Search

A key step in remanufacturing is disassembly of the ``core'' or the returned product to be remanufactured. Disassembly sequence planning is challenging due to uncertainties in the conditions of the cores. Rust, corrosion, deformation, and missing parts may require disassembly plans to be changed and adapted frequently. Conventional industrial automation that usually serves in repetitive and structured activities may fail when it is applied to disassembly. This research investigates the flexible sequencing of robotic disassembly in the presence of failed automation operations and develops online recovery by incorporating backup actions. It starts with modeling the time and success rate of a backup action. The expected disassembly time and completion rate of a disassembly plan are deduced according to the failure probability of both the operations and their backup actions. A biobjective optimization model for robotic disassembly sequence planning is established using a dual-selection multiobjective evolutionary algorithm. Two solution selection criteria are combined to produce potential offspring candidates in each evolutionary generation. Experimental results show that the backup actions allow efficient recovery from automation and can potentially improve the robustness of robotic disassembly.

Cloud manufacturing (CMfg) is an emerging paradigm that aims to provide on-demand manufacturing services over the Internet. Service composition as an important means for generating value-added services plays an important role in achieving the aim of CMfg. Most of previous works focused on exploring techniques of service composition for a single composite task using meta-heuristic algorithms. However, the issue of service composition for multiple composite tasks has rarely been considered. Meta-heuristic algorithms suffer from cumbersome parameter tuning as well as the tendency of getting into local optima. In addition, the effectiveness of different algorithms has not yet been fully explored when different degrees of constraints are imposed. Different from approaches in most of the previous works, this paper proposes an extended Gale–Shapley (GS) algorithm-based approach for service composition that allows generation of multiple service composition solutions effectively. Requirements with different constraints are considered. Experimental results indicate that: 1) meta-heuristic algorithms can be used in various scenarios with different degrees of constraints. However, they are incapable of finding the optimal solutions in situations with relatively loose constraints, and moreover, the failure rate of finding solutions for a batch of multiple tasks is high; 2) the dynamic programming (DP) is a method that is the most sensitive to constraints. It performs better only under loose constraints and in the case of a single requirement; and 3) the application range of the GS method proposed is wider than that of the DP method. It can achieve better performance when constraints are relaxed irrespective of task status (i.e., a single task or multiple tasks), and moreover, it can make more tasks find solutions in the multitask scenario without service reuse.

Service composition is a core issue of cloud manufacturing (CMfg) to integrate distributed manufacturing services for customised manufacturing tasks. Existing studies focus on the quality of servic...

Uncertainties in the end-of-life conditions of products make disassembly difficult to robotise. A key problem is that existing industrial automation techniques use pre-determined robotic processes which cannot deal with unforeseen failed disassembly operations. This chapter models the completion rate of a disassembly plan and introduces the concept of backup actions. The aim of this strategy is to allow a disassembly robot to recover from failures automatically, and thus improve the system’s robustness. Experimental results indicate that the incorporation of automatic backup actions can triple the completion rate of a plan. The proposed computational method also outperforms other popular evolutionary approaches.

Agent-Based Simulation (ABS) provides distributed entities for simulating agent emergence or interactive behaviors, but the agent behaviors usually rely on the hard rules, thus lacking the intelligent decision-making capability. With the development of artificial intelligence, Multi-Agent Reinforcement Learning (MARL) has shown positive potential in robot control, autonomous driving, and human-machine battles as its powerful learning capability for making intelligent decisions. There are many challenges in applying MARL directly to ABS, and there is no unified framework that integrates them. The paper proposed the Multi-Agent Discrete Event Simulation (MADES) framework based on several DEVS atomic models to construct the multi-agent system, which has advantages for representing various MARL architectures. A predator-prey system simulation with a mainstream MARL algorithm is built under our framework, the training curves and event transition time figure have verified the learning and the simulation performance of the framework.

