含有山区小水电负荷的气象回归短期负荷预测技术

将负荷分解为正常负荷及小水电负荷,进一步将其分别分解为气象负荷和长期趋势负荷分量,建立气象因素和气象负荷的回归关系,并以回归结果对历史负荷数据进行相似搜索,该方法可提高预测样本同被预测日负荷的相似度,从而增加预测结果的可信度和精确度。采用多种负荷预测方法以权重优化组合的方式进行负荷组合预测。应用实例证明,所提出的方法可体现不同地区、不同类型、不同气象敏感度的负荷特性,对于负荷总量较小,变动范围较大,受天气因素影响明显且含有山区小水电负荷的地区具有较好的精度。

Weather line regression and combination load forecast of mountainous area contain small hydro-power unit

This paper divides the load into normal load and small hydro-power load,and decomposes them into weather-sensitive load and secular trend load respectively,and then found the relation between the weather-sensitive load and the weather factors by line regression model.According to the regression result,similarity search can find better samples for load forecast.This method can improve the similarity of the loads between forecast day and sample days,and so as to improve the reliability and precision of load forecast.Manifold load forecast methods assembled by optimal weight were also applied to load forecast in this paper.Technical application manifest these techniques put forward in this paper can represent the load character of different areas,types and weather sensitivities,so as to have robust adaptability,and then have higher precision even to those small,big-vibration-range,weather-sensitive and mountainous area load contain small hydro-power unit.