A New Self-Learning Optimization Management Scheme for Smart Grid Systems

This paper presents a new energy optimization management scheme for the smart grid system (SGS), which not only considers the inclusion of renewable energy in energy management, but also considers the feedback sale of redundant renewable energy to the grid, so as to obtain better optimization management results and avoid energy waste. A new performance index function is constructed, which aims to save users’ electricity costs and protect energy storage batteries. We construct a periodic iterative self-learning method based on the characteristics that the relevant data of SGS is approximately periodic. The proposed self-learning optimization method is based on adaptive dynamic programming (ADP). The initial iterative control law is obtained by pre-training, and the designed method can be realized by neural networks. Simulation experiments are carried out by using the relevant data of SGS for four weeks. The experimental results show that the new energy management scheme can help users save a lot of electricity costs, and is more effective than some common methods.