Parallelization of an evolutionary algorithm takes the advantage of modular population division and information exchange among multiple processors. However, existing parallel evolutionary algorithms are rather ad hoc and lack a capability of adapting to diverse problems. To accommodate a wider range of problems and to reduce algorithm design costs, this paper develops a parallel transfer evolution algorithm. It is based on the island-model of parallel evolutionary algorithm and, for improving performance, transfers both the connections and the evolutionary operators from one sub-population pair to another adaptively. Needing no extra upper selection strategy, each sub-population is able to select autonomously evolutionary operators and local search operators as subroutines according to both the sub-population’s own and the connected neighbor’s ranking boards. The parallel transfer evolution is tested on two typical combinatorial optimization problems in comparison with six existing ad-hoc evolutionary algorithms, and is also applied to a real-world case study in comparison with five typical parallel evolutionary algorithms. The tests show that the proposed scheme and the resultant PEA offer high flexibility in dealing with a wider range of combinatorial optimization problems without algorithmic modification or redesign. Both the topological transfer and the algorithmic transfer are seen applicable not only to combinatorial optimization problems, but also to non-permutated complex problems.

By mimicking the information expression ways in human's brain, deep neural network refers to a deeply structured framework with multiple processing layers that attempt to model high-level abstractions of the data. It is becoming a mainstream technology for pattern recognition, data mining and intelligent control at industrial scale. Previous work on constructing very deep networks, such as convolutional neural network and recurrent neural network, makes complex tasks such as image classification feasible. However, they are very limited when dealing with irregular data whose features are unstructured or even unknown. The traditional fully connected neural network is contrarily too shallow to extract high-level features. In this paper, we present a balance gate controlled deep network structure to deepen the fully connected neural network. It uses a new gating strategy to control information flow and increase network stability. Experimental results on both irregular regression and time-series forecasting demonstrate that the proposed network out-performs other ad-hoc models and is easier to train in a deeper form than the fully connected neural network.

The problem of service matching and scheduling in cloud manufacturing (CMfg) is complex for different types of manufacturing services. 3D printing, as a rapidly developing manufacturing technology, has become an important service form in the CMfg platform due to its characteristics of personalized manufacturing. How to solve the task scheduling problem for distributed 3D printing services in CMfg needs further research. In this paper, a service transaction model of 3D printing services in CMfg is built. Based on the service transaction model, we propose 3D printing service matching strategies and matching rules of different service attributes, including model size, printing material, printing preciseness, task cost, task time, and logistics. To reduce the delivery time of tasks from service suppliers to service demanders, a 3D printing service scheduling (3DPSS) method is proposed to generate optimal service scheduling solutions. In 3DPSS, optimization objective, constraints, and optimization algorithm are presented in detail. Experimental results show that the average task delivery time of 3DPSS is shorter than that of typical scheduling methods, such as particle swarm optimization, pattern search, and sequential quadratic programming, when the amounts of tasks change.

With the development of cloud computing (CC), service-oriented architecture (SOA), and container technology, modeling and simulation (M&S) resources, such as simulation software and different sorts of models, can be shared and reused in a cloud environment. Modeling and Simulation as a Service (MSaaS), as a new paradigm, supports sharing simulation models or modeling tools and has enabled a wide range of model reuse. However, reusing or combining some immature models may result in inefficient M&S activities or even false simulation results. To make sure the appropriate reuse and composition of simulation models in cloud environments, which is also termed as model service composition for simulation (MSCS), this paper incorporates model maturity with service cooperation as a metric to evaluate the quality of model composition in cloud. Then, as a multi-objective optimization problem with multiple constraints, the MSCS problem and its process are described in detail. To solve the MSCS problem, a novel evolutionary algorithm named CA-AO-NSGAII is proposed. In the algorithm, adaptive crossover and mutation operators, as well as probabilistic initialization are developed. Furthermore, a half-local search algorithm in an elitist mechanism is designed for efficient decision-making. To validate the performance of CA-AO-NSGAII, experiments with respect to four different cases are conducted. Results show that the proposed method for addressing MSCS issue is effective and feasible.

Cloud manufacturing (CMfg) is a new business paradigm that aims to provide manufacturing resources as services over the Internet in a convenient pay-as-you-go mode. Service composition is a critical means for achieving value adding and synergy of resources in CMfg. There are a vast number of services in a CMfg platform, which makes traditional service composition methods incapable and low efficiency in solving the problem of service composition. Most of existing research on CMfg was devoted to the optimal selection of services under a specific composition flow and a group of given candidate pools. Hence, there is a need to explore effective approaches to obtaining service composition flow and candidate sets. The network-based web service composition approach has recently drawn much attention and has been proved effective in coping with the challenge of large-scale services. Inspired by this, a novel approach called service clustering network-based service composition is proposed in this paper. In this met...

