Correlation coefficient-based industry electricity consumption law forecasting method

Abstract

The invention discloses a correlation coefficient-based industry electricity consumption law forecasting method, and includes: collecting electricity consumption data of users in a set industry in a set area; forming an electricity consumption historical data sequence and performing normalization; obtaining correlation coefficients of electricity consumption of the users and industry overall electricity consumption, and determining a correlation characteristic between an electricity consumption change of the users and an industry overall electricity consumption law; and selecting a user whose power load change trend has the highest consistency with an industry overall load change, and forecasting the electricity consumption data change law of an overall industry. The correlation coefficient-based industry electricity consumption law forecasting method provided by the invention has the beneficial effects of being callable of deriving a forecast of an abnormality of a specific industry and even a whole society power load abnormality from an abnormality of a certain user power load, improving accuracy of a power load forecasting result, and providing a power guarantee for reasonable economic dispatching of an electric power system, reduction of production cost, and prevention of a large-area power failure of a power grid or a power grid breakdown.

Description

technical field [0001] The invention relates to the technical field of power system electricity consumption characteristic analysis, in particular to a method for predicting industry electricity consumption law based on correlation coefficients. Background technique [0002] With the development of the economy, the power consumption is increasing year by year, and the diversification and complexity of the power load have put forward higher requirements for the decision-making theory, management methods and technical support of the industry's power consumption change trend, but the current work is still There are many unreasonable and unsatisfactory problems: [0003] 1. The analysis of industry electricity consumption focuses on the macro perspective [0004] At present, the analysis of electricity consumption in relevant industries in China can only be done after the fact. It can only grasp the changes in the overall electricity consumption law of the industry from a macro...

AI Technical Summary

Problems solved by technology

[0004] At present, the analysis of electricity consumption in relevant industries in China can only be done after the fact. It can only grasp the changes in the overall electricity consumption law of the industry from a macro level, and cannot target the consumption of a certain industry or a certain customer. Specific analysis of power characteristics

[0005] 2. The intelligence of power consumption prediction is not enough

[0006] At present, the forecast of electricity consumption is usually based on the display of data and reports, and the staff often need to use their own work experience to perform secondary processing on the data in order to obtain an effective judgment; such a forecast method, on the one hand, uses The power prediction results have a great relationship with the actual experience and theoretical level of the analysts; on the other hand, when the amount of data is large, it will greatly increase the workload of the forecasters, and the prediction results cannot be effectively Comprehensive coverage of market conditions

[0007] 3. The early warning mechanism for changes in electricity consumption is not perfect

[0008] At present, early warnings of electricity consumption changes at home and abroad often focus on macro and medium perspectives, and forecast from the perspectives of economic changes and industry changes. Due to untimely data acquisition, the best early warning opportunities are often missed, and even only after-the-fact analysis can not be performed. serve as an early warning

Images