Search

Low carbon manufacturing has received increasingly more attention in the context of global warming. The flexible job shop scheduling problem (FJSP) widely exists in various manufacturing processes. Researchers have always emphasized manufacturing efficiency and economic benefits while ignoring environmental impacts. In this paper, considering carbon emissions, a multi-objective flexible job shop scheduling problem (MO-FJSP) mathematical model with minimum completion time, carbon emission, and machine load is established. To solve this problem, we study six variants of the non-dominated sorting genetic algorithm-III (NSGA-III). We find that some variants have better search capability in the MO-FJSP decision space. When the solution set is close to the Pareto frontier, the development ability of the NSGA-III variant in the decision space shows a difference. According to the research, we combine Pareto dominance with indicator-based thought. By utilizing three existing crossover operators, a modified NSGA-III (co-evolutionary NSGA-III (NSGA-III-COE) incorporated with the multi-group co-evolution and the natural selection is proposed. By comparing with three NSGA-III variants and five multi-objective evolutionary algorithms (MOEAs) on 27 well-known FJSP benchmark instances, it is found that the NSGA-III-COE greatly improves the speed of convergence and the ability to jump out of local optimum while maintaining the diversity of the population. From the experimental results, it can be concluded that the NSGA-III-COE has significant advantages in solving the low carbon MO-FJSP.

Proposing new strategies to improve the optimization performance of differential evolution (DE) is an important research study. The jSO algorithm was the announced winner of the Congress on Evolutionary Computation (CEC) 2017 competition on numerical optimization, and is the state-of-the-art algorithm in the SHADE (Success-History based Adaptive Differential Evolution) algorithm series. However, the jSO algorithm converges prematurely in the search space with different dimensions and is prone to falling into local optimum during evolution, as well as the problem of decreasing population diversity. In this paper, a modified jSO algorithm (MjSO) is proposed which is based on cosine similarity with parameter adaptation and a novel opposition-based learning restart mechanism incorporated with symmetry to address the above problems, respectively. Moreover, it is well known that parameter setting has a significant impact on the performance of the algorithm and the search process can be divided into two symmetrical parts. Hence, a parameter control strategy based on a symmetric search process is introduced in the MjSO. The effectiveness of these designs is supported by presenting a population clustering analysis, along with a population diversity measure to evaluate the performance of the proposed algorithm, three state-of-the-art DE variant algorithms (EBLSHADE, ELSHADE-SPACMA, and SALSHADE-cnEPSin) and two original algorithms (jSO and LSHADE) are compared with it, for solving 30 CEC&rsquo, 17 benchmark functions and three classical engineering design problems. The experimental results and analysis reveal that the proposed algorithm can outperform other competitions in terms of the convergence speed and the quality of solutions. Promisingly, the proposed method can be treated as an effective and efficient auxiliary tool for more complex optimization models and scenarios.

Particle swarm optimization (PSO) has the disadvantages of easily getting trapped in local optima and a low search accuracy. Scores of approaches have been used to improve the diversity, search accuracy, and results of PSO, but the balance between exploration and exploitation remains sub-optimal. Many scholars have divided the population into multiple sub-populations with the aim of managing it in space. In this paper, a multi-stage search strategy that is dominated by mutual repulsion among particles and supplemented by attraction was proposed to control the traits of the population. From the angle of iteration time, the algorithm was able to adequately enhance the entropy of the population under the premise of satisfying the convergence, creating a more balanced search process. The study acquired satisfactory results from the CEC2017 test function by improving the standard PSO and improved PSO.

Swarm-based algorithm can successfully avoid the local optimal constraints, thus achieving a smooth balance between exploration and exploitation. Salp swarm algorithm (SSA), as a swarm-based algorithm on account of the predation behavior of the salp, can solve complex daily life optimization problems in nature. SSA also has the problems of local stagnation and slow convergence rate. This paper introduces an improved salp swarm algorithm, which improve the SSA by using the chaotic sequence initialization strategy and symmetric adaptive population division. Moreover, a simulated annealing mechanism based on symmetric perturbation is introduced to enhance the local jumping ability of the algorithm. The improved algorithm is referred to SASSA. The CEC standard benchmark functions are used to evaluate the efficiency of the SASSA and the results demonstrate that the SASSA has better global search capability. SASSA is also applied to solve engineering optimization problems. The experimental results demonstrate that the exploratory and exploitative proclivities of the proposed algorithm and its convergence patterns are vividly improved.