Cloud computing is getting more prevalent and finding a way to reduce the cost of cloud computing platform through the migration of virtual machines (VM) is a concerned issue. In this paper, the problem of dynamic migration of VMs (DM-VM) in the cloud computing platform (or simply the cloud) is investigated. A triple-objective optimization model for DM-VM is established, which takes energy consumption, communication between VMs, and migration cost into account under the situation that the platform works normally. The DM-VM problem is divided into two parts: (i) forming VMs into groups, and (ii) determining the best way to place the groups into certain physical nodes. A binary graph matching-based bucket-code learning algorithm (BGM-BLA) is designed for solving the DM-VM problem. In BGM-BLA, bucket-coding and learning is employed for finding the optimal solutions, and binary graph matching is used for evaluating the candidate solutions. The computational results demonstrate that the proposed BGM-BLA algorithm performs relatively well in terms of the Pareto sets obtained and computational time in comparison with two optimization algorithms, i.e., Non-dominated Sorting Genetic Algorithm (NSGA-II) and binary graph matching-based common-coding algorithm.

Credibility is an integrated index to measure whether a simulation model is credible enough to a specific requirement. It is an overview of model accuracy, uncertainty, and performance throughout its whole life cycle following a particular simulation requirement. In this chapter, we present a framework based on a NASA standard to unify the complete process of model credibility measurement. As a significant amount of theories and methods have been proposed to implement VV&A for various models, we mainly focus on how to extract the credibility-relevant characteristics from the life cycle of a model and how to incrementally incorporate the existing methods and historical data to evaluate the credibility of a specific model during its real-time simulation. With the framework proposed in this chapter, both quantitative evaluation result and experts’ scoring are combined to give a hierarchical view on model credibility. Moreover, the credibility evaluation process can be accelerated and made more intelligent using the incremental learning method.

Cloud manufacturing is an advanced production method in modern manufacturing. Cloud manufacturing can improve the production efficiency of a company by satisfying the diversified needs of customers by managing distributed resources in a centralized manner and rationally distributing and sharing resources according to production requirements. The production scheduling problem is the core issue of production in the cloud manufacturing environment. This paper first analyzes the characteristics of the cloud manufacturing mode of production and the new problems brought by these characteristics to the scheduling, and then analyzes the limitations of the traditional scheduling algorithm. Thirdly, based on the uncertainty of service time in cloud manufacturing environment, the paper proposes a new dynamic scheduling algorithm. Finally, the algorithm is verified by simulation experiments.

Cloud Manufacturing environment enables enterprises to share their resources together for rental profits and customized production. The fact that most manufacturing devices are organized and controlled in a particular production line hinders the flexible use of the corresponding services in a cloud platform. Therefore, the collaborative selection of upper layer suppliers and the underlying manufacturing services is of great importance, but rarely considered. To address the problem, a two-layer integrated model of supplier selection and service scheduling is proposed to provide feasible solutions for different kinds of production requirements. The decomposition-based multi-objective evolutionary algorithm, i.e., MOEA/D, is applied to minimize the production time, the rental cost and the transportation cost for producing a customized product. We empirically demonstrate that the integrated optimization way is more efficient than the original two-step decision way in practice.

With the conception and application of cloud manufacturing getting into manufacturing enterprises, more and more enterprises begin to establish the cloud system. How to collect the knowledge generated in these systems and pro-vide it to the enterprise manufacturing cloud for use is now an important issue. This paper presents an architecture of knowledge cloud based on manufacturing big data, according to the characteristics of manufacturing big data, building a knowledge database by ontology, encapsulation the knowledge service, and finally providing the provide the support for the enterprise manufacturing cloud.

As an emerging service-oriented manufacturing paradigm, Cloud Manufacturing (CMfg) is expected to provide smart networked platforms that enable efficient global collaborations among cloud service providers in a product lifecycle. The service provider cooperative relationship (SPCR) plays a crucial part in cloud service scheduling and thus potentially influences the operational performance of a CMfg platform. The guaranteed SPCR could ensure service quality and reduce the interaction costs among service providers in the process of collaborative manufacturing tasks, thereby having a positive impact on the operational efficiency of a CMfg platform. The cost reduction and quality assurance, however, usually make the cost-effective services more attractive for an increasing number of manufacturing tasks and lead to load imbalance in a CMfg platform, thus having a negative impact on the operational efficiency. The impact mechanism of SPCR on a CMfg platform is still unclear from an evolutionary perspective. In this paper, we propose a CMfg platform evolution model (CPEM) to investigate the impacts of SPCR on the operational performance of a CMfg platform. Three quantitative metrics, from the perspective of cloud consumer, cloud operator, and cloud service provider, respectively, are established to support the performance evaluation. The results of contrast experiments reveal the impacts of SPCR on a CMfg platform.

