Load Shedding in Microgrids with Dual Neural Networks and AHP Algorithm

Abstract

This paper proposes a new load shedding method based on the application of a Dual Neural Network (NN). The combination of a Back-Propagation Neural Network (BPNN) and of Particle Swarm Optimization (PSO) aims to quickly predict and propose a load shedding strategy when a fault occurs in the microgrid (MG) system. The PSO algorithm has the ability to search and compare multiple points, so the proposed NN training method helps determine the link weights faster and stronger. As a result, the proposed method saves training time and achieves higher accuracy. The Analytic Hierarchy Process (AHP) algorithm is applied to rank the loads based on their importance factor. The results of the ratings of the loads serve as a basis for constructing the load shedding strategies of a NN combined with the PSO algorithm (ANN-PSO). The proposed load shedding method is tested on an IEEE 25-bus 8-generator MG power system. The simulation results show that the frequency recovery of the power system is positive. The proposed neural network adapts well to the simulated data of the system and achieves high performance in fault prediction.

Prioritisation of Environmental Improvement Projects in Deep-Level Mine Ventilation Systems

“…Several studies considered incorporating additional aspects, such as the risk factor that is difficult to quantify during the decision-making process, but were unable to do so as the decision is left open to bias [6,9,13,14,19,20]. Multi-criteria decision-making (MCDM) methods have been used in many industries to assist decision-makers with multicriteria decision-making [24][25][26][27][28][29]. Mining-related studies are contemplated in more detail in the remainder of this section.…”

Levy Enhanced Cross Entropy-based Optimized Training of Feedforward Neural Networks

“…Authors in [10] proposed a Particle Swarm Optimization (PSO)-based neuro-fuzzy model to enhance dynamic voltage stability of a wind connected grid. Authors in [11] proposed a PSO-powered back-propagation neural network load-shedding strategy in the post-fault condition in a microgrid. Another AI method is Gravitational Search Algorithm (GSA) [12], which has been inspired from the law of gravity and mass interactions.…”

“…These measures were used initially to create a linear model to classify the species in machine learning. Different hidden nodes such as H=4, 5,6,7,8,9,10,11,12,13,14 environment, Intel CORE i5 with 16 GB RAM. All tested methods find the optimal combinations of the weights and biases which results into minimum error of the FNN.…”

Pelican Optimization Algorithm for Optimal Demand Response in Islanded Active Distribution Network Considering Controllable Loads

“…In [19], a multiple-deme parallel genetic algorithm (MDPGA) is introduced for load balance when there is a low voltage stability margin due to either line contingencies and/or generator failures. In [20][21][22], based on the coordination of the load importance factor (LIF), the reciprocal phase angle sensitivity (RPAS), and the voltage electrical distance (VED) to rank the load buses, the analytical hierarchy process (AHP) algorithm-based approach to load shedding for restoring the frequency under generation shortage is used. In [23], conservative voltage reduction (CVR) based load shedding is implemented while restoring the RE integrated distribution network from an intentional island using mixed-integer quadratic constraint programming (MIQCP).…”