Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00009
Zhixuan Jia, Shuangxi Huang, Yushun Fan
With the emergence of service Internet, various service networks have been developed, including manufacturing, health, and technology service networks. Currently, there is a lack of systematic research on the structure, characteristics, and evolution mechanism of service internet. It leads to the missing of theoretical guidance in management and optimization of service Internet. Intending to solve this problem, this paper evaluates the different aspects of service Internet ranging from concept, structure, composition, and system characteristics. A proposition of the synecological model for service internet based on ecosystem theory is also provided. Then, for the research on evolution mechanism, a service population evolution model and a service community succession model of service Internet synecosystem are proposed based on the logistic growth model. We also give the mathematical analysis methods for the stability and balance of these models. At last, the validity and reliability of our models are verified by the use of real-world automobile industrial cluster data.
{"title":"Research on the Synecological Model and Dynamic Evolution Mechanism of Service Internet","authors":"Zhixuan Jia, Shuangxi Huang, Yushun Fan","doi":"10.1109/SCC49832.2020.00009","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00009","url":null,"abstract":"With the emergence of service Internet, various service networks have been developed, including manufacturing, health, and technology service networks. Currently, there is a lack of systematic research on the structure, characteristics, and evolution mechanism of service internet. It leads to the missing of theoretical guidance in management and optimization of service Internet. Intending to solve this problem, this paper evaluates the different aspects of service Internet ranging from concept, structure, composition, and system characteristics. A proposition of the synecological model for service internet based on ecosystem theory is also provided. Then, for the research on evolution mechanism, a service population evolution model and a service community succession model of service Internet synecosystem are proposed based on the logistic growth model. We also give the mathematical analysis methods for the stability and balance of these models. At last, the validity and reliability of our models are verified by the use of real-world automobile industrial cluster data.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125195171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00014
Jing Li, Ming Zhu, Miao Yu, Yuhong Yan, Li-zhen Cui
Database-based composition approaches are evolving and coming into researchers’ notice. In this paper, we present a pre-joined service composition approach with dynamic services in a Graph database. Firstly, services’ information is stored in a graph database. Secondly, a composition network is constructed. Last but not least, a solution by converting the composition problem into graph database queries is fetched. Considering that services are dynamic and lead to frequent changes of service compositions, we discuss how to update the graph database, e.g., service addition, disappearance and update. Preliminary experiment indicates that the proposed approach can support service composition with services’ dynamic changes.
{"title":"A Pre-joined Service Composition Approach with Dynamic Services in a Graph Database","authors":"Jing Li, Ming Zhu, Miao Yu, Yuhong Yan, Li-zhen Cui","doi":"10.1109/SCC49832.2020.00014","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00014","url":null,"abstract":"Database-based composition approaches are evolving and coming into researchers’ notice. In this paper, we present a pre-joined service composition approach with dynamic services in a Graph database. Firstly, services’ information is stored in a graph database. Secondly, a composition network is constructed. Last but not least, a solution by converting the composition problem into graph database queries is fetched. Considering that services are dynamic and lead to frequent changes of service compositions, we discuss how to update the graph database, e.g., service addition, disappearance and update. Preliminary experiment indicates that the proposed approach can support service composition with services’ dynamic changes.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116061262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00057
Jianglei Han, Aixin Sun
Ticket routing is a part of software support process, where multiple expert groups are involved in processing incident tickets. The goal of routing is to find an expert group which can resolve a ticket at the initial assignment, or when it needs to be transferred to another group. Matching a ticket to its potential resolver effectively provides significant business value for both service providers and their customers. Previous works used hand-crafted features to train predictive models to automate or assist in routing. One of the findings shows that, the similarity between a ticket and an expert group is prominent in identifying the resolver among other groups. Meanwhile, numerous studies demonstrate the effectiveness of deep neural networks in text similarity modeling problems. In this paper, we propose a multi-view deep neural network solution to jointly learn a relevance score for a ticket-group pair, using both text and routing path information. The text relevance is modeled by a classic deep semantic matching model, while the routing graph representation is embedded using a convolutional graph network. Experimental results show that the proposed approach outperforms baseline models in resolver ranking and assistive routing tasks. Comparative experiments also show that text has higher importance than routing path information.
