Multi-objective Swarm Optimization Research Articles

Developing and optimizing a new cogeneration cycle to produce hydrogen from seawater

Global warming and the depletion of fossil fuels have driven countries to develop alternative fuel strategies. As an alternative fuel, hydrogen is very attractive since it has a high thermal energy and near-zero emissions. This paper proposes a new arrangement of the cogeneration cycle for hydrogen production from seawater is proposed and optimized via the multi-objective swarm optimization (MOPSO) algorithm. In this survey, hydrogen is produced through the electrochemical cycle Copper-Chloride (Cu-Cl), using the heat and electricity provided via waste heat recovery of a gas cycle. A reverse osmosis system provides drinking water for the Cu-Cl cycle. This cycle can produce 256 GWh of electricity and 23616 tons/year of hydrogen during a year. This cycle's first and second law efficiencies are 35.3 % and 7.2 %. Based on the financial aspects, this cycle's investment return time equals 4.1 years. By using MOPSO algorithm, the exergy efficiency of the cogeneration system is improved by 22.7 %, while the payback is decreased by around 33.3 %.

Fuzzy particle swarm for the right-first-time of fused deposition

Right-first-time production enables manufacturing companies to be profitable as well as competitive. Ascertaining such a concept is not as straightforward as it may seem in many industries, including 3D printing. Therefore, in this research paper, a right-first-time framework based on the integration of fuzzy logic and multi-objective swarm optimization is proposed to reverse-engineer the radial based integrated network. Such a framework was elicited to represent the fused deposition modelling (FDM) process. Such a framework aims to identify the optimal FDM parameters that should be used to produce a 3D printed specimen with the desired mechanical characteristics right from the first time. The proposed right-first-time framework can determine the optimal set of the FDM parameters that should be used to 3D print parts with the required characteristics. It has been proven that the right-first-time model developed in this paper has the ability to identify the optimal set of parameters successfully with an average error percentage of 4.7%. Such a framework is validated in a real medical case by producing three different medical implants with the desired mechanical characteristics for a 21-year-old patient.

Multi Objective Salp Swarm based Energy Efficient Routing Protocol for Heterogeneous Wireless Networks

Routing is a persistent concern in wireless sensor networks (WSNs), as getting data from sources to destinations can be a tricky task. Challenges include safeguarding the data being transferred, ensuring network longevity, and preserving energy in harsh environmental conditions. Consequently, this study delves into the suitability of using multi-objective swarm optimization to route heterogeneous WSNs in the hope of mitigating these issues while boosting the speed and accuracy of data transmission. In order to achieve better performance in terms of load balancing and reducing energy expenditure, the MOSSA-BA algorithm was developed. This algorithm combines the Multi-Objective Salp Swarm Algorithm (MOSSA) with the exploiting strategy of the artificial bee colony (BA) in the neighbourhood of Salps. Inspired by the SEP and EDEEC protocols, the integrated solutions of MOSSA-BA were used to route two and three levels of heterogeneous networks. The embedded solutions provided outstanding performance in regards to FND, HND, LND, percentage of remaining energy, and the number of packages delivered to the base station. Compared to SEP, EDEEC, and other competitors based on MOSSA and a modified multi-objective particle swarm optimization (MOPSO), the MOSSA-BA-based protocols demonstrated energy-saving percentages of more than 34% in medium-sized areas of interest and over 22% in large-sized areas of detection.

