Pradyumna Kumar Tripathy, Anurag Shrivastava, Varsha Agarwal, Devangkumar Umakant Shah, Chandra Sekhar Reddy L. and S.V. Akilandeeswari
This paper aims to provide the security and privacy for Byzantine clients from different types of attacks.
Abstract
Purpose
This paper aims to provide the security and privacy for Byzantine clients from different types of attacks.
Design/methodology/approach
In this paper, the authors use Federated Learning Algorithm Based On Matrix Mapping For Data Privacy over Edge Computing.
Findings
By using Softmax layer probability distribution for model byzantine tolerance can be increased from 40% to 45% in the blocking-convergence attack, and the edge backdoor attack can be stopped.
Originality/value
By using Softmax layer probability distribution for model the results of the tests, the aggregation method can protect at least 30% of Byzantine clients.
Details
Keywords
Rafi Vempalle and Dhal Pradyumna Kumar
The demand for electricity supply increases day by day due to the rapid growth in the number of industries and consumer devices. The electric power supply needs to be improved by…
Abstract
Purpose
The demand for electricity supply increases day by day due to the rapid growth in the number of industries and consumer devices. The electric power supply needs to be improved by properly arranging distributed generators (DGs). The purpose of this paper is to develop a methodology for optimum placement of DGs using novel algorithms that leads to loss minimization.
Design/methodology/approach
In this paper, a novel hybrid optimization is proposed to minimize the losses and improve the voltage profile. The hybridization of the optimization is done through the crow search (CS) algorithm and the black widow (BW) algorithm. The CS algorithm is used for finding some tie-line systems, DG locations, and the BW algorithm is used for finding the rest of the tie-line switches, DG sizes, unlike in usual hybrid optimization techniques.
Findings
The proposed technique is tested on two large-scale radial distribution networks (RDNs), like the 119-bus radial distribution system (RDS) and the 135 RDS, and compared with normal hybrid algorithms.
Originality/value
The main novelty of this hybridization is that it shares the parameters of the objective function. The losses of the RDN can be minimized by reconfiguration and incorporating compensating devices like DGs.