Data-analytics and forecasting for smart home energy usage

Abstract

The rapid growth of smart home technologies has led to an unprecedented rise in amount and complexity of data generation from these systems. Smart homes collect data on various parameters such as energy consumption, temperature, humidity, and occupancy, among others. Efficient data collection and analysis is crucial for smart homes to operate efficiently and reduce energy consumption. While smart homes offer many advantages, the efficient data analytics for smart home energy usage is a significant challenge. The high volume and complexity of data generated by smart homes require advanced analytics techniques to extract meaningful insights. One key area of research is load forecasting, which involves predicting energy consumption based on historical data. Load forecasting is an important tool for optimizing energy consumption and reducing costs in smart homes. This report presents a study on data analytics and load forecasting for smart home energy usage. The studied forecasting methods include ARIMA and LSTM models. The goal of this study is to develop accurate forecasting models that can predict energy consumption in smart homes, based on historical data, and to evaluate the effectiveness of these methods.