This paper presents an IoT based load forecasting and management system for distribution grids using Raspberry Pi. The proposed system integrates with real time data acquisition, statistical forecasting, and intelligent load management to enhance grid reliability. IoT enabled sensors are employed to capture real time electrical parameters, which are processed by Raspberry Pi and transmitted to the cloud for monitoring and control. The forecasting methodology incorporates statistical and time series models, including Linear Regression, Multiple Regression, Polynomial Regression, ARIMA means Auto regressive Integrated Moving Average, SARIMA means Seasonal ARIMA, and Holt Winters, implemented in MATLAB Simulink. Two categories of features, based on historical demand patterns and calendar effects, are used to train the forecasting models. Furthermore, the influence of model selection on forecasting accuracy and scalability is analyzed. Finally, an intelligent load management strategy is proposed to reduce peak demand stress, maximize operational efficiency, and provide a cost effective solution for distribution networks. The developed system shows improved accuracy, adaptability, and scalability, making it suitable for real time smart grid applications.
G.B. et al. (Wed,) studied this question.