ThesisPDF Available

Data Analytics based Efficient Energy Management in Smart Grids

Authors:

Abstract and Figures

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.
Content may be subject to copyright.
A preview of the PDF is not available
ResearchGate has not been able to resolve any citations for this publication.
Full-text available
Article
Due to the increase in the number of electricity thieves, the electric utilities are facing problems in providing electricity to their consumers in an efficient way. An accurate Electricity Theft Detection (ETD) is quite challenging due to the inaccurate classification on the imbalance electricity consumption data, the overfitting issues and the High False Positive Rate (FPR) of the existing techniques. Therefore, intensified research is needed to accurately detect the electricity thieves and to recover a huge revenue loss for utility companies. To address the above limitations, this paper presents a new model, which is based on the supervised machine learning techniques and real electricity consumption data. Initially, the electricity data are pre-processed using interpolation, three sigma rule and normalization methods. Since the distribution of labels in the electricity consumption data is imbalanced, an Adasyn algorithm is utilized to address this class imbalance problem. It is used to achieve two objectives. Firstly, it intelligently increases the minority class samples in the data. Secondly, it prevents the model from being biased towards the majority class samples. Afterwards, the balanced data are fed into a Visual Geometry Group (VGG-16) module to detect abnormal patterns in electricity consumption. Finally, a Firefly Algorithm based Extreme Gradient Boosting (FA-XGBoost) technique is exploited for classification. The simulations are conducted to show the performance of our proposed model. Moreover, the state-of-the-art methods are also implemented for comparative analysis, i.e., Support Vector Machine (SVM), Convolution Neural Network (CNN), and Logistic Regression (LR). For validation, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), Receiving Operating Characteristics Area Under Curve (ROC-AUC), and Precision Recall Area Under Curve (PR-AUC) metrics are used. Firstly, the simulation results show that the proposed Adasyn method has improved the performance of FA-XGboost classifier, which has achieved F1-score, precision, and recall of 93.7%, 92.6%, and 97%, respectively. Secondly, the VGG-16 module achieved a higher generalized performance by securing accuracy of 87.2% and 83.5% on training and testing data, respectively. Thirdly, the proposed FA-XGBoost has correctly identified actual electricity thieves, i.e., recall of 97%. Moreover, our model is superior to the other state-of-the-art models in terms of handling the large time series data and accurate classification. These models can be efficiently applied by the utility companies using the real electricity consumption data to identify the electricity thieves and overcome the major revenue losses in power sector.
Full-text available
Article
Multi-microgrid (MMG) system is a new method that concurrently incorporates different types of distributed energy resources, energy storage systems and demand responses to provide reliable and independent electricity for the community. However, MMG system faces the problems of management, real-time economic operations and controls. Therefore, this study proposes an energy management system (EMS) that turns an infinite number of MMGs into a coherence and efficient system, where each MMG can achieve its goals and perspectives. The proposed EMS employs a cooperative game to achieve efficient coordination and operations of the MMG system and also ensures a fair energy cost allocation among members in the coalition. This study considers the energy cost allocation problem when the number of members in the coalition grows exponentially. The energy cost allocation problem is solved using a column generation algorithm. The proposed model includes energy storage systems, demand loads, real-time electricity prices and renewable energy. The estimate of the daily operating cost of the MMG using a proposed deep convolutional neural network (CNN) is analyzed in this study. An optimal scheduling policy to optimize the total daily operating cost of MMG is also proposed. Besides, other existing optimal scheduling policies, such as approximate dynamic programming (ADP), model prediction control (MPC), and greedy policy are considered for the comparison. To evaluate the effectiveness of the proposed model, the real-time electricity prices of the electric reliability council of Texas are used. Simulation results show that each MMG can achieve energy cost savings through a coalition of MMG. Moreover, the proposed optimal policy method achieves MG's daily operating cost reduction up to 87.86% as compared to 79.52% for the MPC method, 73.94% for the greedy policy method and 79.42% for ADP method.
Full-text available
Article
The increasing penetration of renewable energy resources in power systems, represented as random processes, converts the traditional deterministic economic dispatch problem into a stochastic one. To estimate the uncertainty in the stochastic economic dispatch (SED) problem for the purpose of forecasting, the conventional Monte-Carlo (MC) method is prohibitively time-consuming for practical applications. To overcome this problem, we propose a novel Gaussian-process-emulator (GPE)-based approach to quantify the uncertainty in SED considering wind power penetration. Facing high-dimensional real-world data representing the correlated uncertainties from wind generation, a manifold-learning-based Isomap algorithm is proposed to efficiently represent the low-dimensional hidden probabilistic structure of the data. In this low-dimensional latent space, with Latin hypercube sampling (LHS) as the computer experimental design, a GPE is used, for the first time, to serve as a nonparametric, surrogate model for the original complicated SED model. This reduced-order representative allows us to evaluate the economic dispatch solver at sampled values with a negligible computational cost while maintaining a desirable accuracy. Simulation results conducted on the IEEE 118-bus test system reveal the impressive performance of the proposed method.
Full-text available
Article