Secure Internet of Things based hybrid optimization techniques for optimal centroid routing protocol in wireless sensor network

SummaryThe recent survey depicts internet growth has been reached to billion of people and Internet of Things (IoT) as another milestone. IoT is wired or wireless communication technologies to establish a communication channel between devices and services available over the Internet. The wireless sensor networks (WSNs) is one of the most essential technologies assisted in IoT for real‐time applications. The energy efficiency is a major issue in IoT and it becomes more complex due to large scalability and the WSNs cannot be applied directly to the IoT. Moreover, routing is a very challenging aspect that takes place in such platform because of it is intrinsic properties. In this article, we propose an optimal centroid‐based routing protocol (OCRP) for WSN assisted IoT based on hybrid optimization techniques, which aim is to enhance the energy efficiency and network lifetime. IoT network is composed by serving nodes and end users. In OCRP, a multi‐objective swarm optimization (MSO) algorithm is used to perform the clustering, which reduce the chaotic in nature of energy consumption. Then, multiservice queue based ant optimization algorithm is proposed for next neighborhood selection for inter‐cluster routing. Finally, our OCRP protocol is experimented with different simulation in network simulator (NS‐2) tool with wireless body sensor network (WBSN) application. The simulation results show the effectiveness of OCRP protocol in terms of energy consumption, average data transmission rate and network lifetime.

Multivariate selection-combination short-term wind speed forecasting system based on convolution-recurrent network and multi-objective chameleon swarm algorithm

Wind energy, as a typical environmentally friendly source of energy for power generation, has the advantages of being renewable and emitting no greenhouse gases. Moreover, in wind power generation, accurate wind speed prediction is vital. However, most existing forecasting models use only univariate time series forecasting models, ignoring the effect of other variables on wind speed and the improvement of the model using optimization algorithms, resulting in lower accuracy and stability. Aiming to fill this gap, we develop a complete multivariate selection-combination short-term wind speed forecasting system, which is composed of two advanced feature-selection methods; six single forecasting models based on convolutional and recurrent neural networks and a multi-objective chameleon swarm optimization algorithm. We prove theoretically that the proposed multi-objective chameleon swarm optimization algorithm has Pareto optimal solutions and performs best in some test functions by comparing it with other multi-objective swarm optimization algorithms. For wind speed prediction in summer, our proposed prediction system achieves a mean absolute percentage error of 1.937%, 2.110% and 2.584% in one-, two- and three-step forecasting, respectively, which is higher than single and other combined models.

Differentiated fares depend on bus line and time for urban public transport network based on travelers’ day-to-day group behavior

Considering travelers’ day-to-day group behavior based on social interaction, this paper proposes a differentiated fare strategy depending on bus line and time. Based on the analysis of travelers’ generalized cost, a day-to-day group travel behavior evolution model with social interaction is established, and the corresponding OD matrix evolutionary model based on the complexity of the group behavior is designed. Set the differentiated fares of bus lines, private car parking fees and bus departure frequency as the optimization variables, the multi-objective optimization model is established to maximize the profit of the public transportation system and travelers’ utility On this basis, the improved particle swarm multi-objective optimization algorithm is introduced to solve the model. Finally, the proposed model and algorithm are applied to a bus network under real case. The numerical results show that: (1) The implementation of differentiated fares depends on bus line and time based on travelers’ day-to-day group behavior can improve the Pareto frontier, in which the travelers obtain higher utility and the public transportation system achieves higher profit than the model based on perfect rationality; (2) Compared with the traditional traffic flow model, the day-to-day evolution model of group behavior under differentiated fares can reduce the congestion of the network; (3) Properly reducing the information interaction range of travelers can effectively reduce the travel time under the differentiated fares.

A Hybrid Deep Learning Approach for Sentiment Analysis using CNN and Improved SVM with Multi Objective Swarm Optimization for Domain Independent Datasets

A Hybrid Deep Learning Approach for Sentiment Analysis using CNN and Improved SVM with Multi Objective Swarm Optimization for Domain Independent Datasets

STATISTICAL MARKOV MODEL BASED NATURAL INSPIRED GLOWWORM SWARM MULTI-OBJECTIVE OPTIMIZATION FOR ENERGY EFFICIENT DATA DELIVERY IN MANET

