Network Load Forecasting Method Based on Comprehensive Evaluation of Regional Load Forecasting Values

Abstract

The invention discloses a load forecasting method of the whole network based on the comprehensive evaluation of the regional load forecasting value, which is characterized in that firstly, the historical data in a recent sample period is obtained as the historical data sample space, and then the t of each area in the historical data sample space is calculated. The average proportion coefficient at each time point is used to predict the proportion coefficient of each region at the same time point t on the day to be predicted, and a multi-index evaluation system at time point t is constructed. According to the multi-index evaluation system, a comprehensive evaluation index at time point t is constructed, and t For the q areas with higher priority at the time point, use the selected q areas to predict the system load of the entire network at the time point t, and then establish the optimal comprehensive model at the time point t for the q different predicted values, and solve it to obtain For the final prediction result of the whole network system load at time t, for the T time points of the whole day on the day to be predicted, the optimal comprehensive model is established respectively, and the whole day load forecast sequence is obtained. The method of the invention can improve the accuracy rate of short-term load forecasting of the power system.

Description

technical field [0001] The invention relates to a large power grid load forecasting method based on comprehensive evaluation of regional load forecast values, which is used for short-term load forecasting of power systems and belongs to the technical field of power system load forecasting. Background technique [0002] In order to ensure the dynamic balance between power generation power and load power in the power system, it is necessary to make a scientific forecast of the power system load. Load forecasting is an important task of dispatching centers and power grid development planning departments. The results of load forecasting have important guiding value for power grid operation, control, dispatch, planning, construction, etc. It is the basis for scientific development and scientific dispatch of power grids. [0003] Improving the level of load forecasting technology is conducive to planning power consumption management, rationally arranging power grid operation mode ...

AI Technical Summary

Problems solved by technology

[0008] Since this method needs to predict each regional subnetwork, and for short-term load forecasting, due to the different load stability in each region, the difficulty of forecasting is very different. At the same time, the plant power consumption and network loss data also need to be predicted, so , when using the forecasted load of all areas for subnet accumulation, the accuracy of the system load forecast of the whole network may not be ideal

Images