{"title":"DeepRouting: A Deep Neural Network Approach for Ticket Routing in Expert Network","authors":"Jianglei Han, Aixin Sun","doi":"10.1109/SCC49832.2020.00057","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00057","url":null,"abstract":"Ticket routing is a part of software support process, where multiple expert groups are involved in processing incident tickets. The goal of routing is to find an expert group which can resolve a ticket at the initial assignment, or when it needs to be transferred to another group. Matching a ticket to its potential resolver effectively provides significant business value for both service providers and their customers. Previous works used hand-crafted features to train predictive models to automate or assist in routing. One of the findings shows that, the similarity between a ticket and an expert group is prominent in identifying the resolver among other groups. Meanwhile, numerous studies demonstrate the effectiveness of deep neural networks in text similarity modeling problems. In this paper, we propose a multi-view deep neural network solution to jointly learn a relevance score for a ticket-group pair, using both text and routing path information. The text relevance is modeled by a classic deep semantic matching model, while the routing graph representation is embedded using a convolutional graph network. Experimental results show that the proposed approach outperforms baseline models in resolver ranking and assistive routing tasks. Comparative experiments also show that text has higher importance than routing path information.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121514653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00071
Ahmed Y. Al Hammadi, C. Yeun, E. Damiani
The Cybersecurity of organization is becoming quite alarming especially in National Critical Infrastructure (NCI) as to protect their sensitive information and other valuable assets. A lot of focus has been done in managing outside attacks of data in organizations. Including Cyber-Physical System (CPS), which is a complex mixture of physical and computer components typically monitored or controlled by computer-based algorithms. However, there has been need to safeguard insider’s behavior of breaching the expected code of conduct in maintaining the critical organizations’ data and assets. The technology is highly reliable as it cannot be easily fabricated. The analysis of the brainwave signal will be performed using an advanced deep learning algorithm called Long Short Term Memory Recurrent Neural Network (LSTM-RNN) classifier which will remember a previous mental states of each insider and compare it with new present brain state to classify the risk level associated. The brain wave is also analysed with Adaptive Machine learning Algorithm which combines several weak learners which is decision trees, to form a single strong learner. In this study, our targets is to increase the security of NCI by providing a significant proof of concept system to detect insider threats through fitness evaluation using EEG signals that gets analyzed using deep learning algorithm which will classify different mental states into four categories risk matrix.
{"title":"Novel EEG Risk Framework to Identify Insider Threats in National Critical Infrastructure Using Deep Learning Techniques","authors":"Ahmed Y. Al Hammadi, C. Yeun, E. Damiani","doi":"10.1109/SCC49832.2020.00071","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00071","url":null,"abstract":"The Cybersecurity of organization is becoming quite alarming especially in National Critical Infrastructure (NCI) as to protect their sensitive information and other valuable assets. A lot of focus has been done in managing outside attacks of data in organizations. Including Cyber-Physical System (CPS), which is a complex mixture of physical and computer components typically monitored or controlled by computer-based algorithms. However, there has been need to safeguard insider’s behavior of breaching the expected code of conduct in maintaining the critical organizations’ data and assets. The technology is highly reliable as it cannot be easily fabricated. The analysis of the brainwave signal will be performed using an advanced deep learning algorithm called Long Short Term Memory Recurrent Neural Network (LSTM-RNN) classifier which will remember a previous mental states of each insider and compare it with new present brain state to classify the risk level associated. The brain wave is also analysed with Adaptive Machine learning Algorithm which combines several weak learners which is decision trees, to form a single strong learner. In this study, our targets is to increase the security of NCI by providing a significant proof of concept system to detect insider threats through fitness evaluation using EEG signals that gets analyzed using deep learning algorithm which will classify different mental states into four categories risk matrix.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130720123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00034
A. Ramamurthy, Saket Saurabh, M. Gharote, S. Lodha
With the evolving data regulations and residency laws, it is becoming challenging for enterprises to serve all the geographically distributed users. To abide with the regulations and to leverage the benefits, such as good quality of service at a low cost, and avoid vendor lock-in, enterprises are seeking multiple Cloud Service Providers (CSPs) for hosting their web applications. The selection of CSPs in a multi-cloud environment is a challenging problem as it depends on multiple criteria such as security, service cost, manageability and so on.In this paper, we address the CSP selection problem for multiple applications in a multi-cloud environment comprising of multiple criteria. We provide a holistic solution methodology that ranks the CSP combinations for each web application using a multiple-criteria decision-making (MCDM) technique. The solution methodology takes virtual machine and cloud center selection into consideration for ranking the CSP combinations. However, selecting the top ranked CSP combinations for all applications may not be a viable option from the manageability and budget perspectives. Hence, we propose an optimization model to select CSPs for multiple applications of an enterprise considering budget and rank. We demonstrate our methodology through numerical experiments and provide various insights.
