IoT based Linear Models Analysis for Demand-Side Management of Energy in Residential Buildings

In modern homes, energy consumption accounts for most of the economic aspects and environmental sustainability. Intelligent energy management and its control play an important role in energy supply and demand; and it will change behavior and environmental changes. For energy management and its control, a hybrid Internet of Things (IoT) and personal wireless network-based devices have been developed. In terms of the need-side-management approach, the use of energy can be intelligently controlled by the device for greater durability. In this study, electricity consumption and utilization are categorized accurately based on data collected from consumer behavior in energy consumption and utilization. First, the data cut through the device is used to identify and summarize the power consumption patterns hidden in the data. Second, the different linear mode algorithms extracted from the Schick-Lear Python library will be used for energy consumption and its intelligent power control. By analyzing different algorithms, the predictive score is found to be sufficiently efficient for the recurrence prediction, while the multi-step and lead-time technique proved to be suitable for multidimensional energy prediction. Results show that root squared mean error (RSME) performance of the predictive model increased by 35% in the lead time approach. Similarly, in per day approach it is 33% more efficient than the recursive model when residual energy forecasting is utilized.