ABSTRACT
Blockchain based microgrid mechanisms can be designed efficiently to provide uninterrupted power supply and to balance load demands dynamically. In this present work, a conceptual design of a microgrid system is proposed in power system modeling. A blockchain based trading mechanism has been implemented on this system. Various optimization algorithms have been used to maximize economic profit. Finally, the Coronavirus Herd Immunity Optimizer (CHIO) algorithm is described to accommodate the impression that arises for the optimal power flow (OPF) and energy capacity. A case study has been provided to authenticate the performance of this method. The result expresses that the present scheme can largely improve the power dispatch and trading system. © 2022 IEEE.
ABSTRACT
In load frequency control (LFC) study of a large power system, the key concept is control area, which is the segment of the system consisting of strongly interconnected buses, generator buses thereof working in unison. For accurate linearization of load frequency control problem, proper determination of control area is important. In the present work, a novel deterministic method is proposed and formulated to calculate the sharing of load changes by the generators to determine the control areas for LFC study of multimachine systems. This method is applied on a weakly interconnected two-area system and then on the 10-Machine New England Test System for area segmentation of each of the two systems. Furthermore, LFC studies are carried out with proposed Fuzzy Rule-tuned PID controllers (FRT-PID Controllers) for both the systems incorporated with Dish-Stirling Solar thermal system (DSTS) in each area. The scaling factors and the controller gains are optimized using Coronavirus Herd Immunity Optimizer Algorithm (CHIOA). Performance of the proposed FRT-PID controllers is compared with that of the Conventional PID controllers for the LFC studies of the systems. To test effectiveness of the FRT-PID controllers, effect of random step load perturbation (SLP) in load buses located in different areas are considered. © 2023 Elsevier B.V.
ABSTRACT
In this study, a computer-assisted kidney stone diagnosis system based on CT images has been proposed. The method is based on a combination of deep training and metaheuristics. The method aims to provide a customized Deep Believe Network (DBN) based on a fractional version of the coronavirus herd immunity enhancer to provide an efficient and reliable kidney stone diagnosis system. The designed method is then authenticated by running a standard benchmark called a "CT kidney dataset". Subsequently, a comparison is made between the results and some other state-of-the-art methods. Simulations show that the recommended DBN/FO-CHIO outperforms the other studied approaches in terms of efficiency with an accuracy of 97.98%. Moreover, the proposed DBN/FO-CHIO recall outperforms others with 92.99%, demonstrating its excellent accuracy compared to other comparison algorithms. Moreover, the higher specificity of the proposed method compared to the other evaluated approaches indicates its advanced event-independent value.Copyright © 2023 Elsevier Ltd
ABSTRACT
The world has now looked towards installing more renewable energy sources type distributed generation (DG), such as solar photovoltaic DG (SPVDG), because of its advantages to the environment and the quality of power supply it produces. However, these sources' optimal placement and size are determined before their accommodation in the power distribution system (PDS). This is to avoid an increase in power loss and deviations in the voltage profile. Furthermore, in this article, solar PV is integrated with battery energy storage systems (BESS) to compensate for the shortcomings of SPVDG as well as the reduction in peak demand. This paper presented a novel coronavirus herd immunity optimizer algorithm for the optimal accommodation of SPVDG with BESS in the PDS. The proposed algorithm is centered on the herd immunity approach to combat the COVID-19 virus. The problem formulation is focused on the optimal accommodation of SPVDG and BESS to reduce the power loss and enhance the voltage profile of the PDS. Moreover, voltage limits, maximum current limits, and BESS charge-discharge constraints are validated during the optimization. Moreover, the hourly variation of SPVDG generation and load profile with seasonal impact is examined in this study. IEEE 33 and 69 bus PDSs are tested for the development of the presented work. The suggested algorithm showed its effectiveness and accuracy compared to different optimization techniques. © 2023 TÜBÍTAK.
ABSTRACT
The success of the supervised learning process for feedforward neural networks, especially multilayer perceptron neural network (MLP), depends on the suitable configuration of its controlling parameters (i.e., weights and biases). Normally, the gradient descent method is used to find the optimal values of weights and biases. The gradient descent method suffers from the local optimal trap and slow convergence. Therefore, stochastic approximation methods such as metaheuristics are invited. Coronavirus herd immunity optimizer (CHIO) is a recent metaheuristic human-based algorithm stemmed from the herd immunity mechanism as a way to treat the spread of the coronavirus pandemic. In this paper, an external archive strategy is proposed and applied to direct the population closer to more promising search regions. The external archive is implemented during the algorithm evolution, and it saves the best solutions to be used later. This enhanced version of CHIO is called ACHIO. The algorithm is utilized in the training process of MLP to find its optimal controlling parameters thus empowering their classification accuracy. The proposed approach is evaluated using 15 classification datasets with classes ranging between 2 to 10. The performance of ACHIO is compared against six well-known swarm intelligence algorithms and the original CHIO in terms of classification accuracy. Interestingly, ACHIO is able to produce accurate results that excel other comparative methods in ten out of the fifteen classification datasets and very competitive results for others.