{"title":"Selection of Cloud Service Providers for Hosting Web Applications in a Multi-cloud Environment","authors":"A. Ramamurthy, Saket Saurabh, M. Gharote, S. Lodha","doi":"10.1109/SCC49832.2020.00034","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00034","url":null,"abstract":"With the evolving data regulations and residency laws, it is becoming challenging for enterprises to serve all the geographically distributed users. To abide with the regulations and to leverage the benefits, such as good quality of service at a low cost, and avoid vendor lock-in, enterprises are seeking multiple Cloud Service Providers (CSPs) for hosting their web applications. The selection of CSPs in a multi-cloud environment is a challenging problem as it depends on multiple criteria such as security, service cost, manageability and so on.In this paper, we address the CSP selection problem for multiple applications in a multi-cloud environment comprising of multiple criteria. We provide a holistic solution methodology that ranks the CSP combinations for each web application using a multiple-criteria decision-making (MCDM) technique. The solution methodology takes virtual machine and cloud center selection into consideration for ranking the CSP combinations. However, selecting the top ranked CSP combinations for all applications may not be a viable option from the manageability and budget perspectives. Hence, we propose an optimization model to select CSPs for multiple applications of an enterprise considering budget and rank. We demonstrate our methodology through numerical experiments and provide various insights.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131689247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00016
Shuyu Zheng, Fuqi Lin, Xuan Lu, Yulian Yang, Hongfei Deng, Jun Zhang, Yun Ma, Xuanzhe Liu
Service providers usually maintain multiple kinds of service clients, such as desktop Web pages, mobile Web pages, and mobile native apps, to satisfy different user requirements. Understanding how users consume services via these heterogeneous clients is important for service providers to efficiently manage back-end resources. However, little has been known about such facts. To bridge the knowledge gap, in this paper, we conduct the first empirical study on service access patterns via heterogeneous clients. Our study is based on two large-scale real-world datasets of launching events from both app and Web clients of 986 services, involving a sample of 60 million users within 7 days. We analyze the characteristics of service access patterns from both spatial view and temporal view. We explore how users consume online services through different service clients, and to what extent their usage behavior patterns vary when consuming the same service. Our findings provide better understandings for heterogeneous service clients that can facilitate the development, configuration, deployment and maintenance of service back-end.
{"title":"Characterizing Service Access Patterns under Heterogeneous Clients","authors":"Shuyu Zheng, Fuqi Lin, Xuan Lu, Yulian Yang, Hongfei Deng, Jun Zhang, Yun Ma, Xuanzhe Liu","doi":"10.1109/SCC49832.2020.00016","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00016","url":null,"abstract":"Service providers usually maintain multiple kinds of service clients, such as desktop Web pages, mobile Web pages, and mobile native apps, to satisfy different user requirements. Understanding how users consume services via these heterogeneous clients is important for service providers to efficiently manage back-end resources. However, little has been known about such facts. To bridge the knowledge gap, in this paper, we conduct the first empirical study on service access patterns via heterogeneous clients. Our study is based on two large-scale real-world datasets of launching events from both app and Web clients of 986 services, involving a sample of 60 million users within 7 days. We analyze the characteristics of service access patterns from both spatial view and temporal view. We explore how users consume online services through different service clients, and to what extent their usage behavior patterns vary when consuming the same service. Our findings provide better understandings for heterogeneous service clients that can facilitate the development, configuration, deployment and maintenance of service back-end.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134329051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/scc49832.2020.00083
{"title":"Message from the SCC 2020 Chairs","authors":"","doi":"10.1109/scc49832.2020.00083","DOIUrl":"https://doi.org/10.1109/scc49832.2020.00083","url":null,"abstract":"","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114300999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) represents the new industrial revolution, in which physical and virtual objects are interconnected. On the other hand, microservices architectures have broken the monolithic and centralized way to build software, and provide systems with high-quality characteristics (e.g., resilience, availability, modularity, and portability). Therefore, the idea of merging those technologies can constitute a powerful strategy to be applied in environments that demand the distribution and management of many IoT devices using high-quality software. In this context, several studies that integrate IoT with microservices solutions have been analyzed. However, most of these studies aim to satisfy the functional requirements related to software and hardware, without taking into account software engineering methodologies and good practices that allow the creation of software for IoT devices considering their distributed nature. Thus, this paper presents the first approach to an agile methodology that i) contemplates the main characteristics of the IoT and ii) guides the development of appropriate software solutions based on microservices architectures to manage IoT environments acknowledging the serious difficulties that microservices imply.