With the escalation of the trade war between China and the United States and the outbreak of the new coronavirus epidemic in early 2020, China’s economy has been seriously affected. Accurate prediction of future economic development is a necessary means to formulate economic development strategies. For this reason, taking Guangdong province, the province with the strongest economic vitality, as an example, this paper uses multiple regression method to calculate the correlation degree and influence weight of population number, number of enterprises and per capita disposable income with economic development, and obtains multiple regression linear equation. In addition, this paper also uses the NAR dynamic neural network model in machine learning algorithms to predict the future trends of the three factors and economic aggregates, and analyzes the feedback results of network training errors, autocorrelation values, and partial correlation values. Compared with the multiple regression method, it is found that the final results of the two are very similar, with small errors and high correlation.

Particle swarm optimization is one of the most effective optimization algorithms motivated by bird flocking behaviours. Population topology is a key aspect of particle swarm optimization research. However, after more than twenty years of research, the effects of the population topology are still poorly understood. Previous research has established that the information propagation speed determined by the population topology has an important impact on the algorithm performance; however, the impact of information propagation speed on particle swarm optimization and its variants has not yet been investigated. In this paper, information propagation in particle swarms is described and, hence, a method of simulating information propagation in particle swarms is introduced, which is used to obtain the information propagation speed. The correlation between the information propagation speed and algorithm performance is clarified through numerical simulation. The results show that the information propagation speed has a strong negative correlation with the population diversity of particle swarm optimization and its variants in the early iterations, regardless of the adopted test function and population diversity measure. The results also show that when optimizing problems with the same property, the impact of population topology on the optimization results of particle swarm optimization and variant algorithms is similar. Further more, this study provides some guidance on the population topology selection for particle swarm optimization and its variants. These findings contribute to our understanding of the impact of population topology on particle swarm optimization and its variants, and provide a basis for population topology selection for particle swarm optimization and its variants.

The reconnection of broken edges is an effective way to avoid drawback for the commons in past studies. Inspired by this, we proposed a public goods game model under the edges rules, where we evaluate the weight of edges by their nodes&rsquo, payoff. The results proved that the game obtains a larger range of cooperation with a small gain factor by this proposed model by consulting Monte Carlo simulations (MCS) and real experiments. Furthermore, as the following the course of game and discussing the reason of cooperation, in the research, we found that the distribution entropy of the excess average degree is able to embody and predict the presence of cooperation.

Tobacco is an essential economic crop in China. The detection of tobacco plants in aerial images plays an important role in the management of tobacco plants and, in particular, in yield estimations. Traditional yield estimation is based on site inspections, which can be inefficient, time-consuming, and laborious. In this paper, we proposed an algorithm to detect tobacco plants in RGB aerial images automatically. The proposed algorithm is comprised of two stages: (1) A candidate selecting algorithm extracts possible tobacco plant regions from the input, (2) a trained CNN (Convolutional Neural Network) classifies a candidate as either a tobacco-plant region or a nontobacco-plant one. This proposed algorithm is trained and evaluated on different datasets. It demonstrates good performance on tobacco plant detection in aerial images and obtains a significant improvement on AP (Average Precision) compared to faster R-CNN (Regions with CNN features) and YOLOv3 (You Only Look Once v3).

For most of differential evolution (DE) algorithm variants, premature convergence is still challenging. The main reason is that the exploration and exploitation are highly coupled in the existing works. To address this problem, we present a novel DE variant that can symmetrically decouple exploration and exploitation during the optimization process in this paper. In the algorithm, the whole population is divided into two symmetrical subpopulations by ascending order of fitness during each iteration, moreover, we divide the algorithm into two symmetrical stages according to the number of evaluations (FEs). On one hand, we introduce a mutation strategy, DE/current/1, which rarely appears in the literature. It can keep sufficient population diversity and fully explore the solution space, but its convergence speed gradually slows as iteration continues. To give full play to its advantages and avoid its disadvantages, we propose a heterogeneous two-stage double-subpopulation (HTSDS) mechanism. Four mutation strategies (including DE/current/1 and its modified version) with distinct search behaviors are assigned to superior and inferior subpopulations in two stages, which helps simultaneously and independently managing exploration and exploitation in different components. On the other hand, an adaptive two-stage partition (ATSP) strategy is proposed, which can adjust the stage partition parameter according to the complexity of the problem. Hence, a two-stage differential evolution algorithm with mutation strategy combination (TS-MSCDE) is proposed. Numerical experiments were conducted using CEC2017, CEC2020 and four real-world optimization problems from CEC2011. The results show that when computing resources are sufficient, the algorithm is competitive, especially for complex multimodal problems.