ABSTRACT
The Reactive Power Reserve (RPR) is a very important indicator for voltage stability and is sensitive to the operating conditions of power systems. Thorough understanding of RPR, specifically Effective Reactive Reserve (ERR) under intermittent Wind Power (WP) and uncertain demand is essential and key focus of this research. Hence, a stochastic multivariate ERR assessment and optimization problem is introduced here. The proposed problem is solved in three stages: modeling of multivariate uncertainty, studying the stochastic behavior of ERR and optimizing ERR. The volatilities associated with WP generation and consumer demand are modeled explicitly, and their probability distribution function is discretized to accommodate structural uncertainty. A combined load modeling approach is introduced and extended further to accommodate multi-variability. The impact of these uncertainties on ERR is assessed thoroughly on modified IEEE 30 and modified Indian 62 bus system. A non-linear dynamic stochastic optimization problem is formulated to maximize the expected value of ERR and is solved using ‘Coronavirus Herd Immunity Optimizer (CHIO)'. The impact of the proposed strategy on stability indices like the L-index, Proximity Indicator (PI) are analyzed through various case studies. Further, the effectiveness of the proposed approach is also compared with the existing mean value approach. Additionally, the performance of CHIO is confirmed through exhaustive case studies and comparisons. © 2023 Elsevier B.V.
ABSTRACT
The permutation flow shop scheduling problem (PFSSP) is well-applied in the industry, which is confirmed to be an NP-Hard optimization problem, and the objective is to find the minimum completion time (makespan). A modified coronavirus herd immunity optimizer (CHIO) with a modified solution update is suggested in this work. Meanwhile, the simulated annealing strategy is used on the updating herd immunity population to prevent trapping on local optima, and an adjusted state mechanism is involved to prevent fast state change/ convergence. Nine instances of different problem scales on the FPSSP dataset of Taillard were tested. The experimental results show that the proposed method can find the optimal solutions for the tested instances, with ARPDs no more than 0.1, indicating that the proposed method can effectively and stably solve the PFSSP. © 2022 IEEE.
ABSTRACT
Classification is a technique in data mining that is used to predict the value of a categorical variable and to produce input data and datasets of varying values. The classification algorithm makes use of the training datasets to build a model which can be used for allocating unclassified records to a defined class. In this paper, the coronavirus herd immunity optimizer (CHIO) algorithm is used to boost the efficiency of the probabilistic neural network (PNN) when solving classification problems. First, the PNN produces a random initial solution and submits it to the CHIO, which then attempts to refine the PNN weights. This is accomplished by the management of random phases and the effective identification of a search space that can probably decide the optimal value. The proposed CHIO-PNN approach was applied to 11 benchmark datasets to assess its classification accuracy, and its results were compared with those of the PNN and three methods in the literature, the firefly algorithm, African buffalo algorithm, and ß-hill climbing. The results showed that the CHIO-PNN achieved an overall classification rate of 90.3% on all datasets, at a faster convergence speed as compared outperforming all the methods in the literature. Supplementary Information: The online version contains supplementary material available at 10.1007/s00500-022-06917-z.
ABSTRACT
Wireless sensor networks (WSNs) are composed of a large number of spatially distributed sensor nodes to monitor and transmit information from the environment. However, the batteries used by these sensor nodes have limited energy and cannot be charged or replaced due to the harsh deployment environment. This energy limitation will seriously affect the lifetime of the network. Therefore, the purpose of this research is to reduce energy consumption and balance the load of sensor nodes by clustering routing protocols, so as to prolong the lifetime of the network. First, the coronavirus herd immune optimizer is improved and used to optimize the network clustering. Second, the cluster heads (CHs) are selected according to the energy and location factors in the clusters, and a reasonable CH replacement mechanism is designed to avoid the extra communication energy consumption caused by the frequent replacement of CHs. Finally, a multihop routing mechanism between the CHs and the base station is constructed by Q-learning. Simulation results show that the proposed work can improve the structure of clusters, enhance the load balance of nodes, reduce network energy consumption, and prolong the network lifetime. The appearance time of the first energy-depleted node is delayed by 25.8%, 85.9%, and 162.2% compared with IGWO, ACA-LEACH, and DEAL in the monitoring area of $300×300 m, respectively. In addition, the proposed protocol shows better adaptability in varying dynamic conditions. © 2001-2012 IEEE.
