In a renewable energy-based islanded microgrid system, frequency control is one of the major challenges. In general, frequency oscillations occur in islanded microgrids due to the stochastic nature of load and variable output power of distributed generating units (DGUs). In the presented research proposal, frequency oscillations are suppressed by implementing the proportional integral derivative (PID) controller-based control design strategy for an islanded microgrid. The modeling of the islanded microgrid is firstly presented in the form of a linearized transfer function. Further, the derived transfer function is approximated into its equivalent first-order plus dead time (FOPDT) form. The approximated FOPDT transfer function is obtained by employing the reaction curve method to calculate the parameters of the FOPDT transfer function. Furthermore, the desired frequency regulation is achieved for the manifested FOPDT transfer function by incorporating PID control design. For PID controller tuning, different rule-based methods are implemented. Additionally, comparative analysis is also performed to ensure the applicability of the comparatively better rule-based tuning method. The Wang–Chan–Juang (WCJ) method is found effective over other rule-based tuning methods. The efficacy of the WCJ method is proved in terms of transient response and frequency deviation. The tabulated data of tuning parameters, time domain specifications, and error indices along with responses are provided in support of the presented control strategy.

Microgrids are being considered to be very crucial in enhancing the involvement of renewable energy sources (RESs) in electrical grids and also improving their overall sustainability and resilience. Modern day control techniques are getting attention by researchers for optimal control and management of microgrids, as it is found in many articles that classical control techniques are short-falling in adaptability in different environments, data handling and data driven decision making. This article provides systematic review to follow a thorough evaluation of the present status of research on reinforcement learning (RL)-based microgrid control. The description of microgrid systems, their components, control and management challenges are also provided in this survey. Further, majorly implemented RL-based algorithms for microgrid control are discussed. Summary and critical assessment of main findings and contributions in this field are tabulated through methodical categorization of selected articles. Emerging algorithms for microgrid control are also discussed thoroughly. A comparative analysis based on performance of RL algorithms, and RL based control with other types of control frameworks is also systematically presented. Further safety and deploying challenges, along with ongoing trends in RL implementation for microgrids, are elaborated. This work will be helpful for practitioners and researchers who want to investigate the best way to design microgrid systems, especially when it comes to using RL algorithms for microgrid control systems and management.

Automatic generation control (AGC) is employed in power systems to maintain balance between generation and load by adjusting output of generators in real time. Controller continuously monitors system frequency and tie-line power flow by responding to fluctuations in electricity demand and supply and optimizes generator dispatch, reduces power imbalances, and enhances grid stability. This work proposes and solves the issues of the AGC in two-area interconnected power systems by proposing a new approach based on both Jaya algorithm and the rank exponent method. In particular, we design a proportional-integral-derivative controller with derivative filtering (PIDm), where the effect of the noise is mitigated by the use of a filter with derivative gain. We propose to build the objective function, to tune the controller’s parameters, as the linear combination of three sub-objectives, namely integral of time multiplied absolute error (ITAE) for frequency deviations, tie-line power deviation, and area-control errors (ACEs). The rank method is exploited to evaluate the weights of these sub-objectives, while the final overall objective function is minimized exploiting the Jaya algorithm. The proposed controller’s performance is assessed in six different scenarios with load disturbances, and its effectiveness is compared to state-of-art controllers tuned using salp swarm algorithm (SSA), Nelder-Mead simplex (NMS), symbiotic organisms search (SOS), elephant herding optimization (EHO), and Luus-Jaakola (LJ) optimization algorithms. To illustrate the frequency and tie-line power changes, results are also shown, and a statistical study is finally carried out to evaluate the recommended controller’s overall effectiveness. Additionally, Friedman rank test as no-parametric statistical analysis is also done in order to evaluate the significance level of optimization algorithms. Our numerical findings evidence that the proposed PIDm controller outperforms other existing optimization-based controllers in terms of performance and utility, thus proving to be very effective for handling AGC issues in two-are interconnected power systems.

Mobile ad hoc network (MANET) is a self-configuring network that is formed automatically via wireless links by a collection of mobile nodes without the help of a fixed infrastructure or centralized management. Due to dynamic infrastructure-less nature and lack of centralized monitoring points, the ad hoc networks are vulnerable to Black hole Attack. The network performance and reliability is broken by the attacks on ad hoc routing protocols. Many mechanisms have been proposed to overcome the Black hole Attack. A malicious node or black hole node send Route Response (RREP) incorrectly of having route to destination with minimum hop count and when sender sends the data packet to this malicious node, it drops all the packet in the network. The propose watchdog mechanism detect this black hole nodes in a MANET. This method first detects a black hole node in the network and then provide a new route to source node. In this, the performance of original-AODV and modified AODV called as watchdog-AODV (or W-AODV) in the presence of multiple black hole nodes is find out on the basis of throughput and packet delivery ratio and routing and control load.

The ability of a neural network to realize some complex nonlinear function makes them attractive for system identification. In the recent past, neural networks trained with back-propagation (BP) learning algorithm have gained attention for the identification of nonlinear dynamic systems. Slower convergence and longer training times are the disadvantages often mentioned when the standard BP algorithm are compared with other competing techniques. In addition, in the standard BP algorithm, the learning rate is fixed and that it is uniform for all weights in a layer. In this paper, we present an improvement to the standard BP algorithm based on the use of an adaptive learning rate and momentum term, where the learning rate is adjusted at each iteration to reduce the training time. Simulation results indicate a faster convergence speed and better error minimization as compared to other competing methods.

Mobile Ad hoc NETwork (MANET) is an autonomous, infrastructure-less, self-configuring and self-healing system of mobile nodes connected by wireless links. The nodes are free to move about randomly and may join or leave the network at their will. Due to the mobile nature of the nodes and the unreliable nature of some nodes in a MANET, a critical issue of consistent performance of such a network arises. Here, the concept of routing comes into the picture. Routing refers to the discovery of a reliable-optimal path for data communication between the nodes in a network. The objective of this paper is at describing an optimized method to establish an optimal path between a pair of nodes and detect the misbehaving (selfish, incapable) nodes in MANET. This improves the performance of a routing protocol because in majority of the poor performing networks, the misbehaving nodes are the major cause. To find an optimal path between a set of nodes, DSR protocol has been deployed (using the NS2 simulator) followed by the application of Genetic Algorithm in detecting the selfish nodes. Since the misbehaving node(s) are successfully detected, it proves that the proposed approach is optimal and efficiently improves the performance of DSR protocol significantly. But, sometimes the routes found out by GA are not the ultimate best routes hence to doubly ensure the maximum optimality in the routes found out, ACO (Ant Colony Optimization) has been used.