Electric power system typical daily load curve generation method

Abstract

The invention relates to an electric power system typical daily load curve generation method. The method comprises the following steps that a local multi-year daily load power curve is acquired as a sample by using a fixed sampling period to form a data set; the type number and the length of the generated typical daily load curve are set to be equal to the daily load sampling point number, each coding bit is a coding string of a positive integer in the type number, and daily load samples with the same coding bit value are extracted as the same type; the probability product of the sample value obeying the probability distribution at the same moment is calculated, and the product values are added at all moments to represent the advantages and disadvantages of the sample aggregation; 4, the coding string is optimized to achieve optimal clustering of historical samples by using genetic operation processes such as crossover, variation and the like; and according to the optimal clustering result, the typical daily load curve of the same kind is represented by the mean value of the probability distribution of the samples of the same kind at each moment. According to the invention, a solid foundation is laid for locating and sizing of a local new energy and energy storage system and scheduling planning of a power system.

Description

Technical field: [0001] The invention relates to smart grid technology, in particular to a method for generating a typical daily load curve of an electric power system. Background technique: [0002] In recent years, with the vigorous development of electric vehicles, the power load has increased day by day, and the disordered charging process has increased the complexity of the power grid. At the same time, the penetration rate of renewable energy continues to increase, and energy storage technology is vigorously developed. The uncertainty and constraints of its output have caused great troubles to the dispatching and planning of the power system. bring challenges. It is obvious that the power balance between the power generation unit and the power consumption unit in the grid is a prerequisite for ensuring power stability. Therefore, reasonably and effectively estimating the demand and changes of power load in the region will be the primary issue of local energy allocati...

AI Technical Summary

Problems solved by technology

Each link in these methods reflects unique analysis focus and elements, but the serial generation and extraction process ignores the necessity of overall optimization, making it difficult to obtain a suitable and accurate daily load curve

The methods based on artificial intelligence and machine learning generally need to train a scene generation model (such as variational autoencoder, generative confrontation network, etc.) for a large amount of historical data. The most important issue in this type of method is the effective data The influence of sex is great, the model is often complex, the calculation is large, and the physical meaning is lost

Images