An interference and collision is a significant problem to be solved in Mobile Ad Hoc Network (MANET). Few techniques were developed in existing work to perform energy aware routing in MANET. But, handling both interference and collision on route path was remained open issues which increases the energy usage and reduces the throughput of MANET.  In order to overcome such limitations, Statistical Markov Model Based Natural Inspired Glowworm Multi-objective Optimization (SMM-NIGMO) technique is proposed.  The SMM-NIGMO technique contains three key processes namely interference prediction, optimal node selection, route path identification. The SMM-NIGMO technique at first proposes a Statistical Markov Model to determine the interference level of each mobile node in MANET at the time ‘ ’. After  that, SMM-NIGMO Technique designs a Natural Inspired Glowworm Swarm Multi-Objective Optimization (NIGSMO) algorithm to carry out the optimal node selection process in MANET. During this process, SMM-NIGMO Technique finds the mobile nodes with lower inferences and higher residual energy as optimal in dynamic environment. After discovering the best nodes, SMM-NIGMO Technique uses the Request-To-Send (RTS) and Clear-To-Send (CTS) mechanism for identifying the best route path in MANET. During the route path finding process, SMM-NIGMO Technique selects the mobile node to transmit the packets to destination without any collisions.   As a result, SMM-NIGMO Technique enhances the performance of energy efficient data delivery in MANET as compared to existing works. The simulation of SMM-NIGMO Technique is performed using parameters such as throughput, energy consumption, packet loss rate and end to end delay. The simulation result depicts that the SMM-NIGMO Technique is able to improve the throughput and also reduces the energy consumption of data transmission in MANET as compared to state-of-the-art works.

Oppositional Multi Objective Particle Swarm Based Re source Optimized Job Scheduler f or Load Balanced Cloud Service Provisioning

Job scheduling is a key problem to be resolved in cloud service provisioning for balancing load and improving resource optimization performance. Recently, many research works have been designed for performing job scheduling using different techniques. However, job scheduling efficiency (SE) was not sufficient. In order to addresses the above limitations, Oppositional Multi-Objective Particle Swarm Based Resource Optimized Job Scheduling (OMPS-ROJS) technique is proposed. The designed OMPS-ROJS technique balances the load on computer resources by distributing tasks to available resources with higher efficiency. The OMPS-ROJS technique at first takes number of incoming user requested jobs to cloud server (CS) as input. Then, OMPS-ROJS technique develops Oppositional Particle Swarm Multi-Objective Optimization (OPSMO) algorithm in order to determine the optimal virtual machines for each input user requested jobs with a minimal amount of time. On the contrary to conventional works, OPSMO algorithm assume multi-objective such as energy, makespan, bandwidth, memory and cost for fitness function evaluation. This helps for OMPS-ROJS technique to find out the virtual machine which contains maximum resource availability as best to carry out the user requested jobs. Therefore, OMPS-ROJS technique efficientlybalancedynamic loads on CS through scheduling user requested jobs with a minimal time.Thus, OMPS-ROJS technique enhances the cloud service provisioning performance as compared to conventional works. Experimental result evident that OMPS-ROJS technique enhances the SE and lessen the EC as compared to conventional works.

Multi-Objective Optimized Overlapping Peak Separation Algorithm for Simultaneous Detection of Copper and Cobalt by Ultraviolet-Visible Spectroscopy

In the zinc hydrometallurgy, the excessive impurity ions of copper and cobalt are very harmful to the electrolysis process, which affects product quality and wastes resources. In order to solve the problems of low sensitivity, severe spectral overlap and narrow effective band, an overlapping peak separation algorithm based on multi-objective optimization was proposed for simultaneous detection of copper and cobalt in high concentration zinc solution by ultraviolet-visible spectroscopy. First, according to the characteristics of the spectral signal, the derivative spectroscopy by continuous wavelet transform was used to separate the spectral overlapping peaks of copper and cobalt and shield the zinc interference. Then, taking decomposition scale as decision variable, and the information occupancy and peak separation as the optimization targets, a multi-objective optimization model was established and solved using the particle swarm multi-objective optimization method. Finally, derivative spectroscopy combined with zero-crossing method was used to establish calibration curves for simultaneous detection of copper and cobalt. The experimental results show that the proposed method is suitable for simultaneous detection of trace amounts of copper and cobalt in high concentration zinc solution.

