Long-term load prediction device and method in power grid with multiple sources

Abstract

The invention belongs to the field of long-term load prediction in an electric power system, and particularly relates to a long-term load prediction device and method in a power grid with multiple sources. A double-CPU unit, a GPRS communication unit, a storage unit, a human-computer interaction unit and a power unit are arranged in a device box, wherein the double-CPU unit is connected with the GPRS communication unit, the human-computer interaction unit, the power unit and the storage unit, and power supply is achieved through the power unit. Through the device and method, the relation between various factors and a prediction result can be objectively reflected, and a high-dimensional characteristic space is built; a low-dimensional characteristic having best distinguishing capacity is extracted from the high-dimensional characteristic space in a combined and optimized mode, excessive learning can be avoided to the maximum extent, and algorithm efficiency is improved; a load prediction process can be faster and more effective, long-term load prediction accuracy degree in the power grid with the multiple sources can be improved easily, and therefore match of power generation areas in the power grid can be adjusted, dispatch of electric network power flow is performed, and the overall power generation level of the power grid in the area can meet the overall requirement of loads in the area in future.

Description

technical field [0001] The invention belongs to the field of medium and long-term load forecasting in electric power systems, and in particular relates to a medium- and long-term load forecasting device and method for a power grid with multiple sources. Background technique [0002] At present, my country is in the stage of vigorously developing new energy sources, and the grid structure is in a period of rapid development and construction. The total load demand of the grid is the basic work of urban grid planning, which determines the future demand for electricity in cities and the power supply capacity of future urban grids. The level of accuracy directly affects the quality of grid planning. Therefore, the forecast of the total load demand has become one of the main links in the construction of the power grid. [0003] The existing technology mostly adopts the prediction method based on learning and training to predict the total load demand of the power grid in a certain ...

AI Technical Summary

Problems solved by technology

[0003] Existing technologies mostly use prediction methods based on learning and training to predict the total load demand of the power grid in a certain period. However, the methods currently used generally have the problem of inaccurate prediction.

In this type of prediction method, the core link is the training of the learner. In order to ensure the calculation speed of the prediction, the weak classification method is often used to construct the learner, and the weak classifier may have wrong judgments on the classification of sample features, resulting in wrong learning.

Since the medium and long-term load demand is affected by many factors such as power grid operation mode, power supply composition, load type, regional economic development level, administrative planning, etc., its factor characteristics generally lack significance and regularity, which leads to many current forecasting methods. Serious, it cannot be accurately applied to medium and long-term load demand forecasting problems

[0004] So far, for medium and long-term load forecasting problems, methods such as intelligent learning algorithms, gray system theory, expert systems, and support vector machines have been mainly used. There are no forecasting methods and independent devices that consider a large number of new energy sources connected to the power grid, and only a large amount of historical data is used. There is no differential input calculation, no analysis and selection of medium and long-term load forecasting factors for the specified power grid (including multi-source power grid), the result has large errors and low reliability

Images