Geographic information system short-term load prediction method based on mesh method

Abstract

The invention discloses a geographic information system short-term load prediction method based on mesh method. According to the invention, the method includes the following steps: in a power system,combining short-term load prediction with a geographic information system, based on the data provided by the geographic information system, preliminarily dividing region load into mesh loads; in accordance with the division rules of load uses and load density, further dividing the mesh loads; using a Spectral Multi-Manifold Clustering method and a simple fuzzy clustering method, based on the givenload influence factors and load waveform changes, combining the mesh loads; and on the basis of the aforementioned steps, using a short-term prediction method of BP, RBF neural network, obtaining theresult of short-term load prediction. According to the invention, the method herein uses an improved multi-level mesh segmentation method, can obtain the total result of load prediction by combiningthe mesh loads, not only meets prediction precision, and also reduces the workload of load prediction. The method herein can easily and fast obtain the changes of respective load waveforms and the changes of the total load waveform and provides reasonable and effective basis for work, such as grid scheduling.

Description

technical field [0001] The invention relates to the field of load forecasting of electric power systems, in particular to a short-term load forecasting method of a geographic information system based on a grid method. Background technique [0002] Load forecasting is a basic work of power system, and accurate forecasting of power load is of great significance to power production and dispatch, safe operation of power grid and national economy. With the development of the energy Internet, the access of new energy sources, and the strengthening of information between loads, the power grid has put forward higher requirements for the real-time performance of data processing in load forecasting. Geographic Information System (GIS) is a technology that combines geography, computer science and other disciplines. It plays an important role in power system planning, production, operation, maintenance management and operation management. With the rapid development of computers, The da...

AI Technical Summary

Problems solved by technology

However, the above classification does not consider the simplification of the load forecasting process

There have been a lot of researches on short-term load forecasting methods in geographic information systems, but there are relatively few studies on the combination of short-term load forecasting and geographic information systems for grid division and merging.

Images