Using Orthogonal Grey Wolf Optimizer with Mutation for Training Multi-Layer Perceptron Neural Network

Zhang, Sen; Zhou, Yongquan; Song, Junmin; Zhao, Chenping

doi:10.1166/jctn.2016.5319

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen, by equations (19)–(22), The weights and biases are the main elements of MLPs, that determine the final output values based on given inputs (Zhang et al , 2016). The precise description of training MLPs is to find appropriate weights and biases values to reach the desired relationship between inputs and outputs (Mirjalili, 2015).…”

Section: Feed-forward Neural Network and Multi-layer Perceptronmentioning

confidence: 99%

A multi-objective grey wolf optimizer (GWO)-based multi-layer perceptrons (MLPs) trainer for optimal PMUs placement

Laouid

Mohrem

Djalab

2021

COMPEL

View full text Add to dashboard Cite

Purpose This paper aims to find the minimum possible number of phasor measurement units (PMUs) to achieve maximum and complete observability of the power system and improve the redundancy of measurements, in normal cases (with and without zero injection bus [ZIB]), and then in conditions of a single PMU failure and outage of a single line. Design/methodology/approach An efficient approach operates adequately and provides the optimal solutions for the PMUs placement problem. The finest function of optimal PMUs placement (OPP) should be mathematically devised as a problem, and via that, the aim of the OPP problem is to identify the buses of the power system to place the PMU devices to ensure full observability of the system. In this paper, the grey wolf optimizer (GWO) is used for training multi-layer perceptrons (MLPs), which is known as Grey Wolf Optimizer (GWO) based Neural Network (“GW-NN”) to place the PMUs in power grids optimally. Findings Following extensive simulation tests with MATLAB/Simulink, the results obtained for the placement of PMUs provide system measurements with less or at most the same number of PMUs, but with a greater degree of observability than other approaches. Practical implications The efficiency of the suggested method is tested on the IEEE 14-bus, 24-bus, New England 39-bus and Algerian 114-bus systems. Originality/value This paper proposes a new method for placing PMUs in the power grids as a multi-objective to reduce the cost and improve the observability of these grids in normal and faulty cases.

show abstract

Section: Feed-forward Neural Network and Multi-layer Perceptronmentioning

confidence: 99%