is that the aggregator (the entity that manages the community) trades the net community energy in public energy markets. To accomplish economically good transactions, accurate and reliable forecasts of the day-ahead net energy community must be available. These can be obtained using an ensemble of multi-step shallow artificial neural networks, with prediction intervals obtained by the covariance algorithm. Using real data obtained from a small energy community of four houses located in the southern region of Portugal, one can verify that the deterministic and probabilistic performance of the proposed approach is at least similar, typically better than using complex, deep models.
With the rapid development of Distributed Energy Sources (DERs), Peer-to-Peer (P2P) energy trading is regarded as an effective scheme to improve local energy utilization. Nevertheless, unlike wholesale electricity markets of the current grid size, small-scale prosumers and highly unpredictable intermittent DERs account for a significant proportion of P2P markets, leading to an escalation of market uncertainties. To facilitate effective market functionality, penalty mechanisms for unqualified participants are essential, as is typically the case in the wholesale electricity market. However, there has been little discussion of the use of penalty mechanisms in P2P markets. In this context, we propose a novel adaptive penalty mechanism (APM) to drive the defaulting prosumers to fulfill orders. Unlike the traditional two-dimensional (price, quantity) penalty price, APM uses a three-dimensional penalty and introduces deviation percentage factors to reduce the risk of excessive penalty rates. Penalty prices are determined by utilizing the distributed default clearing algorithm to adapt to market conditions, thereby preventing deviations in clearing prices. Case studies are conducted to demonstrate the feasibility and efficiency of the proposed APM in the P2P market. The results indicate that the APM strike an appropriate between cost-effectiveness and regulation, requiring about 20% less reserve capacity than the severe penalty.
In this work, a local multi-modal energy market is introduced to couple district heating and electric systems. In the course of the ongoing decarbonization of energy systems, electric systems have to integrate more and more volatile renewable energies, whereas in thermal systems, the demand for sustainable heat generation is continuously increasing. Market-based coordination of local thermal-electric energy systems can help to alleviate these challenges. In this work, an adequate representation of conversion assets, e.g., heat pumps, is achieved by introducing novel coupling orders in the market. These enable an explicit coupling of heat and electricity, and thus cross-energy load-shifts. In addition, a new type of storage orders is introduced to offer flexibility options by energy storage systems in the local energy system. The benefits of the market scheme are demonstrated for a day ahead cycle of an exemplary local energy system in Germany. Inter alia, the results lead to the conclusion that coupling orders are able to alleviate price and volume risks of market participants with conversion assets. Moreover, storage orders can provide operational benefits to the local energy system, while respecting the physical characteristics of energy storage systems. For the specified day ahead cycle, the peak load to the transmission grid can be decreased by up to 18.34%, and, thus improving the self-sufficiency of the local energy system.
With the increasing generation of renewable energy in power markets, the mismatch between power production and power demand in the power market is becoming more serious. Power prices in the short term guided the balance of load and demand. Although short-term power price guidance can provide certain benefits, short-term power price guidance disrupts the potential long-term market balance and provides sustainable development challenges. This paper adopts a stochastic differential method to guide flexible energy service providers for long-term price guidance with addressing the challenges of long-term market imbalances. After knowing power production, the stochastic differentiation method guides load power demand to follow changes in power production by a reasonable power price. The stochastic differential method utilizes energy flexibility for long-term price guidance with cost minimization in a long-term market environment. The power demand results of Zhaoqing considering the water tower model show that the long-term price guidance mechanism based on the stochastic differential method saves 12.39% of the operating cost with RMB 782.6987 million each year. The long-term price guidance based on the stochastic differential method mobilizes the energy flexibility by indirectly control the demand of flexible energy systems through reasonable price signals.
Due to the natural intermittency of renewable energy resources (such as wind and PV) and high variations in electricity consumption profiles, planning and scheduling optimisations generally require a large amount of historical energy data to produce accurate forecasts. Often in practical situations, historical data is not sufficient to capture the uncertainties in generation and consumption. A promising approach to solve this issue is to generate various generation and consumption scenarios, specifying possible trajectories of solar and load power. Then these scenarios can be incorporated into the optimisation models for infrastructure planning and power operation. In this paper, we propose a data driven Generative Adversarial Networks (GAN) based model to generate domestic solar production and electricity consumption scenarios. We train our generative model using historical solar and load data collected by Solar Analytics from Australian residential PV customers. Moreover, by using a conditional GAN, we demonstrate we can generate synthetic data conditioned on site specific conditions. By validating the distributions of our generated data against real-time data, we illustrate that we can produce realistic PV generation and consumption profiles.