ABSTRACT
Wireless sensor networks (WSNs) are composed of a large number of spatially distributed sensor nodes to monitor and transmit information from the environment. However, the batteries used by these sensor nodes have limited energy and can not be charged or replaced due to the harsh deployment environment. This energy limitation will seriously affect the lifetime of the network. Therefore, the purpose of this research is to reduce energy consumption and balance the load of sensor nodes by clustering routing protocols, so as to prolong the lifetime of the network. Firstly, the coronavirus herd immune optimizer is improved and used to optimize the network clustering. Secondly, the cluster heads are selected according to the energy and location factors in the clusters, and a reasonable cluster head replacement mechanism is designed to avoid the extra communication energy consumption caused by the frequent replacement of cluster heads. Finally, a multi-hop routing mechanism between the cluster heads and the base station is constructed by Q-learning. Simulation results show that the proposed work can improve the structure of clusters, enhance the load balance of nodes, reduce network energy consumption and prolong the network lifetime. The appearance time of the first energy-depleted node is delayed by 25.8%, 85.9% and 162.2% compared with IGWO, ACA-LEACH and DEAL in the monitoring area of 300m ×300m, respectively. In addition, the proposed protocol shows better adaptability in varying dynamic conditions. IEEE
ABSTRACT
This paper proposes an improved version of the Coronavirus Herd Immunity Optimizer (CHIO) algorithm, called RFDB-CHIO, for solving the Unmanned Aerial vehicle carried Base Stations (UAV-BSs) placement problem in 5G networks. The proposed RFDB-CHIO is based on the integration of the Roulette Fitness Distance Balance (RFDB) selection mechanism into the original CHIO algorithm. RFDB-CHIO is validated in terms of user coverage and mean coverage radius under 16 scenarios with different numbers of drones and users. The simulation results demonstrated that RFDB-CHIO obtained better results than CHIO, Whale optimization algorithm (WOA), and Grey Wolf Optimization (GWO) algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
In this study, the problem of finding an optimal location and size of a distributed generator (DG) in distribution systems with considering operational distribution system constraints is proposed with the objective of maximizing DG hosting capacity (MDHC), reducing system loss, and improving voltage stability index (VSI). The proposed objective function is formulated as a multi-objective mixed-integer nonlinear optimization in order to solve it simultaneously. To solve this problem, the coronavirus herd immunity optimizer (CHIO), a bio-inspired metaheuristic optimization method, is herein proposed to simultaneously tackle a discrete and continuous DG integration problem in distribution systems. Extensive simulations on an IEEE 69-node system with different load levels and DG numbers are performed using MATLAB software to evaluate the efficacy of the proposed method. The simulation results demonstrate that the proposed method efficiently improves overall distribution system performance when compared to different DG numbers and load levels. Furthermore, the CHIO optimization method shows encouraging results and almost obtains the best results in all proposed cases when compared with well-known metaheuristic optimization methods such as genetic algorithm (GA), the hunger games search (HGS), the chaotic neural network algorithm (CNNA), and the water cycle algorithm (WCA). The CHIO can successfully offer a notable solution for the DG integration problem, and the obtained results, for example in case 1, revealed outperforming the CHIO compared to other methods in terms of the MDHC (i.e., 99.999 %), voltage profile improvement (i.e., the minimum voltage magnitude of 0.9696 p.u), VSI improvement (i.e., 29.16 %), and system loss reduction (i.e., 66.95 %) compared with the base case, respectively © 2022, International Journal of Intelligent Engineering and Systems.All Rights Reserved.
ABSTRACT
In an era of depleting fossil fuels and a contaminated environment, legislators, governments, industries, academics, and other energy organizations have focused their attention on renewable energy distributed generation (REDG). REDGs' appropriate size and location should be determined optimally. Since, the operating characteristics of the distribution system (DS) such as losses, voltage profile depends upon placement and sizing of DG in DS. Optimal accommodation includes placement and sizing of PV-DG is implemented using a novel Coronavirus herd immunity optimizer in the present work. This model is aiming to minimize total power loss and improve the voltage profile of the whole DS. Further, the constraints used for this study are voltage limits and current limits. Also, the seasonal load and PV generation variation for a typical year is included during the optimization. The results and performance of the proposed technique have been compared with well-known methods in the literature. The results obtained show the efficacy of the suggested method. © 2022 IEEE.
