Web application for Electric Load Forecasting using Machine Learning

Abstract

Electricity plays an important role in many activities supporting all kinds of developments. To supply adequately and efficiently the demand required can protect the electric power system blackout. Nowadays we see that companies or industries working on a large scale usually consumes enormous amount of electric power, which leads to high opertional costs and this has been recognized as a main challenge in terms of economy. The purpose of the short-term electricity demand prediction is to forecast in advance the system load. The basic idea of this project is to determine the load of a user and alert the user in order to reduce consumption of electricity through a web interface accordingly. An efficient electricity predicton model is needed to minimize the electricity bills. Here we are using web application through which we will interact with the user. Power demand forecasting is important for economically efficient operation and effective control of power systems and enables to plan the load of generating unit. A precise load forecasting is required to avoid high generation cost and the spinning reserve capacity. Under-prediction of the demands leads to an insufficient reserve capacity preparation and can threaten the system stability, on the other hand, over-prediction leads to an unnecessarily large reserve that leads to a high cost preparations. Multiple linear regressions are the earliest technique of load forecasting methods. Here, unit of electricity is the main target(dependent) variable that influence the load. The other influential variables are identified on the basis of correlation analysis with load. This study uses the linear static parameter estimation technique as they apply to the twenty four hour off- line forecasting problem.The results of the developed system is a convenient way of monitoring and forecasting electricty usage through the use of web application.