Medium and long term power load forecasting method based on factor-main attribute model

Abstract

The invention discloses a medium and long term power load forecasting method based on a factor-main attribute model. The medium and long term power load forecasting method based on the factor-main attribute model includes that step 1, building (n-1) impact factor indexes X1-Xn-1 and an original matrix of a forecast object Xn, using Z standardization to pre-process the impact factor index data X1-Xn-1 and Xn, and carrying out dimensionless on the index data to obtain an index matrix Ao*n; step 2, according to a factor analyzing method, confirming a selected common factor, calculating the corresponding factor score, and building a factor forecasting model FORMULA (shown in the description); step 3, sieving to obtain main attributes m1, ..., mr according to a main attribute algorithm, wherein the main attribute model is FORMULA (shown in the description), and v is the feature vector; step 4, building a factor-main attribute medium and long term power load forecasting model according to FORMULA (shown in the description), calculating to obtain a normalized forecast variable value, performing Z standardization formula conversion, and calculating again to obtain the practical value of the corresponding original variable value.

Description

technical field [0001] The invention belongs to the research field of power load forecasting methods, relates to a complex problem forecasting method influenced by multiple factors, in particular to a mid- and long-term power load forecasting method based on a factor-principal attribute model. Background technique [0002] Forecasting is a discipline that predicts and controls the uncertainty of the development of things through the research of mathematical models, and finds the methods and theoretical research of the laws of the development of things. It is widely used and occupies an important position in various industries and fields, especially in the period of industrial modernization and development, it has played a great role in rational planning and decision-making. [0003] There are many theories and methods of forecasting, which can be classified from qualitative and quantitative perspectives. Qualitative forecasting methods are highly subjective, mainly relying ...

AI Technical Summary

Problems solved by technology

There are many corresponding prediction methods for these two types of methods, but usually a single method from these two types of methods is applied to each prediction problem separately, and the research on the research object is either a qualitative analysis or a data-oriented The embodiment of the structure, the lack of mutual integration

[0004] With the rapid development of economy, society and science and technology, the background of the object to be predicted is becoming more and more complex, often affected by many factors, and these influences come from a wide range of sources, and the range of influence is also different, so the traditional method of fitting is through a single variable Forecasting methods are no longer suitable for the increasingly diverse forecasting problems

[0005] The traditional medium and long-term forecasting of electric load generally adopts a single economic forecasting method, and the research data is limited to the single data of the research object itself, or only involves a single influencing factor

Images