Power load short-term prediction method, model, device and system

Abstract

The invention discloses a power load short-term prediction method, model, device and system, and the method comprises the steps of receiving the load data, and complementing the missing data of the load data; receiving the influence factor data which comprises the air temperature data, the holiday data and the industry category data to which the power consumers belong, and quantifying the influence factors by adopting a quantification method corresponding to the load data; processing the historical load data by adopting the wavelet decomposition, carrying out the multi-scale decomposition to obtain four historical load reconstruction data sequences, and respectively carrying out correlation measurement on the four historical load reconstruction data sequences and the influence factor datato obtain a correlation characteristic data set of each reconstruction load characteristic and the influence factor; and carrying out preliminary prediction on the four sequences obtained according tothe load data by adopting a cubic exponential smoothing algorithm, further optimizing a preliminary prediction result, and finally obtaining a power short-term load prediction value as the power loadscheduling reference data.

Description

technical field [0001] The present disclosure belongs to the technical field of electric power systems, and relates to a short-term prediction method, model, device and system of electric power load. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] During the operation of the power system, in order to complete the power transmission and power transaction, and to ensure the safe and stable operation and power quality of the power system, power-load balance has become the core link of power grid security and stability control. With the gradual advancement of energy supply-side reform and electricity market-oriented reform, power grid companies are faced with challenges such as the complexity of the grid form, the force of electricity marketization, and the explosion of the information economy to create a changeable market. Service satisfacti...

AI Technical Summary

Problems solved by technology

[0005] The current power load forecast is mainly based on historical power consumption data to predict future power demand. The traditional forecasting method is mainly the triple exponential smoothing method, that is, based on the power load data of the previous period, combined with the seasons, policies, etc. contained in the current time step data. Information, with an adjustable parameter to control the weight of old and new data, the weight is an exponentially decreasing moving average, and presents seasonal changes in a fixed period of time, and is adjusted by automatically identifying changes in data patterns to generate short-term power load forecast data , however, this method lacks the detection ability and adaptive learning ability for the mutation point of the data, and the prediction accuracy is difficult to guarantee; the long short-term memory neural network (long short-termmemory networks, LSTM) is a popular model of the deep learning framework, because of its learning ability Strong and good at fitting time series data has become an ideal solution to solve short-term forecasting problems. However, high forecasting accuracy leads to more hidden layers and high complexity of the model, which not only causes too many parameters to make model training and learning difficult, but also makes The model has problems such as fragility, poor robustness, and low generalization, especially the lack of discrimination against detailed disturbances, and error data that deviate from expectations often lead to immeasurable errors in model predictions

Images