首页|Imitation Learning Based Real-time Decision-making of Microgrid Economic Dispatch Under Multiple Uncertainties
Imitation Learning Based Real-time Decision-making of Microgrid Economic Dispatch Under Multiple Uncertainties
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
万方数据
维普
The intermittency of renewable energy generation,variability of load demand,and stochasticity of market price bring about direct challenges to optimal energy management of microgrids.To cope with these different forms of operation un-certainties,an imitation learning based real-time decision-mak-ing solution for microgrid economic dispatch is proposed.In this solution,the optimal dispatch trajectories obtained by solv-ing the optimal problem using historical deterministic operation patterns are demonstrated as the expert samples for imitation learning.To improve the generalization performance of imita-tion learning and the expressive ability of uncertain variables,a hybrid model combining the unsupervised and supervised learn-ing is utilized.The denoising autoencoder based unsupervised learning model is adopted to enhance the feature extraction of operation patterns.Furthermore,the long short-term memory network based supervised learning model is used to efficiently characterize the mapping between the input space composed of the extracted operation patterns and system state variables and the output space composed of the optimal dispatch trajectories.The numerical simulation results demonstrate that under vari-ous operation uncertainties,the operation cost achieved by the proposed solution is close to the minimum theoretical value.Compared with the traditional model predictive control method and basic clone imitation learning method,the operation cost of the proposed solution is reduced by 6.3%and 2.8%,respective-ly,over a test period of three months.
Energy managementimitation learningdata-driven decisioneconomic dispatch
Wei Dong、Fan Zhang、Meng Li、Xiaolun Fang、Qiang Yang
展开 >
School of Automation,Hangzhou Dianzi University,Hangzhou 310018,China
College of Electri-cal Engineering,Zhejiang University,Hangzhou 310027,China
万方数据
维普