A multi-swarm particle swarm optimization algorithm based on clustering dynamic grouping(DGMSPSO) is presented for the problem of easy to getting struck at local optima in optimization process and low precision of the particle swarm optimization algorithm. The clustering grouping strategy is introduced to enhance the location information of the particles to each other in the search process to improve the diversity of the algorithm. Local search ability and global ability of the algorithm are balanced with the dynamic adjustment strategy. The results of simulations on the test functions show that the dynamic grouping process is stable, feasible and effective, and has fast convergence and high accuracy compared with several other PSO-based algorithms in terms of global searching ability and convergent speed.

In this paper, A new particle swarm optimization algorithm based on local-world evolving network model is proposed to solve the problem that particle swarm optimization algorithm is prone to local optimum. The topology of particle swarm is generally considered to be a very important factor and determine the performance of the algorithm. In this paper, the particle swarm optimization algorithm and the local-world evolving network model are briefly reviewed, and then we use the network generated by the local-world evolving network model to represent the topological structure of the particle swarm. The new algorithm and original particle swarm optimization algorithm are tested in 6 benchmark functions. Comparing the test results, the new algorithm performs better on multimodal functions, the ability of the new algorithm to optimize on complex problems is significantly improved.

This paper studies the effects of logical random grouping and physical location grouping on the performance of multi-population particle swarm optimization (MSPSO) algorithm and realizes the dynamic grouping of multi-swarm particle optimization algorithms by introducing clustering algorithm. And the effects of K-Means algorithm, K-Medoids algorithm and DBSCAN algorithm on MSPSO are compared.

Single objective optimization algorithms are the foundation of establishing more complex methods, like constrained optimization, niching and multi-objective algorithms. Therefore, improvements to single objective optimization algorithms are important because they can impact other domains as well. This paper proposes a method using turning-based mutation that is aimed to solve the problem of premature convergence of algorithms based on SHADE (Success-History based Adaptive Differential Evolution) in high dimensional search space. The proposed method is tested on the Single Objective Bound Constrained Numerical Optimization (CEC2020) benchmark sets in 5, 10, 15, and 20 dimensions for all SHADE, L-SHADE, and jSO algorithms. The effectiveness of the method is verified by population diversity measure and population clustering analysis. In addition, the new versions (Tb-SHADE, TbL-SHADE and Tb-jSO) using the proposed turning-based mutation get apparently better optimization results than the original algorithms (SHADE, L-SHADE, and jSO) as well as the advanced DISH and the jDE100 algorithms in 10, 15, and 20 dimensional functions, but only have advantages compared with the advanced j2020 algorithm in 5 dimensional functions.

particle swarm optimization (PSO) is a kind of swarm optimization algorithm with fast search speed, high efficiency and suitable for practical optimization problems. Once it was put forward, it has attracted extensive attention of scholars in various fields. A quorum sensing particle swarm optimization (CPSOQS) algorithm based on chaos is proposed to solve the shortcomings of traditional PSO algorithms, such as poor handling of discrete optimization problems and the loss of searching ability due to the fast particle velocity decline in the later stage. Firstly, the search ability of the algorithm is improved by generating chaotic sequences and mapping them to the solution space of the definition domain; Secondly, the quorum sensing mechanism of bacteria is introduced into PSO. Chaos search was used twice in the algorithm, which improved the global search ability. CEC 2005 benchmark is used to test the performance of the algorithm. The experimental results show that among the 14 selected test functions, 11 test functions have better experimental results than the comparison algorithm.

In this paper, a new Bonus Points Alliance is designed based on the key technology of Block chain. We make use of the technical features of decentralization, trust-consensus, distributed network, collective maintenance and so on and research on Bonus Points Alliance business model based on block chain. We take advantage of the key technologies such as consensus mechanism and smart contract in block chain and take the “alliance blockchain” as a form of organization to design a full technical solution which solves the shortcomings of traditional alliance, such as a high cost of system development, difficulty of bonus points exchange, and difficulty of bonus points circulate.

Voltage stability is a traditional and important study field. Load shedding is a normal method to enhance the voltage stability when system operates at limits. Estimating how close the load is to the maximum deliverable power of transmission system is an effective method to evaluate the voltage stability. The impedance match criterion based on Thevenin equivalent is considered as a necessary and sufficient condition whether the load approaches the maximum deliverable power of transmission system or not and can be used as a reference for load shedding. This paper presents a preliminary analysis of Thevenin equivalent impedance match criterion for load shedding in some specific scenarios which may lead to system collapse. A 3-bus simple system simulation is performed to show the potential collapse. And the simulation results show that the Thevenin equivalent impedance match criterion does not hold in some specific scenarios. The Thevenin Equivalent impedance of the system match the load equivalent impedance twice before the system collapse and the criterion would not be sufficient in the specific scenarios, which may lead misoperation on load shedding. Simulations on IEEE 39 also prove that the issue exists.