Optimization of parabolic through collector (PTC) with multi objective swarm optimization (MOPSO) and energy, exergy and economic analyses

The availability of reliable electricity and heat sources for community guarantees a better living environment in terms of education, healthcare and economy. Two main parameters should be considered in heat production which are the cost of this production and the performance of the devices used to produce this heat. In this work, a thermodynamic analysis based on energy and exergy analyses as well as economic analysis are presented to analyze the performance of parabolic trough solar collector (PTC). A multiobjective swarm optimization (MOPSO) technique is used to find out the maximum exergy efficiency and the minimum heat production cost of PTC. The optimum results show that the exergy efficiency, energy efficiency and heat cost are 29.22%, 35.55% and 0.0142 $/kWh. The effect of PTC geometrical parameters such as length, focal length, width and internal absorber diameter on the performance of PTC and heat production cost are investigated. Energy efficiencies of the system at different times during the day are calculated and they are in good agreement with the experimental results available in literature. The proposed system of PTC is located in Tehran, Iran.

Location of temporary depot after an earthquake based on robust optimization

In today's world, natural disasters such as earthquakes, floods, crises such as terrorist attacks and protests threaten the lives of many people. Hence, in this research we present a mathematical modeling that provide efficient and effective model to locate temporary depot, equitable distribution of resources and movement of injured people to health centers, with the aim of developing the multi-objective model and considering multiple central depot, multiple temporary depot and several type of relief items in the model . This paper is considered certainty state and uncertainty of influencing parameters of the models in robust optimization for three different levels uncertainty and in different size with consideration of traditional goals function and humanitarian purposes functions simultaneously. The model has been solved with multi-objective Particle Swarm optimization algorithm (MOPSO) and GAMS software to validate the model. Some numerical examples are presented. In Addition, we present sensitivity analyzes of model and study the relationship of the number of temporary depot location and the number of injured people to move to health centers and the number of uncovered damaged points.

Multi-Objective Particle Swarm Optimization Based on Grid Ranking

Multi-Objective Particle Swarm Optimization Based on Grid Ranking

A Semiactive and Adaptive Hybrid Control System for a Tracked Vehicle Hydropneumatic Suspension Based on Disturbance Identification

The riding conditions for a high-speed tracked vehicle are quite complex. To enhance the adaptability of suspension systems to different riding conditions, a semiactive and self-adaptive hybrid control strategy based on disturbance velocity and frequency identification was proposed. A mathematical model of the semiactive, self-adaptive hybrid suspension control system, along with a performance evaluation function, was established. Based on a two-degree-of-freedom (DOF) suspension system, the kinematic relations and frequency zero-crossing detection method were defined, and expressions for the disturbance velocity and disturbance frequency of the road were obtained. Optimal scheduling of the semiactive hybrid damping control gain (csky, cground, chybrid) and self-adaptive control gain (cv) under different disturbances were realized by exploiting the particle swarm multiobjective optimization algorithm. An experimental study using a carefully designed test rig was performed under a number of typical riding conditions of tracked vehicles, and the results showed that the proposed control strategy is capable of accurately recognizing different disturbances, shifting between control modes (semiactive/self-adaptive), and scheduling the damping control gain according to the disturbance identification outcomes; hence, the proposed strategy could achieve a good trade-off between ride comfort and ride safety and efficiently increase the overall performance of the suspension under various riding conditions.

