Conference PaperPDF Available

Short-Term Load and Price Forecasting based on Improved Convolutional Neural Network

Authors:
A preview of the PDF is not available
... Similarly, peak electricity demand can be observed in monthly Buddhists' holiday called "Poya day". The unique and unsteady peak demand pattern is shown because of the Sinhalese and Tamil cultural festival season called as "New Year Season" during April and Buddhists' religious activities for "Wesak Poya" in May [8]. It is necessary to clean and scale data to zero mean and unit variance under the preprocessing step, after collecting the data of highly correlated factors to the electricity demand forecasting [9]. ...
Conference Paper
Full-text available
Most of the time electricity cannot be stored, it should be generated as soon as it is demanded. Therefore, electricity demand forecasting is a vital process in the planning of electricity industry and the operation of electric power systems. Two major scenarios should be considered when forecasting the electricity demand. They are short term and long term forecasting scenarios. The short term scenario is more critical since many features have to be considered. In this research study, deep learning techniques such as Recurrent Neural Network(RNN), Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) were considered for electricity demand forecasting of Sri Lankan demand profile. Further, the results of deep learning approaches were compared with traditional techniques such as Linear Regression, Lasso Regression, Light Gradient Boosting Model (LGBM) and Random Forest Regressor. It was found from our studies that LSTM based approach performs better than other approaches.
Thesis
Full-text available
This thesis examines the use of blockchain technology with the Electric Vehicles (EVs) to tackle different issues related to the existing systems like privacy, security, lack of trust, etc., and to promote transparency, data immutability and tamper proof nature. Moreover, in this study, a new and improved charging strategy, termed as Mobile vehicle-to-Vehicle (M2V) charging strategy, is used to charge the EVs. It is further compared with conventional Vehicle-to-Vehicle (V2V) and Grid-to-Vehicle (G2V) charging strategies to prove its efficacy. In the proposed work, the charging of vehicles is done in a Peer-to-Peer (P2P) manner to remove the intermediary parties and deal with the issues related to them. Moreover, to store the data related to traffic, roads and weather conditions, a Transport System Information Unit (TSIU) is used, which helps in reducing road congestion and minimizing road side accidents. In TSIU, InterPlanetary File System (IPFS) is utilized to store the data in a secured manner. Furthermore, mathematical formulation of the total charging cost, the shortest distance between EVs and charging entities, and the time taken to traverse the shortest distance and to charge the vehicles is done using real time data of EVs. The phenomena of range anxiety and coordination at the crossroads are also dealt with in the study. Moving ahead, edge service providers are introduced to ensure efficient service provisioning. These nodes ensure smooth communication with EVs for successful service provisioning. A caching system is also introduced at the edge nodes to store frequently used services. The power flow and the related energy losses for G2V, V2V and M2V charging strategies are also discussed in this work. In addition, an incentive provisioning mechanism is proposed on the basis of timely delivery of credible messages, which further promotes users’ participation. Furthermore, a hybrid blockchain based vehicular announcement scheme is proposed through which secure and reliable announcement dissemination is realized. In addition, IOTA Tangle is used, which ensures decentralization of the system. The real identities of the vehicles are hidden using the pseudo identities generated through an Elliptic Curve Cryptography (ECC) based pseudonym update mechanism. Moreover, the lightweight trustworthiness verification of vehicles is performed using a Cuckoo Filter (CF). It also prevents revealing the reputation values given to the vehicles upon information dissemination. To reduce the delays caused due to inefficient digital signature verification, transactions are verified in the form of batches. Furthermore, a blockchain based revocation transparency enabled data-oriented trust model is proposed. Password Authenticated Key Exchange by Juggling (J-PAKE) scheme is used in the proposed model to enable mutual authentication. To prevent collusion attacks, message credibility check is performed using Real-time Message Content Validation (RMCV) scheme. Furthermore, K-anonymity algorithm is used to anonymize the reputation data and prevent privacy leakage by restricting the identification of the predictable patterns present in the reputation data. To enable revocation transparency, a Proof of Revocation (PoR) is designed for the revoked vehicles. The vehicle records are stored in IPFS. To enhance the chances of correct information dissemination, incentives are provided to the vehicles using a reputation based incentive mechanism. To check the robustness of the proposed model, attacker models are designed and tested against different attacks including selfish mining attack, double spending attack, etc. To prove the efficiency of the proposed work, extensive simulations are performed. The simulation results prove that the proposed study achieves high success in making EVs energy efficient, secure and robust. Furthermore, the security analysis of the smart contracts used in the proposed work is performed using Oyente, which exhibits the secure nature of the proposed work.
