Power system load frequency control using RBF neural networks based on μ-synthesis theory

Transmission line (TL) parameters are the basis of power system calculation. In recent years, artificial intelligence has been widely applied and plays a great role in the power system. However, artificial intelligence is rarely applied to transmission line parameter identification. Therefore, from the perspective of line model and artificial intelligence, combined with median estimation and modified Supervisory Control And Data Acquisition (SCADA) data based on TL model, this paper proposes a robust method for parameter identification of TL based on Radial Basis Function (RBF) neural network and modified SCADA data. Firstly, the line parameter identification method based on RBF neural network is proposed. Then, the training set is established through the π-equivalent model in consideration of different operating conditions and different circuit parameters. Furthermore, the input data of RBF neural network is construed by modifying the SCADA data based on TL model. In addition, the median estimation robust method, which can estimate the final result and reduce the noise interference, is introduced. Finally, the validity and practicability of the proposed method are verified by simulation data and measured SCADA data respectively.

In this paper a robust and adaptive temporal difference learning based MLP (TDMLP) neural network for power system load frequency control (LFC) is presented. Power systems, such as other industrial processes, are nonlinear and have parametric uncertainties that for controller design had to take the uncertainties into account. For this reason, in the design of LFC controller the idea of TDMLP neural network is being used. Some simulations with two interconnections are given to illustrate proposed method. Results on interconnected power system show that the proposed method not only is robust to increasing of load perturbations and operating point variations, but also it gives good dynamic response compared with traditional controllers. It guarantees the stability of the overall system even in the presence of generation rate constraint (GRC). To evaluate the usefulness of proposed method we compare the response of this method with RBF neural network and PID controller. Simulation results show the TDMLP has the better control performance than RBF neural network and PID controller.

Wavelet based feature extraction of voltage profile for online voltage stability assessment using RBF neural network

At present, simple and classical tuned controllers are widely used in the power system load frequency control (LFC) application. Existing LFC system parameters are usually tuned based on experiences, classical methods, and trial and error approaches, and they are incapable of providing good dynamic performance over a wide range of operating conditions and various load scenarios. Therefore, the novel modeling and control approaches are strongly required, to obtain a new trade-off between efficiency and robustness. Thus, the proposed techniques in this chapter are referred to be an adaptive control technique based on new optimization methods such as Jaya, Practical Swarm Optimization Algorithm, etc., which are used to make an on-line tuning of the LFC parameters in order to face the previous challenges in LFC. The system under study is a small microgrid with a renewable energy source and variable demand load. Digital simulation results are discussed.

In this study, a particle swarm optimization (PSO) based Multi-Agent Reinforcement Learning (MARL) approach for load frequency control (LFC) of multi-area power system over communication network considering communication delay and packet loss is presented. A networked control system (NCS) is framed to model a constant delay and packet loss using Markovian approach. The controller using PSO based MARL technique having two levels of controlled action in each area of power system act as an estimator agent and controller agent respectively. The proposed method for frequency regulation of multi-area power system is studied in detail and verified for different types of load disturbances. In addition, to check the system dynamic performance of electric power system a mean square errors (MSEs) of states with different value of communication delay are computed. The simulation results of this study is validated and compared with some pre-design methods available from literatures, along with capacity of multi agent system (MAS) for application of LFC in power system over communication network.

A wind power system (WPS) involving a flywheel energy storage (FES) unit is proposed to reduce the fluctuation of output power due to the intermittent nature of wind power. The control of the FES unit is based on a wind speed forecasting technique by the RBF neural network. A new control strategy adopting different reference DC bus voltages under different forecasting wind speeds is presented to improve the output power regulation capability of the FES unit. The wind speeds in the next time array can be accurately forecasted by the radical basis function (RBF) neural network. The mathematical model of a stand-alone wind power generation system including a FES unit is established and simulated by Matlab/Simulink. The simulation results verify the correctness of the system model and the effectiveness of the control method.

Short-term load forecasting of power system is not only the basis of scheduling of generating sets, but also the basis of working out the transaction schedule in electricity market. This paper proposes a short-term load forecasting method based on combination of radial basis function (RBF) neural network and fuzzy control, uses on-line self-modify factor fuzzy control to eliminate forecast error on the basis of RBF neural network forecasting. The practical examples show that the accuracy of short-term load forecasting and training speed can be improved and gains the very satisfactory results by the proposed method

With the increasing penetration of renewable energy and power electronic devices, the frequency fluctuation of the power system will increase sharply, the inertia will decrease significantly, the damping characteristics will be poor, and the frequency adjustment ability needs to be improved. In this paper, a DRL (deep reinforcement learning) based framework is propsed to solve the LFC (load frequency control) problem for power system. This paper first introduces the model of LFC and basic description of DRL. Then the flow of twin delayed deep deterministic policy gradient (TD3) algorithm and a general framework for load frequency control. Finally, the proposed method is verified through a single area LFC test system. The implementation demonstrates that the proposed method is effective in LFC problem.

