Development of IoT based system for energy management system

Bahsharudin, Muhammad Ridzwan (2024) Development of IoT based system for energy management system. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (Full Text) Development of IoT based system for energy management system.pdf - Submitted Version Download (3MB)

Abstract

Energy Management Systems (EMS) have become essential in optimizing energy consumption in the built environment, particularly in commercial buildings. This project presents the development and application of a sophisticated IoT-based EMS, aimed at enhancing energy efficiency in air conditioning and lighting systems. At its core, a rule-based algorithm is employed to improve decision-making regarding energy use intensity and timing. EMS integrates advanced IoT devices and sensors for continuous monitoring and intelligent control of energy usage, leading to substantial energy savings. The algorithm, designed to optimize energy consumption, takes into account parameters like power consumption, illuminance, and room temperature. Its effectiveness is evidenced by a comparative analysis based on a 24-hour monitoring experiment conducted in two phases. These experiments reveal the algorithm's significant impact on energy usage optimization. The report details the IoT infrastructure, the design and implementation of the Fuzzy Logic Rule-Based algorithm, and the data analytics methodologies used. The automated decision-making process of the system efficiently reduces overall consumption, enhances energy efficiency, and lowers operational costs in commercial settings. The result of this project highlights the successful integration of IoT with a Fuzzy Logic Rule-Based approach, significantly improving energy management. The system, characterized by its real-time monitoring and automation capabilities, demonstrated a remarkable advancement in managing energy consumption. Notably, the lighting system observed a 69.41% decrease in energy consumption, while the air conditioning system saw a 30.6% decrease. These results underscore the algorithm's precision in managing energy usage, emphasizing its contribution to sustainable energy practices. Future work will focus on developing a predictive model for energy consumption data, using the XGBoost framework for enhanced accuracy in forecasting energy needs. This advancement is crucial for effective energy management, leading to optimized energy distribution and utilization. The predictive model, as an extension of this project, marks a significant step towards intelligent, efficient, and proactive energy management, aligning with sustainable development goals.

Actions (login required)

View Item