Machine Learning Based Optimization Model for Energy Management of Energy Storage System for Large Industrial Park

Abstract

Renewable energy represented by wind energy and photovoltaic energy is used for energy structure adjustment to solve the energy and environmental problems. However, wind or photovoltaic power generation is unstable which caused by environmental impact. Energy storage is an important method to eliminate the instability, and lithium batteries are an increasingly mature technique. If the capacity is too large, it would cause waste and cost would increase, but too small capacity cannot schedule well. At the same time, the size of energy storage capacity is also constrained by power consumption, whereas large-scale industrial power consumption is random and non-periodic. This is a complex problem which needs a model that can not only dispatch but also give a reasonable storage capacity. This paper proposes a model considering the cycle life of a lithium battery and the installation parameters of the battery, and the electricity consumption data and photovoltaic power generation data of an industrial park was used to establish an energy management model. The energy management system aimed to reduce operating costs and obtain optimal energy storage capacity, which is constrained by lithium battery performance and grid demand. With the operational cost and reasonable battery capacity as the optimization objectives, the Deep Deterministic Policy Gradient (DDPG) method, the greedy dynamic programming algorithm, and the genetic algorithm (GA) were adopted, where the performance of lithium battery and the requirement of power grid were the constraints. The simulation results show that compared with the current forms of energy, the three energy management methods reduced the cost of capacity and operating of the energy storage system by 18.9%, 36.1%, and 35.9%, respectively.