3D shape design is one of the most vital procedures in addictive manufacturing, especially in the environment of cloud manufacturing. And the consumption of time and energy to design a 3D shape is huge. Our objective is developing a 3D shape generative technique applied in the process of 3D printing model shape design. As generative adversarial networks (GAN) in field of deep learning has the potential to generate 3D shape models based the latent vector sampled from prior latent spaces. We use Conditional GAN as the solution to map image information to 3D printing shapes that satisfy the printable requirements. We evaluate the capability of our model to generate authentic 3D printing shapes across the several classes. Basically, the model could be an alternative as an assistant 3D printing shape designer.

The problem of task allocation and service selection in the complex dynamic cloud manufacturing (CMfg) environment is complex for different types of manufacturing resources. With the rapid development of 3D printing technology, the supply-demand matching problem of 3D printing tasks and services in CMfg needs to be modelled specifically. In this paper, the service attributes of 3D printing services are analyzed, including model size, printing material, printing preciseness, cost, time and logistics. The service transaction model of 3D printing services is built. To reduce delivery time of tasks from service suppliers to service demanders, a 3D printing service matching and selection method (MST) is proposed to generate the optimal solutions. Experimental results show that the average task completion time with MST is less than that of the typical method when the amounts of tasks change. Besides, MST can balance the task assignment among different service providers.

Cloud manufacturing (CMfg) mode provides an effective means to intensely utilize distributed resources and manufacturing capability for personalized production. Increasing personalized customization implies more and more heterogeneous tasks and hence more sorts of requirements for services. As the granularity of tasks vary with changing users and products, the solution (or scheme) of task scheduling should be different. In order to efficiently provide the most suitable solution for each kind of tasks, different scheduling ways should be adopted under different circumstances. In this paper, we study scheduling issues for heterogeneous tasks with variable granularity and present two kinds of optimal scheduling mode based on user-oriented comprehensive evaluation. Then different encoding schemes relied on the genetic algorithm are proposed according to different scheduling strategies.

Cloud manufacturing paradigm aims at gathering distributed manufacturing resources and enterprises to serve for more customized production. Production order which involving several tasks can be taken by distributed suppliers collaboratively at lower cost. The cloud manufacturing platform is responsible for not only arranging reasonable priorities, suitable suppliers, and production processes to multiple orders, but also scheduling hybrid tasks from different orders to manufacturing resources. To maximize the production efficiency and balance the trade-off among different production orders, this paper studies multi-phase integrated scheduling of hybrid tasks in cloud manufacturing environment, which containing order priority assignment, supplier and production process selection, and production line scheduling. Five key objectives are taken into account to analyze the interconnections among different resources and production processes. Six representative multi-objective evolutionary algorithms are adopted to solve the integrated scheduling problem. Experimental results on six production cases show that integrated scheduling is more effective than the traditional step-by-step decision, leading to less production cost and time. In addition, a comparison among the six algorithms is carried out to determine the one best suited for the integrated scheduling problem in different circumstances.

With the continuous deepening of the application of information technology in the manufacturing field, the informatization of manufacturing systems has developed from unit digital manufacturing to integrated networked manufacturing, and then to comprehensive digital, networked and intelligent manufacturing. As a comprehensive information technology integrating computer, model theory, and scientific computing, the modeling and simulation technology plays an irreplaceable role in the development process of manufacturing informatization and is widely applied in all stages of product life cycle containing design, production, testing, maintenance, procurement and sales. This paper reviews and summarizes the research and application of modeling and simulation technology in manufacturing, and analyzes typical simulation techniques in manufacturing from aspects of manufacturing unit simulation, manufacturing integrated simulation and manufacturing intelligent simulation.

