基于GA-BP神经网络的微电网短期负荷预测

Short Term Load Forecasting of Micro Grid Based on GA-BP Neural Network

针对微电网负荷功率的不确定性,提出了一种基于遗传算法优化的BP神经网络模型GA-BP,能够快速、有效地建立非线性输入与输出之间的关系,对微电网短期负荷进行预测。通过对遗传算法优化的BP神经网络和传统BP神经网络分别建立微电网负荷预测模型,对某地区的微电网短期负荷进行MATLAB仿真和计算,对2种模型的未来24 h短期负荷预测进行比较,验证了2种预测方法的有效性和可行性。由仿真结果可知,采用遗传算法优化的BP神经网络预测的平均相对误差为3.23%,相较于传统的BP神经网络拥有更好的预测精度。

Aiming at the uncertainty of load power of micro grid,this paper proposes a BP neural network model GA-BP based on genetic algorithm optimization,which can quickly and effectively establish the relationship between nonlinear input and output,and predict the short-term load of micro grid.Through the establishment of micro grid load forecasting models based on BP neural network optimized by genetic algorithm and traditional BP neural network respectively,the short-term load of micro grid in a certain area is simulated and calculated by MATLAB.The short-term load forecasting of the next 24 hours of the two models is compared,which verifies the effectiveness and feasibility of the two forecasting methods.The simulation results show that the average relative error of BP neural network optimized by genetic algorithm is 3.23%,which has better prediction accuracy than the traditional BP neural network.