Partition power grid bus load prediction system based on weather information

Abstract

The invention discloses a partition power grid bus load prediction system based on weather information. Real-time weather information and prediction weather information are used in the system, load prediction of all buses of converting stations of 500 kV and 220 kV is achieved, and recognition of power grid partition and partition load prediction are achieved. A prediction algorithm used by the system comprises a classical algorithm and an intelligent prediction algorithm, the classical algorithm comprises unary linear regression, quadratic polynomial regression, self-adaptation index prediction, index prediction, increasing rate prediction, nonhomogeneous index prediction, a B. Compertz model and a logistic model, the intelligent prediction algorithm comprises an optimized BP neural network algorithm and an optimized particle swarm algorithm, and the system selects a prediction algorithm in a preferential mode during a prediction process. The system is a day-ahead bus load prediction system, bus load and partition load of each time interval from morrow to multiple days in future are predicted, and prediction content is active load of 96 points of a predicted day.

Description

technical field [0001] The invention relates to a grid bus load and partition load forecasting system using meteorological information, which belongs to the technical field of meteorological information application in power systems. Background technique [0002] The results of bus load forecasting are the basis for making day-ahead planning and safety checks, and the prediction accuracy will have a significant impact on the results of day-ahead planning and safety checks. Therefore, actively carrying out bus load forecasting and improving forecasting accuracy is an important measure for the dispatching and operation department to improve the ability to control the power grid. [0003] Jiangsu Power Grid has started bus load forecasting work in 2005, but in practical applications, load transfers often occur due to changes in the operation mode of local / county dispatchers, such as equipment maintenance, etc., resulting in disrupted bus load operation rules. The accuracy of bu...

AI Technical Summary

Problems solved by technology

[0007] (3) Affected by user behavior in the power supply area, the bus load is prone to sudden changes, the stability is relatively poor, and there are many "burrs";

[0008] (4) The accumulated data is imprecise and often contains bad data (outliers with large errors);

[0009] (5) The possibility of being affected by meteorological factors is relatively high;

[0010] (6) The trend of load change is not obvious, and the difference of load curves between different buses is relatively large;

[0011] (7) It is greatly affected by planned related factors such as power grid maintenance and load transfer

[0014] When the predicted daily load fluctuates greatly due to factors such as weather, or extreme loads occur, it is difficult to accurately predict the bus load of the next day based on load modeling based on historical values

[0015] (2) Uncertain power supply

[0018] The real user of the bus load is dispatched at the lower level. It is difficult to consider the details of the power load changes of each power user in a top-down manner. Due to changes in the operation mode of the lower-level local and county dispatchers, the load has been transferred, resulting in the 220kV bus load. There are relatively large changes in the data, and these changes have little to do with the user's electricity consumption itself, but they will also affect the load forecasting modeling

Images