Abstract
This paper presents a hardware testbed for testing the building energy management system (BEMS) based-on the multi agent system (MAS). The objective of BEMS is to maximize user comfort while minimizing the energy extracted from the grid. The proposed system implements a multi-objective optimization technique using a genetic algorithm (GA) and the fuzzy logic controller (FLC) to control the room temperature and illumination setpoints. The agents are implemented on the low cost embedded systems equipped with the WiFi communication for communicating between the agents. The photovoltaic (PV)-battery system, the air conditioning system, the lighting system, and the electrical loads are modeled and simulated on the embedded hardware. The popular communication protocols such as Message Queuing Telemetry Transport (MQTT) and Modbus TCP/IP are adopted for integrating the proposed MAS with the existing infrastructures and devices. The experimental results show that the sampling time of the proposed system is 16.50 s. Therefore it is suitable for implementing the BEMS in a real-time where the data are updated in an hourly or minutely basis. Further, the proposed optimization technique shows better results in optimizing the comfort index and the energy extracted from the grid compared to the existing methods.
Highlights
An energy management system is one of the popular and challenging topics in the electrical power system
A different multi agent system (MAS) architecture of the home energy management systems (HEMSs) is proposed in [8], where the agents are divided into four categories: (a) control and monitoring agents (CMAs), which are used to control and monitor the actuators and sensors; (b) information agents (IAs), which is used to handle the data related to the home devices; (c) application agents (AAs), which are used for prediction, scheduling and feedback functions; (d) management and optimization agents (MOAs), which are used for the optimization tasks
The main contributions of our hardware testbed system are fivefold: (a) It implements the genetic algorithm (GA) technique on the embedded hardware for real-time optimization of the building energy management system (BEMS); (b) It emulates the generator system and the loads on the embedded hardware; (c) It adjusts the room temperature and illumination setpoints according to the optimized power; (d) It implements the popular industrial communication protocol, i.e., Modbus protocol [39] for interfacing between the agents and the devices; (e) It implements the state of the art communication protocol in the Internet of Things (IoT) technology, i.e., the Message Queuing Telemetry Transport (MQTT) protocol [40] for communicating between the agents
Summary
An energy management system is one of the popular and challenging topics in the electrical power system. A different MAS architecture of the HEMS is proposed in [8], where the agents are divided into four categories: (a) control and monitoring agents (CMAs), which are used to control and monitor the actuators and sensors; (b) information agents (IAs), which is used to handle the data related to the home devices; (c) application agents (AAs), which are used for prediction, scheduling and feedback functions; (d) management and optimization agents (MOAs), which are used for the optimization tasks. The hub contains the heat exchanger, the power electronic devices, the compressors, the transformers, the battery and the hot water storage This approach may reduce the energy cost and air pollution. Based-on the implementation platform, they are divided into the simulation-based implementation and the hardware-based implementation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