State estimation is the foundation of energy management system. The innovation graph state estimation has an advantage over traditional state estimation in identifying bad data. We infer the distribution function of innovation difference and set the threshold in certain false drop rate, which provides the theoretical basis for identifying bad data in mathematics. The range of acceptable measuring error depends on the accuracy of corresponding measuring instrument. This method reduces the false detecting rate and the loss detecting rate. The function of innovation graph technique to identify bad data is improved. The method proposed in this paper is verified in a simulation with bad data based on IEEE 14-bus system and the result show that the method is effective.

Since the beginning of the 21st century, research on artificial intelligence has made great progress. Bayesian networks have gradually become one of the hotspots and important achievements in artificial intelligence research. Establishing an effective Bayesian network structure is the foundation and core of the learning and application of Bayesian networks. In Bayesian network structure learning, the traditional method of utilizing expert knowledge to construct the network structure is gradually replaced by the data learning structure method. However, as a result of the large amount of possible network structures, the search space is too large. The method of Bayesian network learning through training data usually has the problems of low precision or high complexity, which make the structure of learning differ greatly from that of reality, which has a great influence on the reasoning and practical application of Bayesian networks. In order to solve this problem, a hybrid optimization artificial bee colony algorithm is discretized and applied to structure learning. A hybrid optimization technique for the Bayesian network structure learning method is proposed. Experimental simulation results show that the proposed hybrid optimization structure learning algorithm has better structure and better convergence.

Official document classification is an integral essential part of daily archives administration. The traditional manual document classification method is time-consuming and labour-intensive, and the classification effect cannot be fully guaranteed. With the popularity of computers and the development of machine learning, the convolutional neural network model is becoming more and more mature, and the CNN model is suitable for the problems encountered in the current official document classification. This paper proposed a model based on convolutional neural network to solve the problem of official document classification. To train and test the model, we manually classify the dataset into ten categories according to the classification of college archives entities. And it was trained on a dataset with size of 6765. And on the testing dataset with size of 676, it reached an accuracy of 90%. And for comparison, we also trained a LSTM model and a GRU model (they are both popular in the natural language processing field), and results showed that the automatic official document classification method based on convolutional neural network can improve the efficiency of traditional official document classification. Also, it provides a new way of thinking for the solution of the official document classification problem.

With the dependent relationship of tasks submitted by the users in the model of Cloud computing resources scheduling become stronger and stronger, it is worthy of studying how to optimize the scheduling strategy and algorithm to meet the different demands of the users, and it is absolutely importance. In this article, the author analysed the factors that will affect the entire task-sets execution firstly. Then proposed a new tasks scheduling model based on the original priority calculation method and the idea of redundant duplication of tasks. In the phase of tasks scheduling in the model, the execution results of all parent tasks of the subtask that being executing are considered. The costs of communication between task-sets has reduced by the method of redundant duplication of tasks, so that the execution time of some subtasks share be advanced, and the entire execution efficiency of task-sets can be increased. At the end of this article, from the comparative results of the space-time complexity of contrast algorithms and the algorithm proposed by the author during the process of processing dependent tasks, we can find that subtasks execution time can be advanced and the complete time of the whole task-set can be cut down to a certain extent

It has gradually realized in the industry that the increasing complexity of cloud computing under interaction of technology, business, society and the like, instead of being simply solved depending on research on information technology, shall be explained and researched from a systematic and scientific perspective on the basis of theory and method of a complex adaptive system (CAS). This article, for basic problems in CAS theoretical framework, makes research on definition of an active adaptive agent constituting the cloud computing system, and proposes a service agent concept and basic model through commonality abstraction from two basic levels: cloud computing technology and business, thus laying a foundation for further development of cloud computing complexity research as well as for multi-agent based cloud computing environment simulation.

Software development is switched from code-centric to model-centric with model-driven development (MDD). Model is expected to bring an essential leap of software development and drive the whole software development process. It means that model is not only an analysis and design specification, but also a software product which can be automatically transformed into the executable system. That requires the executability of model. This paper presents an executable domain-specific model named xDSM and discusses the keys to making xDSM executable. The keys are accuracy and integrality of the model and its behavior modeling. They all are built based on domain-specific meta-modeling.