Efficient operation of electricity markets necessitates a penalty mechanism to penalize market participants who do not fulfill their market obligations. However, the traditional penalty mechanisms that have been successfully implemented in wholesale electricity markets may result in unintended consequences in transactive markets where the participants have uncertain supply or demand. In this regard, this letter investigates main challenges of applying traditional penalty mechanisms for transactive agents. Some efficient strategies are also proposed to operate the transactive markets in such a way that guarantees its security as well as liquidity.
This is the annual report 2018 of the scientific monitoring, which accompanies the governmental funding program for pv home storage systems in Germany.
It covers:
1. Market and technology development of pv home storage systems
- Number of installations
- Designs choices
- Prices
- …
2. Self-consumption, self-sufficiency and their effects on taxes and tariffs
3. High-resolution measurements of 20 privately operated pv home storage systems
Please find more information on www.speichermonitoring.de
Triggered by the increased fluctuations of renewable energy sources, the European Commission stated the need for integrated short-term energy markets (e.g., intraday), and recognized the facilitating role that local energy communities could play. In particular, microgrids and energy communities are expected to play a crucial part in guaranteeing the balance between generation and consumption on a local level. Local energy markets empower small players and provide a stepping stone towards fully transactive energy systems. In this paper we evaluate such a fully integrated transactive system by (1) modelling the energy resource management problem of a microgrid under uncertainty considering flexible loads and market participation (solved via two-stage stochastic programming), (2) modelling a wholesale market and a local market, and (3) coupling these elements into an integrated transactive energy simulation. Results under a realistic case study (varying prices and competitiveness of local markets) show the effectiveness of the transactive system resulting in a reduction of up to 75/% of the expected costs when local markets and flexibility are considered. This illustrates how local markets can facilitate the trade of energy, thereby increasing the tolerable penetration of renewable resources and facilitating the energy transition.
Electricity forecasting is an essential component of smart grid, which has attracted increasing academic interest. Forecasting enables informed and efficient responses for electricity demand. However, various forecasting models exist making it difficult for inexperienced researchers to make an informed model selection. This paper presents a systematic review of forecasting models with the main purpose of identifying which model is best suited for a particular case or scenario. Over 113 different case studies reported across 41 academic papers have been used for the comparison. The timeframe, inputs, outputs, scale, data sample size, error type and value have been taken into account as criteria for the comparison. The review reveals that despite the relative simplicity of all reviewed models, the regression and/or multiple regression are still widely used and efficient for long and very long-term prediction. For short and very short-term prediction, machine-learning algorithms such as artificial neural networks, support vector machines, and time series analysis (including Autoregressive Integrated Moving Average (ARIMA) and the Autoregressive Moving Average (ARMA)) are favoured. The most widely employed independent variables are the building and occupancy characteristics and environmental data, especially in the machine learning models. In many cases, time series analysis and regressions rely on electricity historical data only, without the introduction of exogenous variables. Overall, if the singularity of the different cases made the comparison difficult, some trends are clearly identifiable. Considering the large amount of use cases studied, the meta-analysis of the references led to the identification of best practices within the expert community in relation to forecasting use for electricity consumption and power load prediction. Therefore, from the findings of the meta-analysis, a taxonomy has been defined in order to help researchers make an informed decision and choose the right model for their problem (long or short term, low or high resolution, building to country level).
Precise and representative electrical load profiles of households are an essential basis for a variety of scientific research questions in the field of energy supply and storage. Firstly, this document describes the data basis and preparation of a freely available dataset of highly temporal resolved and representative load profiles. Finally, the data is visualized and its representative status for single family households in Germany is proven.
