Online Optimal Power Scheduling of a Microgrid via Imitation Learning

This paper investigates the economic operation of a microgrid with a variety of distributed energy resources. Given the intermittency of renewable generation and the high stochasticity in market prices and loads, online power scheduling approaches are generally preferred for their uncertainty handli...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on smart grid 2022-03, Vol.13 (2), p.861-876
Main Authors: Gao, Shuhua, Xiang, Cheng, Yu, Ming, Tan, Kuan Tak, Lee, Tong Heng
Format: Article
Language:English
Subjects:
Artificial neural networks
Costs
Distributed generation
Energy management
Energy sources
Forecasting
imitation learning
Integer programming
Linear programming
Machine learning
Microgrid
Microgrids
Mixed integer
online scheduling
Optimization
Predictive control
Pricing
reinforcement learning
Scheduling
Training
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper investigates the economic operation of a microgrid with a variety of distributed energy resources. Given the intermittency of renewable generation and the high stochasticity in market prices and loads, online power scheduling approaches are generally preferred for their uncertainty handling capacity by exploiting real-time information. Traditional online methods like model predictive control require a separate forecaster, while recent reinforcement learning (RL) based methods can learn a policy from historical data directly. However, RL methods often suffer from dimensionality issues arising from the continuous state and action space, complex constraints, and sluggish training. We propose a novel data-driven online approach based on imitation learning instead, which overcomes these limitations through problem decomposition, and more importantly, mimicking a mixed-integer linear programming (MILP) solver rather than learn from scratch. The policy demonstrated by the MILP expert is approximated with a deep neural network. Our approach reduces the training time dramatically even in a small microgrid, achieving a 17-times speedup in contrast to a Q-learning method. Moreover, the operation cost achieved by our approach subject to various uncertainties is close to the theoretical minimum value. Extensive numerical studies on both simulated and real-world data highlight the performance advantage of the proposed approach as compared to other common methods.
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2021.3122570