In order to realize the full-scale sharing, free circulation and transaction, and on-demand-use of manufacturing resource and capabilities in modern enterprise systems (ES), Cloud manufacturing (CMfg) as a new service-oriented manufacturing paradigm has been proposed recently. Compared with cloud computing, the services that are managed in CMfg include not only computational and software resource and capability service, but also various manufacturing resources and capability service. These various dynamic services make ES more powerful and to be a higher-level extension of traditional services. Thus, as a key issue for the implementation of CMfg-based ES, service composition optimal-selection (SCOS) is becoming very important. SCOS is a typical NP-hard problem with the characteristics of dynamic and uncertainty. Solving large scale SCOS problem with numerous constraints in CMfg by using the traditional methods might be inefficient. To overcome this shortcoming, the formulation of SCOS in CMfg with multiple objectives and constraints is investigated first, and then a novel parallel intelligent algorithm, namely full connection based parallel adaptive chaos optimization with reflex migration (FC-PACO-RM) is developed. In the algorithm, roulette wheel selection and adaptive chaos optimization are introduced for search purpose, while full-connection parallelization in island model and new reflex migration way are also developed for efficient decision. To validate the performance of FC-PACO-RM, comparisons with 3 serial algorithms and 7 typical parallel methods are conducted in three typical cases. The results demonstrate the effectiveness of the proposed method for addressing complex SCOS in CMfg.

Multi-objective combinatorial optimization (MOCO) is an essential concern for the implementation of large-scale distributed modeling and simulation (MS) system. It is more complex than general computing systems, with higher dynamics and stricter demands on real-time performance. The quality and speed of the optimal decision directly decides the efficiency of the simulation. However, few works have been carried out for multi-objective combinatorial optimization MOCO especially in large-scale and service-oriented distributed simulation systems (SoDSSs). The existing algorithms for MOCO in SoDSSs are far from enough owing to their low accuracy or long decision time. To overcome this bottleneck, in this paper, a quantum multi-agent evolutionary algorithm (QMAEA), for addressing MOCO in large-scale SoDSSs is proposed. In QMAEA, the concept and characteristics of agent and quantum encoding are introduced for high intelligent searching. Each agent represented by a quantum bit, called a quantum agent (QAgent), is defined as a candidate solution for a MOCO problem, and each QAgent is assigned an energy, which denotes the fitness or objective function value of the candidate solution represented by it. Each QAgent is connected by four other QAgents nearby, and all QAgents are organized by an annular grid, called a multi-agent grid (MAG). In a MAG system, the population of QAgents can reproduce, perish, compete for survival, observe and communicate with the environment, and make all their decisions autonomously. Several operators, i.e. energy-evaluation-operator, competition-operator, crossover-operator, mutation-operator and trimming-operator, are designed to specify the evolvement of the MAG. The theory of predatory search strategy of animals is introduced in the evolution of QMAEA. Multiple evolutionary strategies, such as local-evolution-strategy, local-mutation-strategy and global-mutation-strategy are designed and used to balance the exploration (global search ability) and the exploitation (local search ability) of QMAEA. The framework and procedures of QMAEA are presented in detail. The simulation and comparison results demonstrate the proposed method is very effective and efficient for addressing MOCO in SoDSSs.

Private cloud as an important branch of cloud computing has brought significant benefit to many kinds of conglomerates in resource sharing. With central management of centre console, Service Composition Optimal Selection (SCOS) and Optimal Allocation of Computing Resources (OACR) are two critical steps for implementing high flexible and agile service provision and resource sharing among sub-enterprises and partner-enterprises under the key technologies of virtualization. However, two steps decision-making are inefficient and cumbersome. To overcome this deficiency, the idea of combining SCOS and OACR into one-time decision in one console is first presented in this paper, named Dual Scheduling of Cloud Services and Computing Resources (DS-CSCR). The mutual relations between the upper layer cloud services and the underlying infrastructures and their properties in the private cloud of conglomerate are deeply analyzed. For addressing large-scale DS-CSCR problem, a new Ranking Chaos Optimization (RCO) is proposed. With the consideration of large-scale irregular solution spaces, new adaptive chaos operator is designed to traverse wider spaces within a short time. Besides, dynamic heuristic and ranking selection are introduced to control the chaos evolution in the proposed algorithm. Theoretical analysis and simulations demonstrate that the new DS-CSCR outperforms the traditional two-level decision making with the improvements in both cloud service composition and computing resource allocation. In addition, RCO can remarkably give much prominent solutions with low time-consuming and high stability than a few typical intelligent algorithms for solving DS-CSCR in private cloud. With the new DS-CSCR and RCO, cloud services and computing infrastructures can then be quickly combined and shared with high efficient decision.

