Electricity price super short-term prediction method

Abstract

The invention discloses an electricity price super short-term prediction method. The method comprises the steps that S1, electricity price historical data is acquired, and the electricity price historical data is preprocessed to obtain an electricity price sequence; S2, singular spectrum analysis is utilized to directly extract trend components, oscillation components and noise components in the electricity price sequence; S3, the noise components are filtered out, and a singular spectrum sequence is adopted to perform reconstruction on a trend component and oscillation component sequence obtained after noise reduction to obtain training samples; S4, the training samples are dynamically selected, and a prediction model of a cuckoo search algorithm optimized extreme learning machine is established; S5, the cuckoo search algorithm optimized extreme learning machine model is adopted to perform 0.5h-advanced prediction on the trend component and the oscillation component sequence to obtainsub-sequences; and S6, prediction values of all the sub-sequences are added to obtain an actual prediction result. According to the method, singular spectrum analysis is adopted to preprocess the original data, an input weight and hidden layer offset of the cuckoo search algorithm optimized extreme learning machine are adopted, and a non-optimal parameter defect of the extreme learning machine iseffectively overcome.

Description

technical field [0001] The invention relates to a forecasting method, in particular to an ultra-short-term forecasting method of electricity price. Background technique [0002] With a series of reforms in my country's electricity market, the degree of marketization of the electricity market has gradually increased, and the degree of monopoly has gradually decreased. Under the condition of marketization, certain methods can also be used to predict electricity prices, thereby optimizing market resources, promoting the process of marketization, maximizing the interests of market participants, and making the development of the electricity market more stable, orderly and healthy. With the continuous deepening of electricity marketization, the importance of electricity price forecast will become more and more prominent. A reasonable electricity price mechanism is related to the vital interests of powerful market participants and determines the stability and healthy development of...

AI Technical Summary

Problems solved by technology

However, a single prediction model cannot accurately predict electricity prices. Due to the great volatility of electricity prices, the electricity price data is affected by many interference factors. Singular Spectrum Analysis (SSA) is a powerful noise reduction technology. SSA can Directly extract the trend, oscillation and noise parts of the original sequence, especially suitable for the study of systems with periodic oscillations. SSA has related research in the fields of hydrological forecasting, power load and weather forecasting.

[0004] To sum up, the existing technology has the following disadvantages: first, the traditional single extreme learning machine prediction model is prone to fall into the problem of local optimum, and cannot achieve the optimal prediction effect; second, it is difficult for a single prediction method to deal with the highly nonlinear electricity price The effect on the forecast results requires decomposing the original series using decomposition techniques

Images