OICC Press International Journal of Energy and Environmental Engineering 2251-6832 15 03 (September 2024) 2024 09 30 Research on Cooperative Optimal Configuration of Distributed Energy Storage System and Renewable Energy 10.57647/ijeee.2024.1503.14 EN Wang Xianchun State Grid Hengshui Electric Power Supply Company, Hengshui 053300, Hebei , China Gao Lijuan State Grid Hengshui Electric Power Supply Company, Hengshui 053300, Hebei , China Yang Haiyue State Grid Hengshui Electric Power Supply Company, Hengshui 053300, Hebei , China; Hengshui Electric Power Design Co. , Ltd.，Hengshui 053300, Hebei, China Gao Bing State Grid Hengshui Electric Power Supply Company, Hengshui 053300, Hebei , China Zhang Kang State Grid Hengshui Electric Power Supply Company, Hengshui 053300, Hebei , China Journal Article 2024 09 30 The intermittency, volatility, and intrinsic unpredictability of renewable energy sources provide significant problems to the dependable operation of power grids, especially as these sources are becoming widely available. An essential resource for improving the power grid's flexibility, absorbing a large amount of additional energy, and meeting the dynamic demand-supply balance is energy storage. Energy storage is still somewhat expensive, and finding the best way to set it up is the main challenge right now. Distributed generation, a source of grid energy, is becoming more significant in the distribution network as part of the overall trend toward green energy growth. Distributed generating on a massive scale introduces uncertainty and unpredictability, which threatens distribution network dependability and stability. In order to mitigate the negative effects of dispersed generation and maximize the positive effects on distribution network operations, this article investigates the optimal design of energy storage systems. It provides a reasonable analysis of the possibility of collaboration to increase stability and profitability by building a mathematical model of a distributed generating and energy storage system. According to the operational data, distributed generation exhibits seasonal traits, and the scenario reduction approach groups together a collection of common daily scenarios for spring, summer, fall, and winter and clustered using K-means clustering technique. We solve the optimum building planning problem using an objective function and limitations based on the IEEE 33-bus distribution network using Deep Neural Networks (DNNs). Throughout the year, there are four distinct configurations for energy storage. But in order to limit the impact of dispersed generations, it is generally closed. Finally, it suggests some directions for distribution network expansion in the future and summarizes the paper's operations.