Research on Data Fusion Optimization Model of Mobile Energy Storage Equipment for User-side Services

This paper proposes an innovative data fusion optimization model based on deep neural network, which aims to improve the service quality of mobile energy storage equipment on the user side by effectively integrating multi-source data (such as battery charging and discharging data, user demand data and climate data). First, this paper designs an adaptive weighted data fusion strategy that can dynamically adjust the weights of each data source, strengthen the influence of key information, and reduce the interference of noise data on decision-making. Secondly, combined with multi-objective optimization theory, a framework including multiple optimization objectives such as charging and discharging efficiency, battery life and service stability is proposed. The algorithm simulates complex data in the actual operating environment and performs efficient parameter adjustment and optimization. The proposed algorithm has obvious advantages in improving charging and discharging efficiency, extending battery life and shortening response time. The optimized charging and discharging efficiency are improved by 15%, service stability is improved by 10%, and response time is reduced by 20%.