It is important to understand and forecast a typical or a particularly household daily consumption in order to design and size suitable renewable energy systems and energy storage. In this research for Short Term Load Forecasting (STLF) it has been used Artificial Neural Networks (ANN) and, despite the consumption unpredictability, it has been shown the possibility to forecast the electricity consumption of a household with certainty. The ANNs are recognized to be a potential methodology for modeling hourly and daily energy consumption and load forecasting. Input variables such as apartment area, numbers of occupants, electrical appliance consumption and Boolean inputs as hourly meter system were considered. Furthermore, the investigation carried out aims to define an ANN architecture and a training algorithm in order to achieve a robust model to be used in forecasting energy consumption in a typical household. It was observed that a feed-forward ANN and the Levenberg-Marquardt algorithm provided a good performance. For this research it was used a database with consumption records, logged in 93 real households, in Lisbon, Portugal, between February 2000 and July 2001, including both weekdays and weekend. The results show that the ANN approach provides a reliable model for forecasting household electric energy consumption and load profile.
Smart metering is a quite new topic that has grown in importance all over the world and it appears to be a remedy for rising prices of electricity. Forecasting electricity usage is an important task to provide intelligence to the smart gird. Accurate forecasting will enable a utility provider to plan the resources and also to take control actions to balance the electricity supply and demand. The customers will benefit from metering solutions through greater understanding of their own energy consumption and future projections, allowing them to better manage costs of their usage. In this proof of concept paper, our contribution is the proposal for accurate short term electricity load forecasting for 24 hours ahead, not on the aggregate but on the individual household level.
The increasing use of renewable energy sources with variable output, such as
solar photovoltaic and wind power generation, calls for Smart Grids that
effectively manage flexible loads and energy storage. The ability to forecast
consumption at different locations in distribution systems will be a key
capability of Smart Grids. The goal of this paper is to benchmark
state-of-the-art methods for forecasting electricity demand on the household
level across different granularities and time scales in an explorative way,
thereby revealing potential shortcomings and find promising directions for
future research in this area. We apply a number of forecasting methods
including ARIMA, neural networks, and exponential smoothening using several
strategies for training data selection, in particular day type and sliding
window based strategies. We consider forecasting horizons ranging between 15
minutes and 24 hours. Our evaluation is based on two data sets containing the
power usage of individual appliances at second time granularity collected over
the course of several months. The results indicate that forecasting accuracy
varies significantly depending on the choice of forecasting methods/strategy
and the parameter configuration. Measured by the Mean Absolute Percentage Error
(MAPE), the considered state-of-the-art forecasting methods rarely beat
corresponding persistence forecasts. Overall, we observed MAPEs in the range
between 5 and >100%. The average MAPE for the first data set was ~30%, while it
was ~85% for the other data set. These results show big room for improvement.
Based on the identified trends and experiences from our experiments, we
contribute a detailed discussion of promising future research.
Local electricity markets may emerge as a mechanism for managing the increasing numbers of distributed generation resources. However, in order to be successful, these markets will heavily rely on accurate forecasts of consumption and/or production from its participants. This issue has not been widely researched in the context of such markets, and it presents a clear roadblock for wide market adoption as forecasting errors result in penalty and opportunity costs. Forecasting individual demand often leads to large errors. However, these errors can be reduced through the creation of groups, however small. In the work presented here, we investigate the relationship between group size and forecast accuracy, based on Seasonal-Naïve and Holt-Winters algorithms, and the effects forecasting errors have on trading in an intra-day local electricity market composed of consumers and “prosumers.” Furthermore, we measure the performance of a group participating on the market, and demonstrate how it can be a mitigating strategy to enable even highly unpredictable individuals to reduce their costs, and participate more effectively in the market.
With the technological advancement in the fields of advanced metering infrastructure (AMI), a massive amount of customers’
electricity consumption data is collected. Meanwhile, the energy providers need to make informed decisions based on power
consumption strategy of demand side to reduce overall operational cost. So how to generate demand side load data based on
historical energy consumption data or customer attribute is a pressing issue. In this paper, we propose a data-driven approach to generate new power consumption data based on intrinsic property of load pattern learnt from demand side using conditional
generative adversarial networks (cGANs), which is based on two interconnected deep neural networks known as generator and
discriminator. By using several representative labels from the responded surveys and the load data from demand side to train the
models, the generator is able to generate realistic power consumption data by given labels which can be used for energy management and e main scope of this paper is to assess the feasibility of using the heat demand – outdoor temperature function for heat demand.