The Probabilistic Matrix Factorization (PMF) model has been widely studied for recommender systems, which outperform previous models with a solid probabilistic explanation. To further improve its accuracy by using social information, researchers attempt to combine the PMF model with social network graphs by adding social terms. However, existing works on social terms do not provide theoretical explanations to make the models well understood. The lack of explanations limits further improvement of prediction accuracy. Hence, in this paper we provide our explanation and propose a unified covariance framework to solve this problem. Our explanation, including regularization terms, factorization terms and an ensemble of them, reveals how most social terms work from a probabilistic view. Our framework shows that those terms could be optimized in a direct way compatible to PMF. We find out that accuracy improvements for existing works on regularization terms rely more on personalized properties, and that social information for factorization terms is helpful but not always necessary.

The partner selection problem (PSP) in virtual enterprise has been comprehensively investigated from the aspects of research fields, contents, attributes or criteria been considered, and algorithms. With the consideration of environmental protection, the importance of “green criteria” in PSP is introduced, and two new green criteria, i.e., carbon emission and lead content in manufacturing production, are firstly brought into PSP. A formulation of PSP with green criteria is established which includes four objectives and six constraints. A new improved algorithm, named Pareto genetic algorithm for PSP (Pareto-PSGA), is designed for addressing the specific PSP. With Pareto solution ideas, vector encoding, random selection, two-point crossover, and single-point mutation for Pareto solutions are designed in the Pareto-PSGA. Experimental results demonstrate that compared with other typical intelligent algorithms such as simulated annealing and particle swarm optimization, Pareto-PSGA shows high performance in solving the specific PSP with more suitable Pareto solutions in shorter time.

As a new advanced service-oriented networked manufacturing model, cloud manufacturing (CMfg) has been proposed recently. The optimal allocation of computing resources (OACR) is a core part for implementing CMfg. High heterogeneity, high dynamism, and virtualization make the OACR problem more complex than the traditional scheduling problems in grid system or cloud computing system. In this paper, a new comprehensive model for OACR is proposed in the CMfg system. In this model, all main computation, communication, and reliability constraints in the special circumstances are considered. To solve the OACR problem, a new improved niche immune algorithm was presented. Associated with the niche strategy, new heuristics are designed flexibly based on the characteristics of the problem and pheromone is added for adaptive searching. Experiments demonstrate the effectiveness of the designed heuristic information and show NIA’s high performances for addressing the OACR problem compared with other intelligent algorithms.

Resource service composition RSC, which has the ability to realise the added-value of resource service, can satisfy the high-quality application demand of customers. However, in the process of RSC, there always are many uncertain factors influencing the dynamics of RSC, which makes the manufacturing task impossible to be completed efficiently and with high quality. In order to deal with the resulting failures of RSC due to these dynamic changes, this article presented the concept of RSC flexibility as well as the idea of RSC optimal-selection based on flexibility, which can enable RSC to adapt to the dynamic changes. First, the related factors affecting the life-cycle of RSC were analysed, and the definition and classification of RSC flexibility were investigated. Then, the quantitative measuring method of RSC flexibility was investigated, which can establish the perfect evaluation system of RSC flexibility and to achieve the RSC optimal-selection based on flexibility. Meantime, several case studies were presented to illustrate the proposed measurement method. Finally, the significance and effectiveness to put forward the RSC flexibility were tested through simulation experiments.

More and more evolutionary operators have been integrated and manually configured together to solve a wider range of problems. Considering the very limited progress made on the automatic configuration of evolutionary algorithms (EAs), a rotated neighbor learning-based auto-configured evolutionary algorithm (RNL-ACEA) is presented. In this framework, multiple EAs are combined as candidates and automatically screened for different scenarios with a rotated neighbor structure. According to a ranking record and a group of constraints, the algorithms can be better scheduled to improve the searching efficiency and accelerate the searching pace. Experimental studies based on 14 classical EAs and 22 typical benchmark problems demonstrate that RNL-ACEA outperforms other six representative auto-adaptive EAs and has high scalability and robustness in solving different kinds of numerical optimization problems.