The load frequency control (LFC) problem has been one of the major subjects in electric power system design and operation. LFC is becoming much more significant today in accordance with increasing size, changing structure and complexity in interconnected power systems. Practice LFC systems use simple proportional-integral (PI) controllers, but parameters of PI controllers are usually tuned based on the trial-and-error approaches and they are incapable to obtain good dynamic performance under a wide range of operating conditions. For this problem, in this paper quantitative feedback theory (QFT) method is used for LFC problem. A multi-area electric power system with a wide range of parametric uncertainties is given to illustrate proposed method. To show effectiveness of proposed method, a classical PI type controller optimized by genetic algorithms (GA) is designed to compare with QFT controller. The simulation results visibly show the validity of QFT method in comparison with traditional method. Key words: Multi-area electric power system, electric power system load frequency control, robust control, quantitative feedback theory method.

Persistent electrical supply requires the power systems to be stable and reliable. Against varying load conditions, control strategies such as load frequency control (LFC) is a key mechanism to protect its stability. Traditional control strategies for LFC often face challenges due to system uncertainties, external disturbances, and nonlinearities. This paper presents an advanced approach to control load frequency and enhancing LFC in power systems by using sliding mode control (SMC). SMC offers powerful stability and robustness versus nonlinearities and perturbation, making it a promising approach for addressing the limitations of conventional control methods. We contemporary a comprehensive analysis of the SMC approach tailored for LFC, including the strategy and employment of the control algorithm. The proposed method makes use of a sliding/gliding surface to enable the system trajectories to be continuous on this surface despite parameter variations and external disturbances. Simulation results demonstrate significant improvements in frequency stability and system performance compared to conventional proportional-integral-derivative (PID) controllers. The paper also includes a comparative analysis of SMC with other modern control techniques, highlighting its advantages in terms of robustness and adaptability.

Model reference adaptive sliding mode control (MRASMC) using radical basis function (RBF) neural network (NN) is proposed to control the single-phase active power filter (APF). The RBF NN is utilized to approximate nonlinear function and eliminate the modeling error. AC side model reference adaptive current controller not only guarantees the globally stability of the APF system but also generate the compensating current to track the harmonic current accurately. Moreover, a sliding mode controller based on exponential approach is designed to improve the tracking performance of DC side voltage. Simulation results demonstrate that MRASMC using RBF NN can improve the adaptability and robustness of the APF system and track the given instructional signal quickly.

To improve the accuracy of tracking unmanned vehicles on known trajectories, two optimised model predictive control (MPC) trajectory tracking control systems are designed based on the adaptive compensation and robust control of a radial basis function (RBF) neural network. Based on the traditional MPC trajectory tracking controller and the local approximation characteristics of the RBF neural network, the proposed RBF compensation–MPC control system is designed to compensate for the inaccuracy in the MPC prediction model arising from modelling errors. The results show that this method can achieve a root mean square error of less than 0.3703 m for the lateral position. Subsequently, to suppress the error generated by the RBF neural network and reduce the degree of vehicle sideslip, the error is considered to be external interference, and the anti-interference characteristic of the RBF robust control is incorporated into the RBF robust-MPC control system. Following the re-optimisation of the RBF robust control, the root mean square error of the lateral position is set within 0.2352 m. The results of a MATLAB/Carsim joint simulation show that using the RBF robust control can improve the tracking accuracy of the traditional MPC controller compared with RBF compensation control, while simultaneously improving the driving stability of the vehicle.

To ensure the control of the precision of air-fuel ratio (AFR) of port fuel injection (PFI) spark ignition (SI) engines, a chaos radial basis function (RBF) neural network is used to predict the air intake flow of the engine. The data of air intake flow is proved to be multidimensionally nonlinear and chaotic. The RBF neural network is used to train the reconstructed phase space of the data. The chaos algorithm is employed to optimize the weights of output layer connection and the radial basis center of Gaussian function in hidden layer. The simulation results obtained from Matlab/Simulink illustrate that the model has higher accuracy compared to the conventional RBF model. The mean absolute error and the mean relative error of the chaos RBF model can reach 0.0017 and 0.48, respectively.

In this paper an optimal load-frequency controller for a nonlinear power system is proposed. The mathematical model of the power system consists of one area with several power plants, a few concentrated loads and a transmission network, along with simplified models of the neighbouring areas. Firstly, a substitute linear model is derived, with its parameters being identified from the responses of the nonlinear model. That model is used for load-frequency control (LFC) algorithm synthesis, which is based on discrete-time sliding mode control. Due to a non-minimum phase behaviour of hydro power plants, full-state feedback sliding mode controller must be used. Therefore, an estimation method based on fast output sampling is proposed for estimating the unmeasured system states and disturbances. Finally, the controller parameters are optimized using a genetic algorithm. Simulation results show that the proposed control algorithm with the proposed estimation technique can be used for LFC in a nonlinear power system.

In this paper, a wide area measurement, centralized, load frequency control using model predictive control (MPC) is presented for multi-area power systems. A multivariable constrained MPC was used to calculate optimal control actions including generation rate constraints. To alleviate computational effort and to reduce numerical problems, particularly in large prediction horizon, an exponentially weighted functional MPC was employed. Time-based simulation studies were performed on a three-area power system, and the results were then compared with decentralized MPC and classical PI controller. The results show that the proposed MPC scheme offers significantly better performance against load disturbance. Copyright © 2013 John Wiley & Sons, Ltd.