ABSTRACT
In this computer world, huge data are generated in several fields. Statistics in the healthcare engineering provides data about many diseases and corresponding patient's information. These data help to evaluate a huge amount of data for identifying the unknown patterns in the diseases and are also utilized for predicting the disease. Hence, this work is to plan and implement a new computer-aided technique named modified Ensemble Learning with Weighted RBM Features (EL-WRBM). Data collection is an initial process, in which the data of various diseases are gathered from UCI repository and Kaggle. Then, the gathered data are pre-processed by missing data filling technique. Then, the pre-processed data are performed by deep belief network (DBN), in which the weighted features are extracted from the RBM regions. Then, the prediction is made by ensemble learning with classifiers, namely, support vector machine (SVM), recurrent neural network (RNN), and deep neural network (DNN), in which hyper-parameters are optimized by the adaptive spreading rate-based coronavirus herd immunity optimizer (ASR-CHIO). At the end, the simulation analysis reveals that the suggested model has implications to support doctor diagnoses.
ABSTRACT
The Reactive Power Reserve (RPR) is an important indicator to plan stable and secure power system operations. The evaluation of RPR is very important to analyze the performance of wind integrated power systems. The RPR should be kept as high as possible for a stable and secure operation of a power system. However, it is difficult to maintain adequate RPR in wind integrated power systems owing to the uncertainty associated with it. A scenario-based nonlinear, complex RPR maximization problem is proposed in this work to ensure the voltage stability of the wind integrated power systems. A newly developed 'Coronavirus Herd Immunity Optimizer (CHIO)' is utilized to solve the proposed problem. Programs are developed in MATLAB and tested on IEEE 30 bus system. The voltage controllers present in the power system are adjusted continuously during the optimization for optimality. Further, the free parameters of CHIO are also tuned through sensitivity analysis. The proficiency of CHIO is verified through various case studies and comparisons with other methods. Copyright (C) 2022 The Authors.
ABSTRACT
Wireless sensor networks (WSNs) are characterized by their ability to monitor physical or chemical phenomena in a static or dynamic location by collecting data, and transmit it in a collaborative manner to one or more processing centers wirelessly using a routing protocol. Energy dissipation is one of the most challenging issues due to the limited power supply at the sensor node. All routing protocols are large consumers of energy, as they represent the main source of energy cost through data exchange operation. Cluster-based hierarchical routing algorithms are known for their good performance in energy conservation during active data exchange in WSNs. The most common of this type of protocol is the Low-Energy Adaptive Clustering Hierarchy (LEACH), which suffers from the problem of the pseudo-random selection of cluster head resulting in large power dissipation. This critical issue can be addressed by using an optimization algorithm to improve the LEACH cluster heads selection process, thus increasing the network lifespan. This paper proposes the LEACH-CHIO, a centralized cluster-based energy-aware protocol based on the Coronavirus Herd Immunity Optimizer (CHIO) algorithm. CHIO is a newly emerging human-based optimization algorithm that is expected to achieve significant improvement in the LEACH cluster heads selection process. LEACH-CHIO is implemented and its performance is verified by simulating different wireless sensor network scenarios, which consist of a variable number of nodes ranging from 20 to 100. To evaluate the algorithm performances, three evaluation indicators have been examined, namely, power consumption, number of live nodes, and number of incoming packets. The simulation results demonstrated the superiority of the proposed protocol over basic LEACH protocol for the three indicators. © 2022 Tech Science Press. All rights reserved.
ABSTRACT
The importance of medical data and the crucial nature of the decisions that are based on such data, as well as the large increase in its volume, has encouraged researchers to develop feature selection (FS)-based approaches to identify the most relevant data for specific medical problems In this paper, two intelligent wrapper FS approaches based on a new metaheuristic algorithm named the coronavirus herd immunity optimizer (CHIO) were applied with and without the incorporation of a greedy crossover (GC) operator strategy to enhance exploration of the search space by CHIO. The two proposed approaches, CHIO and CHIO-GC, were evaluated using 23 medical benchmark datasets and a real-world COVID-19 dataset. The experimental results indicated that CHIO-GC outperformed CHIO in terms of search capability, as reflected in classification accuracy, selection size, F-measure, standard deviation and convergence speed. The GC operator was able to enhance the balance between exploration and exploitation of the CHIO in the search and correct suboptimal solutions for faster convergence. The proposed CHIO-GC was also compared with two previous wrapper FS approaches, namely, binary moth flame optimization with Lévy flight (LBMFO_V3) and the hyper learning binary dragonfly algorithm (HLBDA), as well as four filter methods namely, Chi-square, Relief, correlation-based feature selection and information gain. CHIO-GC surpassed LBMFO_V3 and the four filter methods with an accuracy rate of 0.79 on 23 medical benchmark datasets. CHIO-GC also surpassed HLBDA with an accuracy rate of 0.93 when applied to the COVID-19 dataset. These encouraging results were obtained by striking a sufficient balance between the two search phases of CHIO-GC during the hunt for correct solutions, which also increased the convergence rate. This was accomplished by integrating a greedy crossover technique into the CHIO algorithm to remedy the inferior solutions found during premature convergence and while locked into a local optimum search space.