基于周期自回归模型的短期负荷预测

通常，周期自回归（ＰＡＲ）模型适于处理短周期时间序列。故进行电力系统短期负荷预测时，由于周期长度大，阶数高，待估计的参数剧增，难以实现。本文在一定的假设条件下，建立了短期负荷的周期自回归预测模型，提出了相应的算法，并编制了计算分析程序。对一实际系统的负荷预测表明，本文的模型和算法具有很高的预测速度和良好的预测精度。

A Short Term Load Forecasting Method Based on PAR Model

Periodial auto regression model (PAR) is suitble for small period time serise.But for short term load,it is not easy to be dealed with PAR because of the very big period and there is too many parameters to be computed.This paper presents a new method for a week ahead hourely load forecasing based on PAR.A C programme is developed to forecast the load of a power company and a promising result is received.