Agent electric quantity prediction method, device and equipment and medium

Abstract

The invention discloses an agent electric quantity prediction method and device, equipment and a medium, and relates to the technical field of power systems, and the method comprises the steps: determining target monthly agent electric quantity which does not consider user loss and corresponds to a first historical month based on a first loss rate of the first historical month and historical monthly agent electric quantity; decomposing the target monthly agent electric quantity to obtain a plurality of load components, predicting each load component according to a preset rule to obtain a predicted load component of the target month, and obtaining reconstructed target monthly agent electric quantity based on all the predicted load components; and constructing a target user churn rate model, predicting a second churn rate of the target month by using the target user churn rate model, and determining predicted monthly agent electric quantity considering user churn corresponding to the target month based on the second churn rate and the reconstructed target monthly agent electric quantity. Through the technical scheme of the invention, the prediction precision of the power grid enterprise agent electric quantity can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of electric power systems, and in particular, to a method, device, equipment and medium for proxy electric quantity prediction. Background technique [0002] The agency power purchase mechanism of power grid enterprises is a clear requirement put forward by my country to further deepen the market-oriented reform of coal-fired power generation on-grid electricity prices. Power grid companies need to clarify the scope of agency power purchase users, predict the power consumption scale of agency industrial and commercial users, and form agency power purchase user tariffs through market-oriented power purchases. Since the power purchase price of power grid enterprises includes the market power purchase price, transmission and distribution price and government funds and surcharges, it also includes the deviation of electricity generated by the power purchase agent, which should be calculated on a monthly ...

AI Technical Summary

Problems solved by technology

Although the medium and long-term load data series usually have a good trend, the sample size in the forecast is often small, which makes it difficult for this type of method to be practically applied

In addition, because the electricity market encourages industrial and commercial users to directly participate in market transactions, and continuously narrows the scope of power grid enterprises’ agency power purchases, the agency power of grid companies is greatly affected by market environment and policy factors, and the trend of historical load data series is destroyed. It is difficult to directly For medium-term load forecasting

Images