dc.contributor.author | Hemapala, KTMU | |
dc.contributor.author | Wijayapala, WDAS | |
dc.contributor.author | Perera, MK | |
dc.date.accessioned | 2024-01-24T06:01:06Z | |
dc.date.available | 2024-01-24T06:01:06Z | |
dc.date.issued | 2018 | |
dc.identifier.uri | http://dl.lib.uom.lk/handle/123/22109 | |
dc.description | Following papers were published based on the results of this research project. 1. Priyadarshana, H. V. V., Hemapala, K. U., Wijayapala, W. S., Saravanan, V., & Boralessa, M. K. S. (2019, August). Developing Multi-Agent Based Micro-Grid Management System in JADE. In 2019 2nd International Conference on Power and Embedded Drive Control (ICPEDC) (pp. 552-556). IEEE. 2. Perera, M. K., R. U. I. Disanayaka, E. M. C. S. Kumara, W. M. C. S. B. Walisundara, H. V. V. Priyadarshana, E. M. A. G. N. C. Ekanayake, and K. T. M. U. Hemapala. "Multi agent based energy management system for microgrids." In 2020 IEEE 9th Power India International Conference (PIICON), pp. 1-5. IEEE, 2020. HVV Priyadarshana, MA Kalhan Sandaru, KTMU Hemapala, WDAS Wijayapala. A review on Multi-Agent system based energy management systems for micro grids[J]. AIMS Energy, 2019, 7(6): 924-943. doi: 10.3934/energy.2019.6.924 4. M. K. Perera, K. T. M. U. Hemapala and W. D. A. S. Wijayapala, "Developing a Reinforcement Learning model for energy management of microgrids in Python," 2021 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE), 2021, pp. 68-73, doi: 10.1109/ICCIKE51210.2021.9410754. 5. M. K. Perera, K. T. M. U. Hemapala and W. D. A. S. Wijayapala, "Grid dependency minimization of a microgrid using Single and Multi-agent Reinforcement Learning," 2021 IEEE Region 10 Symposium (TENSYMP), 2021, pp. 1-8, doi: 10.1109/TENSYMP52854.2021.9550914. | en_US |
dc.description.abstract | This research focuses on a novel approach which is multi-agent-based control systems for microgrids. A microgrid is important in integrating distributed generators and local loads. Unlike the conventional centralized control, multi-agent system provides a distributed control over the distribution network. A multi agent system comprises of multiple agents. These agents are hardware or software entities that can interact with each other in realizing the objectives of the microgrid. The main objective of this research was achieving the energy management function of a microgrid through a multi-agent-based control system. In addition to that, it was aimed to advance the multiagent system by introducing Reinforcement Learning as a machine learning approach. As the energy management function grid consumption minimization of the proposed microgrid and the maximum utilization of the renewable generation was under consideration. The proposed system was initially simulated in Python. The simulation results were obtained for the performance of the microgrid ensuring that the modeled agents are capable of minimizing the dependency of the microgrid on the grid in catering for the its loads. The trained system using Reinforcement Learning is applied to the microgrid testbed to simulate the proposed system using real time data. As the outcome of this research a complete software solution for the grid consumption minimization together with a hardware platform to test the real operation can be stated. | en_US |
dc.description.sponsorship | Senate Research Committee | en_US |
dc.language.iso | en | en_US |
dc.subject | MULTI AGENT SYSTEM | en_US |
dc.subject | MICROGRIDS | en_US |
dc.subject | DISTRIBUTION NETWORK | en_US |
dc.subject | ELECTRICAL ENGINEERING -Research | en_US |
dc.subject | SENATE RESEARCH COMMITTEE – Research Report | en_US |
dc.title | Multi agent system based microgrids for distribution network | en_US |
dc.type | SRC-Report | en_US |
dc.identifier.department | Department of Electrical Engineering | en_US |
dc.identifier.accno | SRC176 | en_US |
dc.identifier.year | 2018 | en_US |
dc.identifier.srgno | SRC/LT/2018/22 | en_US |