Adaptive Neural Network Linear Parameter-Varying Control of Shipboard Direct Current Microgrids

Abstract

To avoid pollution of transportation applications, renewable energies are deployed. Whereas they are uncontrolled, fully controlled pollution-free energy sources and storage units should be also considered. However, a complicated direct current (DC) microgrid (MG) is obtained, which suffers from nonlinearities, high order, and uncertainties of the power elements. Therefore, it is vital to use advanced nonlinear controllers to assure closed-loop stability and performance of the overall system. In this paper, a neural network (NN)-based adaptive linear parameter varying (LPV) controller is suggested for the whole DC MG power system. The main advantage of the developed controller is that it deploys the operating information of all power energy sources to manipulate each component. This enhances the DC MG stability margin and fast regulation of the power and voltage. Besides, the proposed controller has a systematic and fully offline design algorithm by combining numerical solvers and theoretical theories. The LPV controller is designed via the numerical linear matrix inequality (LMI) approach and the adaptation law for the NN parameters is designed based on the Lyapunov stability theory. A DC MG benchmark including a 5kW fuel cell, a 5kW solar plant, and a 2kW battery package is considered as the case study, which can be utilized in future fully electric boats (EBs). Numerical simulations with different scenarios are conducted to verify the performance of the proposed controller. Furthermore, comparative results are provided to show the advantages of the proposed method dealing with power fluctuations of the solar plant and DC loads over state-of-the-art nonlinear methods.

Accurate voltage regulation for a DC microgrid using nonlinear state feedback controller

“…• Partial state feedback design capability • Reducing the requirement for additional sensors • Cost-effective To be more precise, partial state feedback capability is a merit of the proposed nonlinear state feedback controller over the nonlinear controller presented in [29]. Notably, this point has not been discussed in [32].…”

“…In contrast to the conventional nonlinear EKF, the proposed dual-EKF [31] exhibits higher accuracy in stabilizing DC MG as it accounts for actuator faults. A hybrid controller (Neural Net + LPV) has been studied in [32]. The proposed controller provides semi-global stability compared to conventional controllers such as PID [33] and the one proposed in [29], which primarily ensure local stability.…”

“…2. Compared with [29,32]: The proposed controller benefits from partial state feedback capability, which means that in practical situations where measuring all state variables may not be, often due to reasons such as cost limitations of sensors or system complexity, one has the flexibility to set the corresponding columns of unmeasurable states in the k matrix to zero. Moreover, by carefully selecting k matrix, excellent control performance can still be achieved.…”

Distributed Energy Storage Scheduling Optimization of Micro Grid Based on Particle Swarm Optimization Algorithm

“…It is very important that micro networks operate on the basis of communication systems. Predict network reliability and events that may have negative impact accordingly [11][12].…”

License Plate Recognition Technology Based on Neural Network

“…NN is a typical nonlinear mapping, which has good fault tolerance, self-learning and self-monitoring characteristics [15][16]. In practical application, it is mainly realized by training the input image.…”