Stable electric load forecasting plays a significant role in power system operation and grid management. Improving the accuracy of electric load forecasting is not only a hot topic for energy managers and researchers of the power system, but also a fair challenging and difficult task due to its complex nonlinearity characteristics. This paper proposes a new combination model, which uses the least squares support vector machine, extreme learning machine, and generalized regression neural network to predict the electric load in New South Wales, Australia. In addition, the model employs a heuristic algorithm–whale optimization algorithm to optimize the weight coefficient. To verify the usability and generalization ability of the model, this paper also applies the proposed combined model to electricity price forecasting and compares it with the benchmark method. The experimental results demonstrate that the combined model not only can get accurate results for short-term electric load forecasting, but also achieves fine accuracy for the same period of electricity price forecasting.

稳定的电力负荷预测在电力系统运行和电网管理中起着重要作用。提高电力负荷预测的准确性不仅是能源管理者和电力系统研究人员的热门话题，而且由于其复杂的非线性特性，这也是一项艰巨而艰巨的任务。本文提出了一种新的组合模型，该模型使用最小二乘支持向量机，极限学习机和广义回归神经网络来预测澳大利亚新南威尔士州的电力负荷。另外，该模型采用启发式算法-鲸鱼优化算法来优化权重系数。为了验证模型的可用性和泛化能力，本文还将提出的组合模型应用于电价预测，并将其与基准方法进行比较。实验结果表明，该组合模型不仅能获得短期电力负荷预测的准确结果，而且在同期电价预测中也能达到较高的精度。