SYSTEM FOR FORECASTING ELECTRICITY CONSUMPTION BASED ON TEMPERATURE DATA

Abstract

The paper examines the main tasks of a system for assessing the dependence between electricity consumption and temperature. This system is designed to provide a comprehensive approach to data analysis, starting from data collection, processing, and analysis, and concluding with forecasting and visualization of results. An analysis of various modern approaches and methods for evaluating the relationship between temperature and electricity consumption has been conducted.As a result of the study, key factors influencing energy consumption under varying temperature conditions have been identified, along with the advantages and disadvantages of different methods and tools applied in this field.The correlation between temperature indicators and energy consumption was evaluated using Pearson’s correlation coefficient, ensuring high accuracy in determining the binding between these parameters. A mathematical model for forecasting electricity consumption based on temperature data has been developed, enabling predictions of energy usage while accounting for temperature variations.The selection of tools and technologies for creating a software system that performs data analysis using libraries and tools for processing, storing, and visualizing information is substantiated.The results form the basis for effective energy consumption forecasting in urban environments. The system’s architecture has been developed to ensure efficient data processing and easy scalability. Integration with a database has been implemented, allowing efficient storage and processing of large data volumes for analysis and forecasting. Functional decomposition has been carried out, defining the main modules and their interactions, ensuring clear task execution.The results of the system’s operation enable forecasting electricity consumption levels based on temperature conditions.This facilitates better resource planning and reduces the risk of overloading the energy system during temperature peaks.This approach not only optimizes energy expenditures but also ensures stability and reliability in urban energy supply.