基于IRSO-TCN的短期电力负荷预测

Short Term Power Load Forecasting Based on IRSO-TCN

精准的电力负荷预测对电力系统的安全调度和稳定运行至关重要。为了提升短期电力负荷预测精度,提出了一种基于改进鼠群优化算法(IRSO)和时间卷积网络(TCN)的短期电力负荷预测模型。首先将时序特征输入到TCN预测模型进行预训练;然后针对训练好的TCN模型全连接层阈值与偏置易陷入局部最优的问题,采用改进鼠群优化算法对阈值与偏置进行调整,构建IRSO-TCN组合模型对电力负荷进行预测;最后以澳大利亚实测数据进行仿真建模,实验结果表明,加入交叉算子的IRSO比鼠群优化算法(RSO)寻优能力更强,收敛速度更快,能够有效提高电力负荷的预测精度。

Accurate power load forecasting is very important for the safe dispatching and stable operation of power system.In order to improve the accuracy of short-term power load forecasting,a short-term power load forecasting model based on improved rat swarm optimization algorithm(IRSO)and time convolution network(TCN)is proposed.Firstly,the time series characteristics are input into the TCN prediction model for pre training;then,aiming at the problem that the threshold and bias of the whole connection layer of the trained TCN model are easy to fall into local optimization,the improved rat swarm optimization algorithm is adopted to adjust the threshold and bias,and the IRSO-TCN combination model is constructed to predict the power load;finally,the simulation modeling is carried out with the measured data in Australia.The experimental results show that the IRSO with cross operator has stronger optimization ability and faster convergence speed than the rat swarm optimization algorithm(RSO).The proposed method can effectively improve the accuracy of power load forecasting.