Virtualization is a crucial technology of cloud computing to enable the flexible use of a significant amount of distributed computing services on a pay-as-you-go basis. As the service demand continuingly increases to a global scale, efficient virtual machine consolidation becomes more and more imperative. Existing heuristic algorithms targeted mostly at minimizing either the rate of service level agreement violations or the energy consumption of the cloud. However, the communication overhead among different virtual machines and the decision time of virtual machine consolidation are rarely considered. To reduce both the over-utilized nodes and the under-utilized nodes with the consideration of migration cost, communication overhead, and energy consumption, this paper presents a new iterative budget algorithm in which a budget heuristic and a multi-stage selection strategy are designed to find suitable migration objects and targets simultaneously. Experiments show that the proposed algorithm provides a substantial improvement over other typical heuristics and metaheuristic algorithms in reducing the energy consumption, the number of migrated virtual machines, the overall communication overhead, as well as the decision time.

In this chapter, CLPS-GA (A Case Library and Pareto Solution-based improved Genetic Algorithm) [Appl Soft Comput 11(3):3056–3065, 2004] for addressing Energy-aware Cloud Service Scheduling (ECSS) in cloud manufacturing is introduced.

In this chapter, for solving optimal allocation of computing resources (OACR) problem in cloud manufacturing (CMfg) [1], serial three-layer operation configuration and parallel configuration are both applied.

Up to now, intelligent optimization algorithm has been developed for nearly 40 years. It is one of the main research directions in the field of algorithm and artificial intelligence. No matter for complex continuous problems or discrete NP-hard combinatorial optimizations, people nowadays is more likely to find a feasible solution by using such randomized iterative algorithm within a short period of time instead of traditional deterministic algorithms. In this chapter, the basic principle of algorithms, research classifications, and the development trends of intelligent optimization algorithm are elaborated.

In this chapter, the idea of combining SCOS and OACR into one-time decision in one console is presented, named Dual Scheduling of Cloud Services and Computing Resources (DS-CSCR) [1]. For addressing large-scale DS-CSCR problem, Ranking Chaos Optimization (RCO) is configured. With the consideration of large-scale irregular solution spaces, new adaptive chaos operator is designed to traverse wider spaces within a short time. Besides, dynamic heuristic and ranking selection are hybrid to control the chaos evolution in the proposed algorithm.

Recently, a new advanced service-oriented networked manufacturing model: Cloud Manufacturing (CMfg) has been proposed. The optimal allocation of computing resources (OACR) for the whole life-circle of manufacturing is an important part of CMfg. In order to implement optimal allocation, A new model for the computing resources and manufacturing tasks in CMfg is presented in this study, in which both the computation and communication factors are considered, and the formalized description on their dynamic process is given out. Primary constraints were introduced and the optimal objective of the model was proposed. Then the standard genetic algorithm (GA) was introduced to OACR. Experiments illustrated the effect of the constraints on the model and the application of GA on this problem.

Product design plays a key role in realizing manufacturing enterprise’s core value and enhancing its competitive power. An open, flexible and agile environment is needed for supporting product collaborative design. The emergence of semantic service oriented architecture (Semantic SOA) has brought about a loosely coupled computing pattern, which can promote system interoperability and resource reusability. In this paper, a Semantic SOA based framework for product collaborative design is proposed. The framework integrates some design resources which are heterogeneous and distributed, and facilitates collaborative work of design teams in different disciplines. In addition, some key enabling technologies including resource encapsulation methodology and product information sharing model are studied. Furthermore, a prototype system is designed and implemented. Feasibility of the prototype system is validated by practical use. The application results show that the framework can shorten the design cycle, and is favorable to collaborative design for complex product.

With the development of cloud computing, more and more virtual computing resources are provided as dynamic services to achieve green and agile computing for different kinds of projects. Virtual machine migration, as one of the main technologies, has brought huge influences on the executive and collaborative efficiency of virtual machines. However, the existing research focuses primarily on management and scheduling of virtual machines. And several studies concerning virtual machine migration in service-oriented computing still have great limitations. Especially, with the expansion of the scale of collaborative computing tasks, the complexity, as well as the number of virtual machines increased significantly. When the pre-allocation of virtual machines becomes unsuitable due to some resource failures or long waiting queue, migration of virtual machine becomes imperative. Considering the influence of initial allocation, this paper proposes a new parallel plant collaborative growth algorithm (namely Parallel-PCGA) which combines efficient plant growth optimisation operator and ring topology-based parallelisation. It brings an effective balance in solution time and accuracy. Experimental results prove that Parallel-PCGA shows high performance in large-scale virtual machine migration in cloud computing.