基于双向长短时记忆网络的并网微电网能量供需平衡优化

为保证并网微电网的稳定运行，针对微电网负荷波动较大，稳定性较差的问题，提出基于双向长短时记忆网络的并网微电网能量供需平衡优化方法。该方法通过双向长短时记忆网络划分并网微电网中的负荷类别，并引入注意力机制优化分类结果，获取并网微电网中的可控负荷结果；结合该结果和储能系统的能量损失情况、风光综合功率波动水平，构建目标函数并确定约束条件，采用改进帝国竞争算法求解目标函数，获取保证获取全局负荷调度最佳结果，实现并网微电网能量供需平衡优化。测试结果显示：该方法能够有效调度并网微电网中负荷，调整并网微电网供需侧有功和无功功率的结果，使其在±0.50kvar内范围波动，优化后满足微电网中的而负荷需求；保证微电网的稳定运行。

Optimization of Energy Supply and Demand Balance in Grid-connected Microgrid Based on Bidirectional Short and Long Time Memory Network

In order to ensure the stable operation of the grid connected microgrid, aiming at the problems of large load fluctuation and poor stability of the microgrid, an optimization method of energy supply and demand balance of the grid connected microgrid based on bidirectional long-term and short-term memory network is proposed. This method divides the load categories in the grid connected microgrid through the bidirectional long-term and short-term memory network, and introduces the attention mechanism to optimize the classification results, so as to obtain the controllable load results in the grid connected microgrid. Combining this result with the energy loss of the energy storage system and the fluctuation level of the integrated wind and solar power, the objective function is constructed and the constraint conditions are determined. The improved Empire competition algorithm is used to solve the objective function to obtain the best result of the global load scheduling, so as to realize the optimization of the energy supply and demand balance of the grid connected microgrid. The test results show that this method can effectively dispatch the load in the grid connected microgrid, adjust the results of active and reactive power on the supply and demand side of the grid connected microgrid, make it fluctuate within the range of ± 0.50 kvar, and meet the load demand in the microgrid after optimization, ensure the stable operation of microgrid.