The study examines the implications of educating prosumers regarding Internet of Things (IoT) use and monitoring to reduce power consumption in the home and encourage energy conservation, sustainable living, and behavior change. Over 15 months, 125 households and household owners received training regarding IoT plug equipment, usage monitoring, and energy reduction. A face to face survey was then conducted regarding power consumption reductions, frequency of monitoring, and user satisfaction compared to the previous year. The study found that participating households used around 5% less energy compared to average households. The reduction rate was found to have increased when more appliances were connected to smart plugs and their power usage was monitored more frequently. Power usage also fell in a greater level when participants were more satisfied with being given smart plugs and related education. Moreover, energy reduction rates increase when smart plugs were used for cooling and heating appliances as well as video, audio, and related devices. The results suggest that this program can be used to reduce energy use, which can be beneficial for smart homes and smart cities. The study demonstrates the importance of education from the perspective of energy conservation and related policies.
Full-text available
Article
Energy saving and emission reduction are the most concerned issues in the world. Objective and accurate prediction of carbon emissions can provide reference and early warning for the implementation of the government’s environmental strategy. Based on the traditional grey Verhulst model, this paper analyzes the main causes of its errors, introduces the extrapolation method to optimize the background value, and uses particle swarm optimization algorithm to optimize its parameters. In order to evaluate the performance of the models, six commonly statistical evaluation indicators are used to compare the new model with other optimization models and grey universal models, and the effect of the new model is basically better than other models. Finally, it is applied to the prediction of carbon dioxide emission of three kinds of coal in China. The results show that the increase of carbon dioxide related to raw coal slows down in 2016–2020, while the increase of carbon dioxide related to clean coal and other washed coal is 12.7097% and 19.2024%, respectively. Therefore, in order to prevent a strong rebound in carbon emissions, China should increase efforts to save energy and reduce emissions, and reduce energy consumption, especially coal consumption.
Article
Forecasts of electricity consumption and peak demand over time horizons of one or two decades are a key element in electric utilities’ meeting their core objective and obligation to ensure reliable and affordable electricity supplies for their customers while complying with a range of energy and environmental regulations and policies. These forecasts are an important input to integrated resource planning (IRP) processes involving utilities, regulators, and other stake-holders. Despite their importance, however, there has been little analysis of long term utility load forecasting accuracy. We conduct a retrospective analysis of long term load forecasts on twelve Western U. S. electric utilities in the mid-2000s to find that most overestimated both energy consumption and peak demand growth. A key reason for this was the use of assumptions that led to an overestimation of economic growth. We find that the complexity of forecast methods and the accuracy of these forecasts are mildly correlated. In addition, sensitivity and risk analysis of load growth and its implications for capacity expansion were not well integrated with subsequent implementation. We review changes in the utilities load forecasting methods over the subsequent decade, and discuss the policy implications of long term load forecast inaccuracy and its underlying causes.
Article
Despite it is essential to distribution network economics, computing energy loss for most major networks is still a tough task due to the absence of full monitoring. Assume the line current follows a normal distribution, the sum of its square is a linear combination of independent chi-square variables, which follows a generalized noncentral chi-square distribution. Based on this finding, we develop a new probability-based analytical method to estimate distribution network energy losses efficiently. The proposed analytical method requires merely the knowledge of mean and variance of line current as well as the line resistance while provides a closed-form formula of the probability characteristics of energy loss. The method is demonstrated on a three-feeder radial network.
Article
An efficient unit commitment planning must consider frequency regulation capacity in the model. Such models are more complicated under a high penetration level of renewable energy because of renewable ramping and uncertainty. This paper addresses these issues in the unit commitment. The proposed model for unit commitment considers uncertainty and ramping of wind power, frequency regulation capacity, spinning reserve, demand response, and pumped-storage hydroelectricity. In order to optimize the costs, the pumped-storage hydroelectricity and demand response program are also included to deal with ramping and uncertainty. The numerical results specify that the arrangement of frequency regulation capacity, pumped-storage system and demand response can effectively tackle both the ramping and uncertainty. The system includes 10-generator with total power equal to 1070 MW and one wind generator with 300 MW power. The initial wind integration level is about 28%. It is verified that decreasing the frequency regulation capacity by 10% reduces wind integration level by 94%. The demand response and pumped-storage increase wind integration level by 10% and 16%; while both together increase wind integration by 25% compared to the initial level. The wind integration level without large wind ramping can be increased up to 200%
Article
This paper presents a comprehensive overview of the potential and outlook of solar energy in Pakistan as a source of renewable and sustainable energy. A detailed energy infrastructure and major reasons behind the power crisis in Pakistan are presented followed by a detailed assessment of solar energy potential. The results obtained from the solar atlas for solar irradiation and PV electricity output show a high potential of solar power throughout the country. An average value of 4.1 kWh/kWp per day is obtained from an installed capacity of 1 KWp. Furthermore, the total estimated potential of solar power in Pakistan is around 2900 GW and its effective use will help in the growth of the country’s economy by reducing the import of fossil fuels. It is foreseen that the present research will help nations develop and utilize solar power in their respective countries efficiently and effectively.