{"title":"Towards a Methodology for creating Internet of Things (IoT) Applications based on Microservices","authors":"Edwin Cabrera, Paola Cárdenas, Priscila Cedillo, Paola Pesántez-Cabrera","doi":"10.1109/SCC49832.2020.00072","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00072","url":null,"abstract":"The Internet of Things (IoT) represents the new industrial revolution, in which physical and virtual objects are interconnected. On the other hand, microservices architectures have broken the monolithic and centralized way to build software, and provide systems with high-quality characteristics (e.g., resilience, availability, modularity, and portability). Therefore, the idea of merging those technologies can constitute a powerful strategy to be applied in environments that demand the distribution and management of many IoT devices using high-quality software. In this context, several studies that integrate IoT with microservices solutions have been analyzed. However, most of these studies aim to satisfy the functional requirements related to software and hardware, without taking into account software engineering methodologies and good practices that allow the creation of software for IoT devices considering their distributed nature. Thus, this paper presents the first approach to an agile methodology that i) contemplates the main characteristics of the IoT and ii) guides the development of appropriate software solutions based on microservices architectures to manage IoT environments acknowledging the serious difficulties that microservices imply.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124870637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep reinforcement learning (RL) is playing an increasingly important role in web services such as news recommendation, vulnerability detection, and personalized services. Exploration is a key component of RL, which determines whether these RL-based applications could find effective solutions eventually. In this paper, we propose a novel gradient–based fast adaptation approach for model agnostic meta-reinforcement learning via Bayesian structure exploration (BSE-MAML). BSE-MAML could effectively learn exploration strategies from prior experience by updating policy with embedding latent space via a Bayesian mechanism. Coherent stochasticity injected by latent space are more efficient than random noise, and can produce exploration strategies to perform well in novel environment. We have conducted extensive experiments to evaluate BSE-MAML. Experimental results show that BSE-MAML achieves better performance in exploration in realistic environments with sparse rewards, compared to state-of-the-art meta-RL algorithms, RL methods without learning exploration strategies, and task-agnostic exploration approaches.
{"title":"BSE-MAML: Model Agnostic Meta-Reinforcement Learning via Bayesian Structured Exploration","authors":"Haonan Wang, Yiyun Zhang, Dawei Feng, Dongsheng Li, Feng Huang","doi":"10.1109/SCC49832.2020.00017","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00017","url":null,"abstract":"Deep reinforcement learning (RL) is playing an increasingly important role in web services such as news recommendation, vulnerability detection, and personalized services. Exploration is a key component of RL, which determines whether these RL-based applications could find effective solutions eventually. In this paper, we propose a novel gradient–based fast adaptation approach for model agnostic meta-reinforcement learning via Bayesian structure exploration (BSE-MAML). BSE-MAML could effectively learn exploration strategies from prior experience by updating policy with embedding latent space via a Bayesian mechanism. Coherent stochasticity injected by latent space are more efficient than random noise, and can produce exploration strategies to perform well in novel environment. We have conducted extensive experiments to evaluate BSE-MAML. Experimental results show that BSE-MAML achieves better performance in exploration in realistic environments with sparse rewards, compared to state-of-the-art meta-RL algorithms, RL methods without learning exploration strategies, and task-agnostic exploration approaches.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116000902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-01DOI: 10.1109/SCC49832.2020.00041
Meng Niu, B. Cheng, Junliang Chen
Network Function Virtualization (NFV) is a promising technology. Connecting Virtual Network Functions (VNFs) forms Service Function Chains (SFCs). SFCs can flexibly orchestrate and expand network functions. However, the SFCs perform network functions that require very high reliability, even reaching the level of physical switches. Therefore, the influence of physical machines and network links can no longer be ignored when considering the reliability of SFCs. This paper proposes the Graph-based Particle Swarm Optimization (GPSO) algorithm to address the SFC placement problem. GPSO adopts a novel velocity update strategy that can adapt to the non-Euclidean structure of the physical machine topology in the data center. Compared to traditional heuristic algorithms, GPSO only needs 57% execution time and can achieve 110% fitness value. Moreover, the GPSO algorithm can trade-off reliability and resource utilization. The evaluation results show that GPSO achieves higher reliability than the state of the art algorithms under the threshold of 80% resource utilization.
{"title":"GPSO: A Graph-based Heuristic Algorithm for Service Function Chain Placement in Data Center Networks","authors":"Meng Niu, B. Cheng, Junliang Chen","doi":"10.1109/SCC49832.2020.00041","DOIUrl":"https://doi.org/10.1109/SCC49832.2020.00041","url":null,"abstract":"Network Function Virtualization (NFV) is a promising technology. Connecting Virtual Network Functions (VNFs) forms Service Function Chains (SFCs). SFCs can flexibly orchestrate and expand network functions. However, the SFCs perform network functions that require very high reliability, even reaching the level of physical switches. Therefore, the influence of physical machines and network links can no longer be ignored when considering the reliability of SFCs. This paper proposes the Graph-based Particle Swarm Optimization (GPSO) algorithm to address the SFC placement problem. GPSO adopts a novel velocity update strategy that can adapt to the non-Euclidean structure of the physical machine topology in the data center. Compared to traditional heuristic algorithms, GPSO only needs 57% execution time and can achieve 110% fitness value. Moreover, the GPSO algorithm can trade-off reliability and resource utilization. The evaluation results show that GPSO achieves higher reliability than the state of the art algorithms under the threshold of 80% resource utilization.","PeriodicalId":274909,"journal":{"name":"2020 IEEE International Conference on Services Computing (SCC)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121385797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：