Initiative optimization operation strategy and multi-objective energy management method for combined cooling heating and power

This paper proposed an initiative optimization operation strategy and multi-objective energy management method for combined cooling heating and power U+0028 CCHP U+0029 with storage systems. Initially, the initiative optimization operation strategy of CCHP system in the cooling season, the heating season and the transition season was formulated. The energy management of CCHP system was optimized by the multi-objective optimization model with maximum daily energy efficiency, minimum daily carbon emissions and minimum daily operation cost based on the proposed initiative optimization operation strategy. Furthermore, the pareto optimal solution set was solved by using the niche particle swarm multi-objective optimization algorithm. Ultimately, the most satisfactory energy management scheme was obtained by using the technique for order preference by similarity to ideal solution U+0028 TOPSIS U+0029 method. A case study of CCHP system used in a hospital in the north of China validated the effectiveness of this method. The results showed that the satisfactory energy management scheme of CCHP system was obtained based on this initiative optimization operation strategy and multi-objective energy management method. The CCHP system has achieved better energy efficiency, environmental protection and economic benefits.

Multi-Objective Optimal Construction Site Layout Planning with Maximize Approach of Safety and Environment(Case Study: Mahestan Residential-Commercial complex)

Abstract.  Construction Site layout optimization is one of concern in recent years In the field of construction management. Site layout planning is an important step in building a development project is considered if a suitable design and optimization will have a large impact on efficiency and save resources. In previous research various approaches According to the designers look To solve this problem there The approaches Commensurate with the nature of the projects Are different. These research efforts as a model of multi-objective optimization Sort workshop for development aims at increasing safety and environmental aspects And also provide a lower cost. To solve the problem Sort Multi-Objective Particle Swarm Optimization algorithm As a meta-heuristic algorithms Used. Also in this study, In order to achieve a real model, A construction project in the city of Tehran. Put the study. In this model, The possibility of embedding the entrance and exit Facilities and buildings is considered.

Choice of Detection Parameters on Fault Detection in Wireless Sensor Networks: A Multiobjective Optimization Approach

In this paper, the intermittent fault detection in wireless sensor networks is formulated as an optimization problem and a recently introduced multiobjective swarm optimization (2LB-MOPSO) algorithm is used to find an optimum trade-off between detection accuracy and detection latency. Faulty sensor nodes are identified based on comparisons of sensed data between one-hop neighboring nodes. Time redundancy is used to detect intermittent faults since an intermittent fault does not occur consistently. Simulation and analytical results show that sensor nodes with permanent faults are identified with high accuracy and by properly choosing the inter-test interval most of the intermittent faults are isolated with negligible performance degradation.

Artificial Glowworm Swarm Optimization Algorithm for Solving Multi-Objective Constrained Optimization

Focused on the disadvantages of some current constrained optimization algorithm, glowworm swarm multi-objective optimization algorithm ( GSMOA） is proposed in this paper. The main character of this algorithm conforms to feasibility rules and adapts self- adaptive penalty function to search feasible solutions. This algorithm has been tested on 4 standard functions and it shows that the proposed algorithm has more advantage in the convergence rate and the solution precision.

A novel hybrid charge system search and particle swarm optimization method for multi-objective optimization

In this paper a new hybrid method is proposed for multi-objective optimization problem. In multi-objective particle swarm optimization methods, selecting the global best particle for each particle ...

A Novel Diversity Guided Particle Swarm Multi-objective Optimization Algorithm

This paper presents a mu lti-objective d iversity gu ided Particle Swa rm Op timization a pproach named MOPSOAR wh ich increases di versity perfo rmance of multi-objective Parti cle S warm optimization by u sing A ttraction a nd Re pulsion (AR) m echanism. AR m echanism us es a d iversity measure to control the swar m. Being attractive and repulsive wil l help to overcome t he problem of premature c onvergence. AR mechanism together wi th cr owding di stance co mputation an d mutation operator maintains the diversity of non -dominated set in external archive. The approach is verified by several te st f unction exper iments. Results demo nstrate t hat the p roposed approach i s highly competitive in distribution of non-dominated solutions but still keeps convergence towards the Pareto front.