A hierarchical load forecasting method for distribution network based on topology

Abstract

The invention discloses a distribution network layering load forecasting method based on topology. A distribution network is layered according to a topology connection relation, forecasting is conducted on the layers respectively, a total forecasting result is obtained by summing in an optimizing mode, summarizing load data of a 10 kV outgoing line switch are read, and contrastive analysis is conducted on the data and the forecasting result. Forecasting accuracy is improved obviously, an intelligent distribution network system is utilized effectively, deep mining based on big data is achieved, the immunity to the data is improved, and lean management of the distribution network is achieved easily.

Description

technical field [0001] The invention belongs to the field of power systems, and in particular relates to a topology-based distribution network layered load forecasting method. Background technique [0002] Accurate short-term power load forecasting has important reference significance for the daily dispatch of the power sector. Most of the existing load forecasting methods are aimed at busbars and transformers. By analyzing their historical load data and adding meteorological factors, the load forecasting of busbars, transformers and other power equipment is directly carried out. In order to improve the prediction accuracy, researchers have done a lot of work on improving the algorithm of load forecasting, such as combining neural network and genetic algorithm, and using the improved least squares support vector machine method, etc. These improved methods have achieved certain results. Effect. However, due to omissions and errors in data collection and layer-by-layer trans...

AI Technical Summary

Problems solved by technology

However, due to omissions and errors in data collection and layer-by-layer transmission, and load prediction is generally based directly on the load data of the transformer or bus where it is located, the source of data samples for power equipment is relatively single, and this prediction method will undoubtedly have large errors

In addition, due to the operation mode of the existing information collection system of the electric power sector, the load samples are insufficient, especially in special cases such as holidays. The number of samples is difficult to meet the precision requirements

On the one hand, inaccurate data directly affects the forecast results; on the other hand, the single source of data samples makes the forecasting insufficient tolerance and immunity to data, which has limitations. Once the sample data has a large error, it will directly affect the forecast results; Affected accuracy improvement

Images