Transactive coordination and control has recently emerged as a new methodology to facilitate large-scale integration of various distributed energy resources into power distribution systems. Various transactive energy systems (TESs) are being developed for power system problems involving self-interested asset owners with privacy concerns. However, there has been very limited work on evaluating and comparing their performance. In this paper, a systematic performance evaluation procedure is presented for the comparison among different TESs in terms of their performance under practical conditions such as information uncertainties, network effects, individual rationality and so on. Both quantitative and qualitative performance metrics are proposed. This procedure is then applied to evaluate and compare two existing TESs using double-auction market. The detailed case studies also illustrate the performance limitations of double-auction-based TESs, and provide useful insights on the necessary design improvements for practical applications.
This paper proposes a simple empirical scaling law that describes load forecasting accuracy at varying levels of aggregation. We show that for many forecasting methods, aggregating more customers improves the relative forecasting performance up to specific point. Beyond this point, no more improvement in relative performance can be obtained. A benchmarking procedure for applying the scaling law to different forecasting models is presented. The aggregation model is evaluated with year long consumption profiles of over 180 thousand Pacific Gas & Electric customers. A theoretical model based on a bias variance decomposition of the forecast error is used to model the Aggregation Error Curves (AECs) that are empirically explored.
Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads. This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better. The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.
The key challenge for household load forecasting lies in the high volatility and uncertainty of load profiles. Traditional methods tend to avoid such uncertainty by load aggregation (to offset uncertainties), customer classification (to cluster uncertainties) and spectral analysis (to filter out uncertainties). This paper, for the first time, aims to directly learn the uncertainty by applying a new breed of machine learning algorithms – deep learning. However simply adding layers in neural networks will cap the forecasting performance due to the occurrence of overfitting. A novel pooling-based deep recurrent neural network (PDRNN) is proposed in this paper which batches a group of customers’ load profiles into a pool of inputs. Essentially the model could address the over-fitting issue by increasing data diversity and volume. This work reports the first attempts to develop a bespoke deep learning application for household load forecasting and achieved preliminary success. The developed method is implemented on Tensorflow deep learning platform and tested on 920 smart metered customers from Ireland. Compared with the state-of-art techniques in household load forecasting, the proposed method outperforms ARIMA by 19.5%, SVR by 13.1% and classical deep RNN by 6.5% in terms of RMSE.
Prosumers are agents that both consume and produce energy. With the growth in small and medium-sized agents using solar photovoltaic panels, smart meters, vehicle-to-grid electric automobiles, home batteries and other ‘smart’ devices, prosuming offers the potential for consumers and vehicle owners to re-evaluate their energy practices. As the number of prosumers increases, the electric utility sector of today is likely to undergo significant changes over the coming decades, offering possibilities for greening of the system, but also bringing many unknowns and risks that need to be identified and managed. To develop strategies for the future, policymakers and planners need knowledge of how prosumers could be integrated effectively and efficiently into competitive electricity markets. Here we identify and discuss three promising potential prosumer markets
related to prosumer grid integration, peer-to-peer models and prosumer community groups. We also caution against optimism by laying out a series of caveats and complexities.
Smart electricity meters are currently deployed in millions of households to collect detailed individual electricity consumption data. Compared with traditional electricity data based on aggregated consumption, smart meter data are much more volatile and less predictable. There is a need within the energy industry for probabilistic forecasts of household electricity consumption to quantify the uncertainty of future electricity demand in order to undertake appropriate planning of generation and distribution. We propose to estimate an additive quantile regression model for a set of quantiles of the future distribution using a boosting procedure. By doing so, we can benefit from flexible and interpretable models, which include an automatic variable selection. We compare our approach with three benchmark methods on both aggregated and disaggregated scales using a smart meter data set collected from 3639 households in Ireland at 30-min intervals over a period of 1.5 years. The empirical results demonstrate that our approach based on quantile regression provides better forecast accuracy for disaggregated demand, while the traditional approach based on a normality assumption (possibly after an appropriate Box-Cox transformation) is a better approximation for aggregated demand. These results are particularly useful since more energy data will become available at the disaggregated level in the future.
