RBF neural network-based online intelligent management of a battery energy storage system for stand-alone microgrids

Abstract

Background: An offline optimization approach based on energy storage management response in a microgrid was not fast and not reliable enough to control and adjust the system efficiently after the loss of the utility grid. Thus, it causes system inefficiency and collapse in the presence of violent changes of loads or outage of distributed generations. To solve such a problem, more real-time management is needed. Any changes in loads/generations should be compensated successfully by a battery energy storage system (BESS) in a short period of time.Methods: This paper presents a new method for the intelligent online management of both active and reactive power of a BESS based on a radial basis function neural network (RBFNN) incorporating particle swarm optimization (PSO) to prevent the stand-alone microgrid from instability and system collapse. BESS is centrally controlled by a controller developed by the proposed RBFNN. PSO is used to determine the optimized active and reactive power at every load/generation changing situation to monitor the effect of system frequency, voltage, and reference power regulation. These optimized power data are then employed as target data for the RBFNN generalization and training process. To enable the online updating of the operating parameters, the proposed RBFNN is implemented in the management process. With an appropriate RBFNN training, the optimum active and reactive power can directly be obtained without the necessity of performing the PSO optimization process at any change of load/generation. Results: The results show that the predictive results of the proposed RBFNN model only slightly differed from the target results based on PSO and have a minimum statistical error compared to the predictive results based on the multilayer perceptron neural network (MLPNN) model. Conclusions: The proposed RBFNN is suitable for the online estimation of the active and reactive power of BESS and can be used for real-time energy storage management as an online controller.

Optimization Techniques for Operationand Control of Microgrids � Review

“…The interlinking-converter droop is modified and applied to the coordination of a community microgrid. The stability of a stand-alone microgrid is improved by implementing a radial basis function neural network (RBFNN) incorporating particle swarm optimization (PSO) by controlling both active and reactive power of battery energy storage system online is proposed in [36].…”

A prediction‐based optimization strategy to balance the use of diesel generator and emergency battery in the microgrid

“…A lagrange programming neural network was utilized to solve the optimal scheduling problem of a hybrid microgrid, which had a more reasonable objective function and was used for a comprehensive economic emission scheduling problem . Since the response to the energy storage management in a smart microgrid was not fast enough to effectively control and adjust the system of the utility grid losses, Kerdphol et al proposed a new method for the intelligent online management of both active and reactive power of a battery energy storage system based on a radial basis function neural network, which worked with a particle swarm optimization to prevent the stand‐alone microgrid from instability and system collapse. Besides, other theories and methods were used to solve EMS problems. Stochastic, adaptive, dynamic optimization is used to deal with the energy management of microgrid during unscheduled events .…”

Research on Frequency Fuzzy Adaptive Additional Inertial Control Strategy for D-PMSG Wind Turbine

“…Thus far, the robust adaptive control techniques have been developed to deal with changes in system parameters. The applications of neural networks, genetic algorithms, optimal control and model predictive control (MPC) for the frequency control have been reported in [27][28][29][30]. Compared with the abovementioned methods, the fuzzy logic control displays better performance, such that there is no need for accurate mathematical models, robustness against load disturbances and parameter uncertainty.…”