TY - GEN
T1 - Catalyzing Energy Balance
T2 - 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
AU - Javaid, Saher
AU - Ioannou, Iacovos I.
AU - Vassiliou, Vasos
AU - Pitsillides, Andreas
AU - Tan, Yasuo
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Renewable energy sources (RESs) such as solar panels and wind turbines are increasingly utilized due to their small ecological footprints. However, their inconsistent power generation results in variations in both power supply and grid stability. Integrating RESs in power grids with AI-driven control systems allows for real-time monitoring and control of the electricity grid. This enables more responsive and adaptive grid management, reducing the impact of imbalances caused by sudden changes in demand or supply. This research proposes utilizing a Distributed AI (DAI) framework to ensure energy balance between supply and demand. DAI agents would be placed on each power device for real-time monitoring and control. In this paper, the performance comparison considering the execution time of two optimization techniques, Particle Swarm Optimization (PSO) and Linear Programming (LP), is investigated considering energy balancing constraints. The simulation results illustrate the effectiveness of both optimization techniques considering the increased number of power devices.
AB - Renewable energy sources (RESs) such as solar panels and wind turbines are increasingly utilized due to their small ecological footprints. However, their inconsistent power generation results in variations in both power supply and grid stability. Integrating RESs in power grids with AI-driven control systems allows for real-time monitoring and control of the electricity grid. This enables more responsive and adaptive grid management, reducing the impact of imbalances caused by sudden changes in demand or supply. This research proposes utilizing a Distributed AI (DAI) framework to ensure energy balance between supply and demand. DAI agents would be placed on each power device for real-time monitoring and control. In this paper, the performance comparison considering the execution time of two optimization techniques, Particle Swarm Optimization (PSO) and Linear Programming (LP), is investigated considering energy balancing constraints. The simulation results illustrate the effectiveness of both optimization techniques considering the increased number of power devices.
KW - Distributed AI
KW - distributed energy resources
KW - power flow control
KW - power fluctuations
KW - power/energy balance
UR - http://www.scopus.com/inward/record.url?scp=85205816232&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Taiwan62264.2024.10674353
DO - 10.1109/ICCE-Taiwan62264.2024.10674353
M3 - Conference contribution
AN - SCOPUS:85205816232
T3 - 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
SP - 257
EP - 258
BT - 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 July 2024 through 11 July 2024
ER -