• Bandari Rajkumar
• Thumula Venugopal

Automatic generation control(AGC) is one of the most critical issues in multi area power system control. AGC models encounters many problems like imbalance between generation and load demand, data exchanging, calculation complexities and memory requirements. To overcome such difficulties this paper presents a controller based on multi agent system (MAS). Change in communication topology, time delay , network induced effects are used to test the system performance. a controller design based on reinforcement learning and it has two individual agents namely controller agent and estimator agent. for the tuning of input parameter particle swarm optimization is used. Furthermore, controller design and control scheme are described. Mean square error of different states of the power system are analyzed in addition. The simulation results shows the capability of proposed controller for distributed automatic generation control in multi area power system.

Communication topology (CT), Automatic Generation Control (AGC), multi-agent reinforcement learning (MARL), smart grid (SG)

"Distributed Automatic Generation Control For Multi Area Power System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 10, page no.96-101, October-2018, Available :http://www.jetir.org/papers/JETIRJ006015.pdf

"Distributed Automatic Generation Control For Multi Area Power System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 10, page no. pp96-101, October-2018, Available at : http://www.jetir.org/papers/JETIRJ006015.pdf