Electricity Price Forecasting for Cloud Computing Using Machine Learning Model

The information technology sector is being swiftly overtaken by cloud computing since it significantly simplifies computing without the need to purchase the actual gear required for computations; instead, these services are hosted by businesses that offer cloud services. These businesses depend on the availability of a reliable and affordable electrical power supply because they house numerous servers and computers whose primary power source is electricity. Cloud centers use a lot of energy. With recent increases in electricity costs, one of the primary issues in designing and efficiently placing data and scheduling nodes to offload or transfer storage are among some of the maintenance tasks of such centers is to minimize electricity use. We propose an Extreme Gradient Boosting (XGBoost) model in this project to offload or transfer storage, predict electricity prices, and so cut energy consumption expenses in data centers. On a dataset from the real world given by the Independent Electricity System Operator (IESO) in the Canadian province of Ontario, the effectiveness of this strategy is assessed in order to offload data storage in data centers and effectively reduce energy consumption. 70% of the data is used for training and 30% towards testing. With a r2_score of 91%, the XGBoost Regressor surpasses the Random Forest Regressor and Support Vector Regressor.