Short-term load forecasting method and system

Abstract

The embodiment of the invention provides a short-term load forecasting method and a system. The method comprises steps: a load curve collection of similar days is acquired, wavelet transformation is used for decomposing and reconstructing all load curves in the load curve collection, and load sub curve collections are obtained; load characteristic analysis is carried out on all load curves in the load sub curve collections, a load characteristic analysis result is forecasted via a combined load forecasting model, and an initial load forecasting result is obtained; and the initial load forecasting result is corrected via an error forecasting model, and the outputted correction result serves as a load forecasting result of the forecasting day. Accuracy of the short-term load forecasting result is improved, and a high-accuracy load forecasting result can be obtained.

Description

technical field [0001] The invention relates to the technical field of electric power engineering, in particular to a short-term load forecasting method and system. Background technique [0002] Short-term load forecasting mainly refers to forecasting the power load for the next 1 to 7 days. Only on the basis of load forecasting at different levels and understanding the development and changes of future loads can targeted demand side management measures be put forward to improve the load curve. At present, due to the subjectivity of the demand side management itself, the uncertainty in the specific implementation, and the difficulty of quantifying the specific implementation effect and other complex conditions, it has affected some theoretical foundations of load forecasting and increased the scope of short-term load forecasting. Difficulty, resulting in low accuracy of short-term load forecasting results. Contents of the invention [0003] In view of this, an embodiment...

AI Technical Summary

Problems solved by technology

[0003] In view of this, an embodiment of the present invention provides a short-term load forecasting method and system to solve the problem of low accuracy of short-term load forecasting results in the prior art

Images