Research Proposal
Full-text available
In this work, an encyclopedic study of the blockchain based energy trading, data trading and sharing, and incentive mechanisms, used in various fields of life like energy, finance, business, data trading, healthcare, etc., is presented. The study critically analyzes different survey papers and ranks them using a recency score. This work also presents major blockchain related future research perspectives, which provide solid working directions to the research community. The use of blockchain technology with the Electric Vehicles (EVs) is also discussed to tackle different issues related to existing systems, such as privacy, security, lack of trust, etc., and to promote transparency, data immutability and tamper proof nature. Moreover, in this study, a new and improved charging strategy, termed as Mobile vehicle-to-Vehicle (M2V) charging strategy, is used to charge the EVs. It is further compared with conventional Vehicle-to-Vehicle (V2V) and Grid-to-Vehicle (G2V) charging strategies to prove its efficacy. In the proposed work, the charging of vehicles is done in a Peer-to-Peer (P2P) manner to remove the intermediary parties and deal with the issues related to them. Moreover, to store the data related to traffic, roads and weather conditions, a Transport System Information Unit (TSIU) is used, which helps in reducing road congestion and minimizing road side accidents. In TSIU, the data is stored in InterPlanetary File System (IPFS). Furthermore, mathematical formulation of the total charging cost, the shortest distance between EVs and charging entities, time taken to traverse the shortest distance and to charge the vehicles is done using real time data of EVs. The phenomena of range anxiety and coordination at the crossroads are also dealt with in the study. Moving ahead, edge service providers (edge nodes) are introduced to ensure efficient service provisioning. A caching system is also introduced at the edge nodes to store frequently used services. The power flow and the related energy losses for G2V, V2V and M2V charging strategies are also discussed in this work. In addition, an incentive provisioning mechanism is proposed on the basis of timely delivery of credible messages, which further promotes users’ participation. To check the robustness of the proposed model, an attacker model is designed and tested against different attacks including selfish mining attack. In future, the proposed model robustness will be tested against more attacks. To prove the efficiency of the proposed work, simulations will be performed. Moreover, the security analysis of the proposed work will also be done using Oyente.
Article
Full-text available
With the continuous development of global science and technology industry, the demand for power is increasing, so short-term power load forecasting is particularly important. At present, a large number of load forecasting models have been applied to short-term load forecasting, but most of them ignore the error accumulation in the iterative training process. To solve this problem, this paper proposes a combined measurement model which combines stacked bidirectional gated recurrent unit (SBiGRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and error correction. In the first stage, SBiGRU model is established to study the time series characteristics of load series under the influence of temperature and holiday types. The error series generated in the prediction process of SBiGRU model reflects the error characteristics of load series; In the second stage, the error sequence is decomposed into several intrinsic mode functions (IMF) components and trend components by CEEMDAN algorithm. The SBiGRU model is established again for each component to learn and predict, and the predicted values of all components are reconstructed to get the error prediction results; Finally, sum the two-stage prediction results to correct the error. The accuracy of SBiGRU-CEEMDAN-SBiGRU combination model is evaluated by two public power load data. The experimental results show that the SBiGRU-CEEMDAN-SBiGRU combination model has better accuracy and stability than the traditional model.
Article
Full-text available
In this paper, we design a controller for home energy management based on following meta-heuristic algorithms: teaching learning-based optimization (TLBO), genetic algorithm (GA), firefly algorithm (FA) and optimal stopping rule (OSR) theory. The principal goal of designing this controller is to reduce the energy consumption of residential sectors while reducing consumer’s electricity bill and maximizing user comfort. Additionally, we propose three hybrid schemes OSR-GA, OSR-TLBO and OSR-FA, by combining the best features of existing algorithms. We have also optimized the desired parameters: peak to average ratio, energy consumption, cost, and user comfort (appliance waiting time) for 20, 50, 100 and 200 heterogeneous homes in two steps. In the first step, we obtain the optimal scheduling of home appliances implementing our aforementioned hybrid schemes for single and multiple homes while considering user preferences and threshold base policy. In the second step, we formulate our problem through chance constrained optimization. Simulation results show that proposed hybrid scheduling schemes outperformed for single and multiple homes and they shift the consumer load demand exceeding a predefined threshold to the hours where the electricity price is low thus following the threshold base policy. This helps to reduce electricity cost while considering the comfort of a user by minimizing delay and peak to average ratio. In addition, chance-constrained optimization is used to ensure the scheduling of appliances while considering the uncertainties of a load hence smoothing the load curtailment. The major focus is to keep the appliances power consumption within the power constraint, while keeping power consumption below a pre-defined acceptable level. Moreover, the feasible regions of appliances electricity consumption are calculated which show the relationship between cost and energy consumption and cost and waiting time.
