Predicting the Creation of Smart Grids considering the Role of Big Data in North America's Electricity Market

Abstract

Using dual-bandwidth digital technology, the smart grid delivers energy from manufacturers to customers, saving consumers energy by controlling their home appliances, reducing costs and enhancing reliability and transparency. The smart grid on the one hand and the shaping of the electricity market, on the other hand, have created a huge amount of data every day through the daily interactions of electricity and to decide which market players to include manufacturers, transmitters, distributors and in the near future on smart grids for electricity consumers, storage and then be analyzed. This huge amount of data, despite the many benefits it can bring, can cause problems in data storage, display and analysis. For example, one of the most important tasks of North America's electricity market management is to forecast electricity prices for future periods based on stored historical data and because of the type of data produced in this area of the big data typ. Data has problems with different fields, especially in data analysis. In this paper, the role of modern data mining methods for big data analysis is compared by comparing two traditional and new data mining methods and performing statistical experiments. The results of this paper show that a slight improvement in electricity price forecasts due to high volume of electricity exchanges can bring incredible savings to the players in this field. Therefore, the use of modern data mining methods in this field is very important and practical.