Intelligent Optimization and Scheduling Method for Distributed Energy Access to Rural Power Grid Based on Deep Learning

Distributed energy sources such as solar and wind power are greatly affected by weather conditions. Their output power has significant fluctuations and intermittency, which poses challenges to the stable operation of the power grid. Therefore, a deep learning-based intelligent optimization scheduling method for distributed energy access to rural power grids is proposed. We construct a strategy set for rural power grid electricity quantity and market electricity price. Under the constraints of expected value and variance, we obtain the limit value of rural power grid load demand and conduct load demand analysis. The distribution of rural power grid load is based on deep learning. Based on this, a rural power grid energy storage capacity scheduling optimization model is constructed, with minimizing daily operating costs as one of the constraints on the objective function. The experimental results show that applying the method designed in this paper for intelligent optimization scheduling in distributed energy access results in higher power density. The active power in the energy storage capacity scheduling optimization implemented by this method is generally high. The energy storage efficiency is significantly optimized.