基于蚁群优化算法递归神经网络的短期负荷预测

SHORT-TERM LOAD FORECASTING BASED ON RECURRENT NEURAL NETWORK USING ANT COLONY OPTIMIZATION ALGORITHM

为了克服BP算法收敛速度慢和易于陷入局部最小的不足,作者提出将蚁群优化算法用于短期负荷预测的递归神经网络模型学习算法,对实际负荷系统日、周预测的仿真测试表明,该模型能有效地提高短期负荷预测的精度,对工作日和休息日都具有良好的稳定性和适应能力,其预测性能明显优于基于BP算法的递归神经网络(BP-RNN)和基于遗传算法的递归神经网络(GA-RNN)。

To overcome the defects of neural network (NN) using BP algorithm such as slow convergence rate and easy to fall into local minimum, a recurrent NN model based on ant colony optimization algorithm (ACO-RNN) is proposed, The simulation results of daily and weekly loads forecasting for actual power system show that the proposed forecasting model can effectively improve the accuracy of short-term load forecasting (SLTF) and this model is stable and adaptable for both workday and rest-day, in addition, its forecasting performance is far better than that of BP-RNN and GA-RNN.