Article
Full-text available
In the recent years, the demand for electricity is growing rapidly and the accuracy of load demand forecast is crucial for providing the least cost and risk management plans. In the competitive power market, utilities tend to maintain their generation reserve close to the minimum required by the system operator. Load forecasting has many applications including energy purchasing and generation, load switching, contract evaluation, and infrastructure development. This creates the requirement for an accurate day-ahead instantaneous load forecast. Therefore, in this paper a novel methodology is proposed for solving the short-term load forecasting problem using the radial basis function neural networks (RBFNNs) considering the weather factors such as temperature and humidity. The RBFNN has the advantage of handling augment new training data without requiring the retraining. The hidden layer and linear output layer of RBFNNs has the ability of learning the connection weights efficiently without trapping in the local optimum. The simulation results are performed on Pennsylvania–New Jersey–Maryland (PJM) interconnection and the obtained results are promising and accurate. The simulation studies show that the forecast results are reliable, specifically when weather factors are included in the training data.
Article
Full-text available
IIn this paper, we propose a home energy management system which employs load shifting strategy of demand side management to optimize the energy consumption patterns of a smart home. It aims to manage the load demand in an efficient way to minimize electricity cost and peak to average ratio while maintaining user comfort through coordination among home appliances. In order to meet the load demand of electricity consumers, we schedule the load in day-ahead and real-time basis. We propose a fitness criterion for proposed hybrid technique which helps in balancing the load during On-peak and Off-peak hours. Moreover, for real-time rescheduling, we present the concept of coordination among home appliances. This helps the scheduler to optimally decide the ON/OFF status of appliances in order to reduce the waiting time of appliance. For this purpose, we formulate our realtime rescheduling problem as knapsack problem and solve it through dynamic programming. This study also evaluates the behavior of the proposed technique for three pricing schemes including: time of use, real-time pricing and critical peak pricing. Simulation results illustrate the significance of the proposed optimization technique with 95% confidence interval.
Article
Full-text available
Nowadays, electricity plays a vital role in national economic and social development. Accurate load forecasting can help power companies to secure electricity supply and scheduling and reduce wastes since electricity is difficult to store. In this paper, we propose a novel Deep Neural Network architecture for short term load forecasting. We integrate multiple types of input features by using appropriate neural network components to process each of them. We use Convolutional Neural Network components to extract rich features from historical load sequence and use Recurrent Components to model the implicit dynamics. In addition, we use Dense layers to transform other types of features. Experimental results on a large data set containing hourly loads of a North China city show the superiority of our method. Moreover, the proposed method is quite flexible and can be applied to other time series prediction tasks.
Article
Full-text available
Leveraging smart metering solutions to support energy efficiency on the individual household level poses novel research challenges in monitoring usage and providing accurate load forecasting. Forecasting electricity usage is an especially important component that can provide intelligence to smart meters. In this paper, we propose an enhanced approach for load forecasting at the household level. The impacts of residents' daily activities and appliance usages on the power consumption of the entire household are incorporated to improve the accuracy of the forecasting model. The contributions of this paper are threefold: (1) we addressed short-term electricity load forecasting for 24 hours ahead, not on the aggregate but on the individual household level, which fits into the Residential Power Load Forecasting (RPLF) methods; (2) for the forecasting, we utilized a household specific dataset of behaviors that influence power consumption, which was derived using segmentation and sequence mining algorithms; and (3) an extensive load forecasting study using different forecasting algorithms enhanced by the household activity patterns was undertaken.
Article
The ever-increasing load demand of the residential sector gives rise to concerns such as-decreased quality of service and increased demand-supply gap in the electricity market. To tackle these concerns, the utilities are switching to smart grids (SGs) to manage the demand response (DR) of the connected loads. However, most of the existing DR management schemes have not explored the concept of data analytics for reducing peak load while taking consumer constraints into account. To address this issue, a novel data analytical demand response (DADR) management scheme for residential load is proposed in this paper with an aim to reduce the peak load demand. The proposed scheme is primarily based on the analysis of consumers' consumption data gathered from smart homes (SHs) for which factors such as-appliance adjustment factor, appliance priority index, etc. have been considered. Based on these factors, different algorithms with respect to consumer's and utility's perspective have been proposed to take DR. In addition to it, an incentive scheme has also been presented to increase the consumers' participation in the proposed scheme. The results obtained show that it efficiently reduces the peak load at the grid by a great extent. Moreover, it also increases the savings of the consumers by reducing their overall electricity bills.