Power System Load Frequency Active Disturbance Rejection Control via Reinforcement Learning-Based Memetic Particle Swarm Optimization

Abstract

Load frequency control (LFC) is necessary to guarantee the safe operation of power systems. Aiming at the frequency and power stability problems caused by load disturbances in interconnected power systems, active disturbance rejection control (ADRC) was designed. There are eight parameters that need to be adjusted for an ADRC, which are challenging to adjust manually, thus limiting the development of this approach in industrial applications. Regardless of the theory or application, there is still no unified and efficient parameter optimization method. The traditional particle swarm optimization (PSO) algorithm suffers from premature convergence and a high computational cost. Therefore, in this paper, we utilize an improved PSO algorithm, a reinforcement-learning-based memetic particle swarm optimization (RLMPSO), for the parameter tuning of ADRC to obtain better control performance for the controlled system. Finally, to highlight the advantages of the proposed RLMPSO-ADRC method and to prove its superiority, the results were compared with other control algorithms in both a traditional non-reheat two-area thermal power system and a non-linear power system with a governor dead band (GDB) and a generation rate constraint (GRC). Moreover, the robustness of the proposed method was tested by simulations with parameter perturbations and different working conditions. The simulation results showed that the proposed method can meet the demand for the frequency deviation to stabilize to 0 in LFC with higher performance, and it is worthy of popularization and application.

A novel ensemble deep reinforcement learning model for short‐term load forecasting based on Q‐learning dynamic model selection

“…The agent of Q‐VMD‐RLG continuously learns to find the optimal policy π based on action value function Q ( S ( t ), a ( t )) and continuously updates action a ( t ) to maximize the value of Q [72–76], thus obtaining the optimal action‐value function Q * ( S ( t ), a ( t )) [77, 78], which is updated as shown in Equation (16). $$$$\begin{eqnarray} Q( {S(t),a(t)} ) &=& ( {1 - \alpha } )Q( {S(t),a(t)} ) + \alpha \left[ R(t + 1)\right.\nonumber\\ && + \left.\,\gamma \max Q( {S(t + 1),a(t + 1)} )\right ]\end{eqnarray}$$$$where Q ( S ( t ), a ( t )) are the values of the action value function at moment t , S ( t ) and a t denote state and action executed by the agent at moment t .…”

“…The agent of Q-VMD-RLG continuously learns to find the optimal policy π based on action value function Q(S(t), a(t)) and continuously updates action a(t) to maximize the value of Q [72][73][74][75][76], thus obtaining the optimal action-value function Q*(S(t), a(t)) [77,78], which is updated as shown in Equation (16).…”

A Bi-Level Differential Game-Based Load Frequency Control With Cyber-Physical Security

“…Based on the individual values of η m (t), the j th instance of η(t) is denoted as η j (t). Consequently, the attacker has two choices: m measurements carry the real data y m (t) or compromised data y ma (t): (7) where C m denotes the m th row of:…”

“…Meanwhile, power systems operate in the presence of disturbances [6]. Disturbances caused by the load variation from their forecasted value have been considered in [7]. However, unlike the existing literature, the effect of the disturbances has been taken into consideration during the design procedure of control and attack strategies.…”