基于负荷分解的短期负荷预测传递函数模型

短期负荷预测主要用于预测未来几小时、1天甚至几天的负荷,对电力系统运行的安全性和经济性具有重要意义。时间序列模型在电力系统短期负荷预测中得到了广泛应用。然而,这种方法的一个主要缺点是无法将影响负荷预测的主要因素之一即气象因素考虑进去。在此背景下,首先基于历史负荷数据,采用传统的分解方法提取出负荷中的周期分量,得到剔除周期分量后的非周期分量。在此基础上,首先采用逐步回归法筛选出影响负荷非周期分量的主要因素,之后发展了预测负荷非周期分量的传递函数模型。最后,用广东电力系统实际负荷数据对所发展的短期负荷预测模型的准确性进行了验证。

A transfer function model for load forecasting based on load decomposition

Short-term load forecasting is used to predict the loads in the coming hours,in the next day and even the next several days,and has important impacts on maintaining the security and economics of the power system.The time series forecasting model represents a classical prediction method,and has been widely used for short-term load forecasting in actual power systems around the world.However,one major disadvantage of the time series model lies in the fact that the weather factor cannot be taken into account,while it usually play an important role in short-term load forecasting.Given this background,the periodical component is first decomposed from the overall load data by using the traditional decomposition method based on historical load data.On this basis,some major factors are selected from those factors having impacts on the non-periodic component of loads by using the stepwise regression model.A transfer function model is next developed for forecasting the non-periodic component of loads.Actual load data from Guangdong power system are employed to demonstrate the developed short-term load forecasting model.