Immune Co-evolutionary Algorithm Research Articles

Optimizing Multi-agent MicroGrid Resource Scheduling by Co-Evolutionary with Preference

This paper presents a multi-agent framework for the control of distributed energy resources organized in Microgrids，which consists of integrated microgrids and lumped loads. Multiple objectives are considered for load balancing among the feeders, minimization of the operating cost, minimizing the emission, minimizing voltage profiles, minimizing active power losses. The agent represents message of microGrid unit and constitutes an autonomic unit. The network is achieved by the evolution of the agent based on the semantic negotiation. Based on the objectives evaluated by membership functions respectively, We propose a new Immune Co-Evolutionary Algorithm with Preference to solve it. Simulation results demonstrated that the proposed method is effective in improving performance and management of micro-sources. DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.3655 Full Text: PDF

Target coverage optimisation of wireless sensor networks using a multi-objective immune co-evolutionary algorithm

Target coverage is an important topic of wireless sensor networks. The target cover can be modelled as a minimal multi-objective vertex cover model with constraint of network connection. In order to search the optimal solution of the target cover set, we propose a multi-objective immune co-evolutionary algorithm (MOICEA) for target coverage. The MOICEA is inspired from the biological mechanisms of immune systems including clonal proliferation, hypermutation, co-evolution, immune elimination and memory mechanism. The affinity between antibody and antigen is used to measure the optimal target cover, and the affinity between antibodies is used to evaluate the diversity of population and to instruct the population evolution process. In order to examine the effectiveness of the MOICEA, we compare its performance with that of integer linear program and genetic algorithm in terms of four objectives while maintaining network connectivity. The experiment results show that the MOICEA can obtain promising performance in efficiently searching optimal vertex set by comparing with other approaches.

Multi-criteria decision making approach based on immune co-evolutionary algorithm with application to garment matching problem

In this paper, we propose a co-evolutionary immune algorithm for the multi-criteria decision making (MCDM) model, and use the model to solve the large scale garment matching problem. Size fitting problem is a main obstacle to large scale garment sales and online sales because it is difficult to find the fit garments by the general size information. This study regards the fit garment matching problem as a MCDM model with the constraints of size satisfaction. An immune co-evolutionary algorithm is used to search the fit garments from the candidate garments in the stock. The garments in the stock are taken as antibodies and the customer request as antigen. The concepts of ideal garment and loose garment are virtual garment to model the customer request. Two affinity measures including dominance affinity and distance affinity are defined to represent the similarity of antibody to antibody and that of antibody to antigen. Correspondingly, the fit garments are chosen by two methods: the Pareto optimal garments by the MCDM solving algorithm, and the optimal garments with the minimal distance affinity to the ideal garments. An evaluation model on garments is proposed to evaluate the fit garments by the affinity measures. Based on the experiment data from the effective study of detail factors of female trousers, the proposed model and algorithm demonstrate to be a feasible and effective attempt aiming at a valuable problem and provide the key tool for garment store sale system or online garment order system to support accurate garment size matching.

A Decision Support System for Tobacco Distribution Partition Optimization Based on Immune Co-Evolutionary Algorithm

The tobacco distribution in China is organized by the tobacco company in the unit of city. The distribution cycle is commonly a week with five fixed distribution districts started from the center depot, and the routes in each district are fixed for the vehicles and drivers. This method with low efficiency and high cost has continued for several decades because of the poor technology and economic reasons. In this paper, we propose a feasible and optimal method for the tobacco distribution partition balance problem (TDPBP) by breaking the fixed partitions. An immune co-evolutionary algorithm (ICEA) is proposed to search the optimal partitions. Moreover, the decision support system (DSS) for partition balance is designed. Linfen city in China as a real-world case is proved that the DSS can discover the efficient distribution planning. The comparisons among three solutions, ‘Fixed’, ‘the DSS’ and ‘Pure VRP’, further prove that the DSS is an effective decision support tool for TDPBP.

