A Group Resident Daily Load Forecasting Method Fusing Self-Attention Mechanism Based on Load Clustering

Daily load forecasting is the basis of the economic and safe operation of a power grid. Accurate prediction results can improve the matching of microgrid energy storage capacity allocation. With the popularization of smart meters, the interaction between residential electricity demand and sources and networks is increasing, and massive data are generated at the same time. Previous forecasting methods suffer from poor targeting and high noise. They cannot make full use of the important information of the load data. This paper proposes a new framework for daily load forecasting of group residents. Firstly, we use the singular value decomposition to address the problem of high dimensions of residential electricity data. Meanwhile, we apply a K-Shape-based group residential load clustering method to obtain the typical residential load data. Secondly, we introduce an empirical mode decomposition method to address the problem of high noise of residential load data. Finally, we propose a Bi-LSTM-Attention model for residential daily load forecasting. This method can make full use of the contextual information and the important information of the daily load of group residents. The experiments conducted on a real data set of a power grid show that our method achieves excellent improvements on five prediction error indicators, such as MAPE, which are significantly smaller than the compared baseline methods.

[1]  J. Chanussot,et al.  UIU-Net: U-Net in U-Net for Infrared Small Object Detection , 2022, IEEE Transactions on Image Processing.

[2]  Jie Gu,et al.  An explainable framework for load forecasting of a regional integrated energy system based on coupled features and multi-task learning , 2022, Protection and Control of Modern Power Systems.

[3]  Lei Wang,et al.  Self-Attention-Based Short-Term Load Forecasting Considering Demand-Side Management , 2022, Energies.

[4]  M. Hammad,et al.  Deep Learning Techniques for Smart Meter Data Analytics: A Review , 2022, SN Computer Science.

[5]  P. Ray,et al.  An Effect of Machine Learning Techniques in Electrical Load forecasting and Optimization of Renewable Energy Sources , 2022, Journal of The Institution of Engineers (India): Series B.

[6]  S. Mariano,et al.  Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting , 2021, Energies.

[7]  Jing Shi,et al.  A combined deep learning load forecasting model of single household resident user considering multi-time scale electricity consumption behavior , 2021, Applied Energy.

[8]  Syed Mohsin Ali,et al.  Deep sequence to sequence Bi-LSTM neural networks for day-ahead peak load forecasting , 2021, Expert Syst. Appl..

[9]  Qian Ai,et al.  A Parallel Electrical Optimized Load Forecasting Method Based on Quasi-Recurrent Neural Network , 2021 .

[10]  Yiqun Zhong,et al.  Study on power consumption load forecast based on K-means clustering and FCM–BP model , 2020 .

[11]  Pengfei Li,et al.  Ultra-Short-Term Load Demand Forecast Model Framework Based on Deep Learning , 2020, Energies.

[12]  Adela Bâra,et al.  Ultra-short-term forecasting for photovoltaic power plants and real-time key performance indicators analysis with big data solutions. Two case studies - PV Agigea and PV Giurgiu located in Romania , 2020, Comput. Ind..

[13]  Taher Niknam,et al.  A novel electrical net-load forecasting model based on deep neural networks and wavelet transform integration , 2020 .

[14]  Lianru Gao,et al.  Graph Convolutional Networks for Hyperspectral Image Classification , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Lianru Gao,et al.  Coupled Convolutional Neural Network With Adaptive Response Function Learning for Unsupervised Hyperspectral Super Resolution , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Xin Liu,et al.  A comparative study of the data-driven day-ahead hourly provincial load forecasting methods: From classical data mining to deep learning , 2020 .

[17]  Ning Zhang,et al.  Comparison of three short-term load forecast models in Southern California , 2019 .

[18]  Weijun Hong,et al.  Deep ensemble learning based probabilistic load forecasting in smart grids , 2019 .

[19]  Sung Wook Baik,et al.  Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM , 2019, Applied Sciences.

[20]  Shanlin Yang,et al.  Time-of-use pricing model based on power supply chain for user-side microgrid , 2019, Applied Energy.

[21]  Yong Yu,et al.  A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures , 2019, Neural Computation.

[22]  Xiao Jing,et al.  Short-Term Electricity Load Forecasting Model Based on EMD-GRU with Feature Selection , 2019, Energies.

[23]  Saifur Rahman,et al.  Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques , 2019, Applied Energy.

[24]  Boning Zhang,et al.  Foreign exchange rates forecasting with an EMD-LSTM neural networks model , 2018, Journal of Physics: Conference Series.

[25]  Shahaboddin Shamshirband,et al.  Forecasting of consumers heat load in district heating systems using the support vector machine with a discrete wavelet transform algorithm , 2015 .

[26]  Luis Gravano,et al.  k-Shape: Efficient and Accurate Clustering of Time Series , 2015, SIGMOD Conference.

[27]  Farshid Keynia,et al.  Short-Term Load Forecast of Microgrids by a New Bilevel Prediction Strategy , 2010, IEEE Transactions on Smart Grid.

[28]  Y. H. Song,et al.  Wavelet transform and neural networks for short-term electrical load forecasting , 2000 .

[29]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[30]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[31]  James V. Hansen,et al.  Neural networks and traditional time series methods: a synergistic combination in state economic forecasts , 1997, IEEE Trans. Neural Networks.

[32]  G. W. Stewart,et al.  On the Early History of the Singular Value Decomposition , 1993, SIAM Rev..

[33]  Zulfiqar Ahmad Khan,et al.  Efficient Short-Term Electricity Load Forecasting for Effective Energy Management , 2022, Sustainable Energy Technologies and Assessments.

[34]  Yun Liu,et al.  A Hybrid Short-Term Load Forecasting Model Based on Improved Fuzzy C-Means Clustering, Random Forest and Deep Neural Networks , 2021, IEEE Access.

[35]  Ai Qian,et al.  Present Situation of Research on Microgrid and Its Application Prospects in China , 2008 .

[36]  D. Kalman.  A Singularly Valuable Decomposition: The SVD of a Matrix , 1996 .