Aspirations of grid independence could be achieved by residential power systems connected only to small highly variable loads if overall demand on the network can be accurately anticipated. Absence of the diversity found on networks with larger load cohorts or consistent industrial customers makes such overall load profiles difficult to anticipate on even a short term basis. Here, existing forecasting techniques are employed alongside enhanced classification/clustering models in proposed methods for forecasting demand in a bottom up manner. A Markov chain based sampling technique derived from practice theory of human behavior is proposed as a means of providing a forecast with low computational effort and reduced historical data requirements. The modeling approach proposed does not require seasonal adjustments or environmental data. Forecast and actual demand for a cohort of residential loads over a five-month period are used to evaluate a number of models, as well as demonstrate a significant performance improvement if utilized in an ensemble forecast.
It is expected that energy management systems (EMS) on the demand side can be used as a method for enhancing the capability of balancing supply and demand of a power system under the anticipated increase of renewable energy generation such as photovoltaics (PV). Energy demand and solar radiation must be predicted in order to realize the optimal operation scheduling of demand side appliances by EMS, including heat pump water heaters, PV systems, and solar powered water heaters. This paper presents a day-ahead forecasting method for electricity consumption in a house to contribute to energy management. Ten forecasting methods are examined using real survey data from 35 households over a year in order to verify forecast accuracy. A daily battery operation model is also developed to evaluate the effect of load forecasts.
The recent development of smart meters has allowed the analysis of household electricity consumption in real time. Predicting electricity consumption at such very low scales should help to increase the efficiency of distribution networks and energy pricing. However, this is by no means a trivial task since household-level consumption is much more irregular than at the transmission or distribution levels. In this work, we address the problem of improving consumption forecasting by using the statistical relations between consumption series. This is done both at the household and district scales (hundreds of houses), using various machine learning techniques, such as support vector machine for regression (SVR) and multilayer perceptron (MLP). First, we determine which algorithm is best adapted to each scale, then, we try to find leaders among the time series, to help short-term forecasting. We also improve the forecasting for district consumption by clustering houses according to their consumption profiles.
This paper presents a generic strategy for short-term load forecasting (STLF) based on the support vector regression machines (SVR). Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms. One of the objectives of the proposed strategy is to reduce the operator interaction in the model-building procedure. The proposed use of feature selection algorithms for automatic model input selection and the use of the particle swarm global optimization based technique for the optimization of SVR hyper-parameters reduces the operator interaction. To confirm the effectiveness of the proposed modeling strategy, the model has been trained and tested on two publicly available and well-known load forecasting data sets and compared to the state-of-the-art STLF algorithms yielding improved accuracy.
The electric grid is changing. With the smart grid the demand response (DR) programs will hopefully make the grid more resilient and cost efficient. However, a scheme where consumers can directly participate in demand management requires new efforts for forecasting the electric loads of individual consumers. In this paper we try to find answers to two main questions for forecasting loads for individual consumers: First, can current short term load forecasting (STLF) models work efficiently for forecasting individual households? Second, do the anthropologic and structural variables enhance the forecasting accuracy of individual consumer loads? Our analysis show that a single multi-dimensional model forecasting for all houses using anthropologic and structural data variables is more efficient than a forecast based on traditional global measures. We have provided an extensive empirical evidence to support our claims.
This empirical paper compares the accuracy of six univariate methods for short-term electricity demand forecasting for lead times up to a day ahead. The very short lead times are of particular interest as univariate methods are often replaced by multivariate methods for prediction beyond about six hours ahead. The methods considered include the recently proposed exponential smoothing method for double seasonality and a new method based on principal component analysis (PCA). The methods are compared using a time series of hourly demand for Rio de Janeiro and a series of half-hourly demand for England and Wales. The PCA method performed well, but, overall, the best results were achieved with the exponential smoothing method, leading us to conclude that simpler and more robust methods, which require little domain knowledge, can outperform more complex alternatives.
Forecasting: Principles and Practice
- R J Hyndman
- G Athanasopoulos