基于自适应滚动优化的电力负荷多模型组合预测系统的研究与开发

RESEARCH AND DEVELOPMENT OF MULTI-MODEL COMBINING LOAD FORECASTING SYSTEM BASED ON SELF-ADAPTIVE ROLLING OPTIMIZATION

该文提出了多模型组合预测等预测策略,采用了包括非线性优化组合模型、逻辑预测模型、组合自适应指数平滑模型和综合模型等多种组合模型来进行短期电力负荷的预测;并使用自适应滚动优化技术保证每种模型能随负荷特性变化,调整模型参数;同时根据对每种模型在一段时间内的预测误差分析,选取最优的组合模型。基于该文预测策略和预测模型所开发的预测系统的预测结果表明,组合预测模型的预测结果优于单一模型的预测结果。

Multi-model combining load forecasting strategy is proposed. Several combining models, such as non-linear optimally combining model,logically predicting model, smoothly self-adaptive exponential combining model, and synthetical model, are adopted in the short-term load forecasting. The parameters of the model can be changed in accordance with the regional load characteristics by using the rolling optimization technique. The optimum combining model can be chosen on the basis of every model's prediction error analysis in a period of time. The results of using the forecasting stratege and models proposed in the paper indicate that the forecasting result of combining forecasting model is better than that of the single model.