Method for predicating power load and evaluating predicated result based on ARIMA (Autoregressive Integrated Moving Average) model

Abstract

The invention discloses a method for predicating a power load and evaluating a predicated result based on an ARIMA (Autoregressive Integrated Moving Average) model. The method comprises the following steps: obtaining a time sequence of original power load data from a JAVA environment, and calling a statistical function in an R environment to process the time sequence, wherein the statistical function in the R environment is used for processing the time sequence based on the ARIMA model; receiving a processing result returned by the R environment from the JAVA environment and carrying out logic judgment on the result to obtain a corresponding predicated result; and evaluating the predicated result by using a pre-set accuracy evaluation index and a similarity evaluation index in the JAVA environment. With the adoption of the scheme, the functions of inputting the time sequence and automatically obtaining the predicated result are realized; and meanwhile, the predicated result is evaluated so that the accuracy of the predicated result is judged.

Description

technical field [0001] The invention relates to the technical field of counting machines, in particular to an ARIMA model-based electric load forecast and a method for evaluating forecast results. Background technique [0002] With the development of my country's economy and the improvement of people's living standards, electricity is becoming more and more important to the national economy and people's livelihood. Especially when entering the peak period of electricity consumption every year, the north and south of the river begin to save electricity and ensure energy conservation. Therefore, it has become a top priority to study the load situation of the existing power grid and optimally allocate the limited power resources. How to effectively model the power load and forecast the future load has become the key to solving this problem. At the same time, accurate power load forecasting can provide a reference for decision-making and has important practical significance fo...

AI Technical Summary

Problems solved by technology

Due to the obvious periodicity of power load as a time series, the time series forecasting model ARIMA model is often used as an effective forecasting method for power load, but it is often only used for the analysis of data of a specific user (industry, region), lacking versatility and Portability, and the accuracy of the prediction results cannot be judged

Images