A bus load forecasting data correction method for power generation planning optimization

Abstract

The invention relates to a bus load forecasting data correction method for power generation plan optimization; based on the power generation plan optimization, the bus load correction factors of each period are calculated during the power generation plan optimization process, and the bus load forecast is performed by adding the correction factors The data can be effectively corrected; effectively solve the problem of large power flow calculation errors in the safety check link in the process of power generation plan optimization due to the low accuracy of bus load forecasting; at the same time, improve the accuracy of power flow calculations.

Description

technical field [0001] The invention relates to the technical field of electric power dispatching automation, in particular to a bus load forecasting data correction method for power generation plan optimization. Background technique [0002] At present, the bus load forecast is the sum of the terminal load supplied by the main transformer of the substation to a relatively small power supply area, which is the refinement of the system load. The bus load forecast is the off-grid load of the substation, which is the grid node load. Therefore, the bus load forecasting takes the node load as the forecasting object, and generally only performs short-term load forecasting, and the forecasting results provide hypothetical power flow data for the power grid to calculate the power grid power flow. [0003] Since the bus load forecasting takes the off-grid load of the substation as the forecasting object, there are the following difficulties in the actual forecasting process: [000...

AI Technical Summary

Problems solved by technology

[0004] 1. Compared with the system load, the base of the bus load is relatively small, and the regularity is weak

[0005] 2. Affected by the behavior of users and small power sources in the power supply area, the bus load is prone to sudden changes, poor stability, and more glitches;

[0006] 3. Error data caused by data collection and transmission and data mutation caused by changes in operation mode, etc., resulting in low data quality;

[0007] 4. Due to the small power supply range, the randomness of users is large, there are many uncertain factors, and the trend of load changes is not obvious;

[0008] 5. The load curves of different buses differ greatly, and the load change trend is not obvious

However, due to the above factors, the bus load prediction accuracy is not high, and it does not match the system load prediction, resulting in large errors in power flow calculations

Images