Attentive Knowledge Transfer for Short-term Load Forecasting

The modern power system is transitioning towards increasing penetration of renewable energy generation and demand from different types of electrical appliances. With this transition, residential load forecasting, especially short-term load forecasting (STLF), is becoming more and more challenging and important. Accurate short-term load forecasting can help improve energy dispatching efficiency and, as a consequence, reduce overall power system operation cost. Most current load forecasting algorithms assume that there is a large amount of training data available upon which to learn a reliable load forecasting model. However, this assumption can be challenging for real-world applications. In this work, we first propose the use of transfer learning and an attention mechanism to improve short-term load forecasting for a target domain with only a limited amount of available data. Furthermore, we extend the proposed method to utilize heterogeneous features which enables the approach to deal with more complex scenarios in the real world. Experimental results using real-world data sets show that the proposed methods can improve forecasting accuracy by a large margin over several existing baselines.

[1]  B. Boulet,et al.  Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting , 2022, AAAI.

[2]  Gregory Dudek,et al.  Active Deep Multi-task Learning for Forecasting Short-Term Loads , 2022, ICC 2022 - IEEE International Conference on Communications.

[3]  Yi Tian Xu,et al.  Short-term Load Forecasting with Deep Boosting Transfer Regression , 2022, ICC 2022 - IEEE International Conference on Communications.

[4]  Di Wu,et al.  Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks , 2021, IJCAI.

[5]  Benoit Boulet,et al.  Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks , 2021, IEEE Transactions on Smart Grid.

[6]  Damla Turgut,et al.  Short-Term Load Forecasting for Smart Home Appliances with Sequence to Sequence Learning , 2021, ICC 2021 - IEEE International Conference on Communications.

[7]  Di Wu,et al.  Ensemble Learning for Charging Load Forecasting of Electric Vehicle Charging Stations , 2020, 2020 IEEE Electric Power and Energy Conference (EPEC).

[8]  Eenjun Hwang,et al.  Monthly Electric Load Forecasting Using Transfer Learning for Smart Cities , 2020, Sustainability.

[9]  Di Wu,et al.  EV Charging Management with ANN-Based Electricity Price Forecasting , 2020, 2020 IEEE Transportation Electrification Conference & Expo (ITEC).

[10]  Doina Precup,et al.  Multiple Kernel Learning-Based Transfer Regression for Electric Load Forecasting , 2020, IEEE Transactions on Smart Grid.

[11]  Hui Xiong,et al.  A Comprehensive Survey on Transfer Learning , 2019, Proceedings of the IEEE.

[12]  Di Wu,et al.  A Q-Learning Based Charging Scheduling Scheme for Electric Vehicles , 2019, 2019 IEEE Transportation Electrification Conference and Expo (ITEC).

[13]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[14]  Di LU,et al.  Online Gaussian Process Regression for Short-term Probabilistic Interval Load Prediction , 2018, 2018 International Conference on Power System Technology (POWERCON).

[15]  Li Yang,et al.  A Comparative Study of Ensemble Support Vector Regression Methods for Short-term Load Forecasting , 2018, 2018 5th International Conference on Systems and Informatics (ICSAI).

[16]  Pitshou Bokoro,et al.  Load Forecasting Using Statistical Time Series Model in a Medium Voltage Distribution Network , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[17]  Nakyoung Kim,et al.  LSTM Based Short-term Electricity Consumption Forecast with Daily Load Profile Sequences , 2018, 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).

[18]  Jun Hu,et al.  Short-Term Load Forecasting With Deep Residual Networks , 2018, IEEE Transactions on Smart Grid.

[19]  Joakim Widén,et al.  Residential probabilistic load forecasting: A method using Gaussian process designed for electric load data , 2018 .

[20]  Di Wu,et al.  Boosting Based Multiple Kernel Learning and Transfer Regression for Electricity Load Forecasting , 2017, ECML/PKDD.

[21]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[22]  Weilin Li,et al.  Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings , 2017 .

[23]  Di Wu,et al.  Two-Stage Energy Management for Office Buildings With Workplace EV Charging and Renewable Energy , 2017, IEEE Transactions on Transportation Electrification.

[24]  Balaraman Ravindran,et al.  $A^2T$: Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources , 2015 .

[25]  Jinghan He,et al.  A two-stage random forest method for short-term load forecasting , 2015, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[26]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[27]  Di Wu,et al.  Neighborhood level network aware electric vehicle charging management with mixed control strategy , 2014, 2014 IEEE International Electric Vehicle Conference (IEVC).

[28]  Vladimir Ceperic,et al.  A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines , 2013, IEEE Transactions on Power Systems.

[29]  Tao Liu,et al.  High frequency short-term demand forecasting model for distribution power grid based on ARIMA , 2012, 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE).

[30]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[31]  Qia Ding,et al.  Long-Term Load Forecast Using Decision Tree Method , 2006, 2006 IEEE PES Power Systems Conference and Exposition.

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

[33]  Doina Precup,et al.  Optimizing Home Energy Management and Electric Vehicle Charging with Reinforcement Learning , 2018 .