Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning
- 2 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 14 (4) , 3259-3270
Abstract
Prediction intervals (PIs) offer an effective tool for quantifying uncertainty of loads in distribution systems. The traditional central PIs cannot adapt well to skewed distributions, and their offline training fashion is vulnerable to the unforeseen change in future load patterns. Therefore, we propose an optimal PI estimation approach, which is online and adaptive to different data distributions by adaptively determining symmetric or asymmetric probability proportion pairs for quantiles of PIs’ bounds. It relies on the online learning ability of reinforcement learning (RL) to integrate the two online tasks, i.e., the adaptive selection of probability proportion pairs and quantile predictions, both of which are modeled by neural networks. As such, the quality of quantiles-formed PI can guide the selection process of optimal probability proportion pairs, which forms a closed loop to improve PIs’ quality. Furthermore, to improve the learning efficiency of quantile forecasts, a prioritized experience replay (PER) strategy is proposed for online quantile regression processes. Case studies on both load and net load demonstrate that the proposed method can better adapt to data distribution compared with online central PIs method. Compared with offline-trained methods, it obtains PIs with better quality and is more robust against concept drift.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U1866206)
This publication has 26 references indexed in Scilit:
- Probabilistic gradient boosting machines for GEFCom2014 wind forecastingInternational Journal of Forecasting, 2016
- Economic dispatch of power systems with virtual power plant based interval optimization methodCSEE Journal of Power and Energy Systems, 2016
- Probabilistic Load Forecasting via Quantile Regression Averaging on Sister ForecastsIEEE Transactions on Smart Grid, 2015
- Day-Ahead Congestion Management in Distribution Systems Through Household Demand Response and Distribution Congestion PricesIEEE Transactions on Smart Grid, 2014
- Probabilistic ForecastingAnnual Review of Statistics and Its Application, 2014
- Probabilistic Forecasting of Wind Power Generation Using Extreme Learning MachineIEEE Transactions on Power Systems, 2013
- Optimal Prediction Intervals of Wind Power GenerationIEEE Transactions on Power Systems, 2013
- Comprehensive Review of Neural Network-Based Prediction Intervals and New AdvancesIEEE Transactions on Neural Networks, 2011
- Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction IntervalsIEEE Transactions on Neural Networks, 2010
- On the Convergence of Stochastic Iterative Dynamic Programming AlgorithmsNeural Computation, 1994