Model is the description and specification of software functions, structure, behaviour and its environment. One of the most important things is to strive to achieve automatically built software according to domain model, to verify the software in developing is better than that of software requirements. This paper integrates domain-specific modeling and web service techniques with model-driven development, then proposes a unified approach, SODSMI to build the executable domain-specific model to achieve the target of model-driven development. In this paper, a case study to construct an online shopping system is introduced for demonstrating the proposed approach.

After combining content release, subscription middleware features, and the traditional event-based software integration together, focus on the problems in the existing system has established an adaptable and efficient events-driven integration framework with XML as the message interaction basis by means of core models defining and filter testing designs such as architecture design and event models.

This paper adopts web service as an integrated technology to shorten virtual enterprises, including recognition, setting-up of time, to find the right partner in a large number of potential partners which used for selection, to increase the degree of autonomy of partners, reducing the coupling degree of virtual enterprise integration. This paper proposes modeling architecture of WSVE, containing the goal view, organization view, function view and resource view. Modeling process is the process of the conception of virtual enterprise from ambiguity to clear.

Process model refers to the research on key model of virtual enterprise dynamic behavior based on Web Service. This paper proposes WSVE process Meta-Model, and presents the algorithm of analysis and simulation based on process model. Through simulation analysis of the process model, we can determine the factors such as cost, time, and others of the process itself and various links, which builds the foundation on research based on service discovery and composite of process model.

This paper analyzes the connotations and characteristics of WSVE, puts forward the integration framework and process of virtual enterprise based on WEB service with target on the change of enterprise demands so as to shorten the time for the identification and organization of virtual enterprise, find out suitable partners among large number of available potential partners, strengthen the autonomy degree of partners and decrease the coupling degree of the integration of virtual enterprise.

This paper establishes WSVE process model as the object of analysis and discovers functional and non-functional QoS demands of WEB service. On the basis of these demands, the paper suggests service discovery algorithms for service and QoS. On the basis of the service discovery, it puts forward the method for transforming process model into BPEL4WS. It achieves the integration of virtual enterprise through WEB service composition and comes up with the idea for dynamic service composition which is driven by information.

Firstly, this paper presents a concept of WEB service-based virtual value net (WSVVN) in consideration of change of application environment for value net. Secondly, it gives a definition of value model for WSVVN, and makes an analysis on actions of member enterprises under this value model. In order to make a value analysis on business process of enterprise, this paper conducts expansion of basic Petri net and proposes a WSVVN Petri net model. Last, it makes an analysis on degree of order of WSVVN Petri net model by using comentropy and structure entropy.

This paper, aiming at enterprise integration between virtual enterprises, presents a concept of web service-based virtual enterprise (WSVE) and integrated framework and model for WSVE. This paper proposes a modeling structure for WSVE, including target view, organization view, function view, resource view and process view, and for process view which integrates all other views, presents a value timed Petri nets model and makes analysis on it. Using web service as integrated technology may shorten the time for identifying and building virtual enterprise, enables the enterprise to find appropriate partners among potential ones in large number, increase self-government of the partners and reduce coupling degree in integration of virtual enterprise.

The often changing needs of users will certainly leadto many modifications of code. Due to lack of CASE tool onLinux platform, it is difficult to maintain and modify Linuxapplication code. After analyzing current CASE tools, on basis of several technologies such as lexical analysis, visual development and persistent object, we design LACM (Linux Application Code Maintenance Tool): a lightweight application code maintenance tool based on Linux driven by database with functions of code recognition, document management and code modification, to adapt to the changing needs of users. We implement parts of functions of LACM in this paper by using Delphi for Linux.

As a practical method to simplify construction of distributed systems, Domain-Specific Modeling raises the level of abstraction beyond programming by specifying the solution directly using visual models to express domain concepts. This paper gives a visual metamodeling language which is suitable for specific domain modeling, namely XMML. It supports development and design of Domain-Specific Modeling languages (DSMLs) and domain model. A formal definition method of domain rules based on events is proposed for domain rules modeling. The paper also gives a loose coupling, scalable implementation schema for visual design of DSMLs. Finally, gives an example used XMML for metamodeling of a distributed application.

The usage of decision models has been given attention by decision makers for many years. How to realise public-use and reuse of model, and gain the adequate information not only limited to local departments in the wide enterprise environment is one of the most concerned issues of decision-makers. The idea of multiple-tier framework put forward by distributed system provides a helpful approach to this issue. This paper proposes a practical approach to model manipulation in a distributed decision support system based on network technology and component technology. It implements the separation among the clients, application and data level, accordingly allows the data and model source distributed storage and sharing for multi-departments. The method based on COM+ component technology makes the model distributed in the host computer all over the Internet/Intranet. Consequently, widespread models can be supplied to the client by application servers.