A Hybrid Neural Network and Immune Algorithm Approach for Fit Garment Design

The purpose of this study was to develop a system to utilize the successful experiences and help the beginners of garment pattern design (GPD) through optimization methods. Size design of fit garments is a basic and difficult problem in GPD for inexperienced designers. We have proposed a hybrid system (NN-ICEA) based on neural network (NN) and immune co-evolutionary algorithm (ICEA) to predict the fit of the garments and search optimal sizes. ICEA takes NN as fitness function and procedures including clonal proliferation, hypermutation and co-evolution search the optimal size values. A series of experiments with a dataset of 450 pieces of pants was conducted to demonstrate the prediction and optimization capabilities of NN-ICEA. In the comparative studies, NN-ICEA was compared with NN-genetic algorithm to show the value of immune-inspired operators. Four types of GPD method have been summarized and compared. Moreover, the hybrid system for general features of garment has been discussed. The research is a feasible and effective attempt aiming at a valuable problem and provides key algorithms for fit prediction and size optimization. The algorithms can be incorporated into garment computer-aided design system.

A Hybrid System Based on Neural Network and Immune Co-Evolutionary Algorithm for Garment Pattern Design Optimization

The purpose of this study is to develop a system to utilize the successful experiences and help the beginners of garment pattern design (GPD) by optimization methods. A hybrid algorithm (NN-ICEA) based on Neural Network (NN) and immune co-evolutionary algorithm (ICEA) to predict the fit of the garments and search optimal sizes. ICEA takes NN as fitness function and procedures including clonal proliferation, hyper-mutation and co-evolution search the optimal size values. Then, a series of experiments with a dataset of 450 pieces of garments are conducted to demonstrate the prediction and optimization capabilities of NN-ICEA. In the comparative studies, NN-ICEA is compared with NN-GA to show the value of immune inspired operators. Four types of GPD methods are summarized and compared. Moreover, the hybrid system for general features of garment is discussed. The fit prediction based on NN can achieve the high accuracy with the error rate less than 0.2. The size optimization based on ICEA works well when number of the missing sizes is less than 1/3 of the total size number. The research is a feasible and effective attempt aiming at a valuable problem and provides key algorithms for fit prediction and size optimization. The algorithms can be incorporated into garment CAD system.

Immune co-evolutionary algorithm based partition balancing optimization for tobacco distribution system

In China, the tobacco distribution is organized by fixed districts and routes with low efficiency and high distribution cost due to its unbalanced workload. And, though the dynamic method adopting vehicle routing algorithms produces optimal routes, the unstable routes increase the delivery time and managerial cost. So it is urgent and feasible to break the fixed districts to provide periodic balanced partitions for tobacco distribution. In this paper, a multi-criteria balanced partition model is built, whose minimal objectives including total number of tours in all districts, the travel distance and time of all tours, and the balance objectives include number of tours, total demand, traveling distance and time of each district are considered. An immune co-evolutionary algorithm with two stages is designed to search the optimal balanced partitions. In the first stage, the initial balanced partitions are produced. In the second stage, the clonal selection procedure, with partition proliferation, selection and elimination, and cooperative searching among districts, is adopted to achieve balanced partition. The experiments on Lenfen city in China as a practical application reveal the efficiency of the proposed model and algorithm. First, the searching processes are analyzed by exploring the partitions and Pareto partitions. Second, the evolutionary process of the algorithm is shown by the varying of the multiple objectives. Finally, three methods including fixed districts and routes, dynamic VRP scheduling and periodic balanced partition are compared to show the value of the study.

A study of a parallelized immune coevolutionary algorithm for division-of-labor problems

Recently, a number of parallelized optimization algorithms have been proposed. We have proposed a co-evolutionary immune algorithm (IA) to solve the division-of-labor problems, in particular the n-th agent’s travelling salesman problem (n-TSP). In this article, we extend the co-evolutionary IA for a large-scale n-TSP with (1) an improvement for the search speed through parallelized search on the PC-cluster, and (2) the introduction of a new division-processing “pre-estimated division processing” to improve the search ability. Some computational experiments show the proposed method can obtain better quality solutions for division-of-labor problems, and present an applicable parameter cofinguration.