Pub Date : 2019-10-01DOI: 10.23919/CNSM46954.2019.9012741
Forough Shahab Samani, Hongyi Zhang, R. Stadler
In networked systems engineering, operational data gathered from sensors or logs can be used to build data-driven functions for performance prediction, anomaly detection, and other operational tasks. The number of data sources used for this purpose determines the dimensionality of the feature space for learning and can reach millions for medium-sized systems. Learning on a space with high dimensionality generally incurs high communication and computational costs for the learning process. In this work, we apply and compare a range of methods, including, feature selection, Principle Component Analysis (PCA), and autoencoders with the objective to reduce the dimensionality of the feature space while maintaining the prediction accuracy when compared with learning on the full space. We conduct the study using traces gathered from a testbed at KTH that runs a video-on-demand service and a key-value store under dynamic load. Our results suggest the feasibility of reducing the dimensionality of the feature space of operational data significantly, by one to two orders of magnitude in our scenarios, while maintaining prediction accuracy. The findings confirm the Manifold Hypothesis in machine learning, which states that real-world data sets tend to occupy a small subspace of the full feature space. In addition, we investigate the tradeoff between prediction accuracy and prediction overhead, which is crucial for applying the results to operational systems.
{"title":"Efficient Learning on High-dimensional Operational Data","authors":"Forough Shahab Samani, Hongyi Zhang, R. Stadler","doi":"10.23919/CNSM46954.2019.9012741","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012741","url":null,"abstract":"In networked systems engineering, operational data gathered from sensors or logs can be used to build data-driven functions for performance prediction, anomaly detection, and other operational tasks. The number of data sources used for this purpose determines the dimensionality of the feature space for learning and can reach millions for medium-sized systems. Learning on a space with high dimensionality generally incurs high communication and computational costs for the learning process. In this work, we apply and compare a range of methods, including, feature selection, Principle Component Analysis (PCA), and autoencoders with the objective to reduce the dimensionality of the feature space while maintaining the prediction accuracy when compared with learning on the full space. We conduct the study using traces gathered from a testbed at KTH that runs a video-on-demand service and a key-value store under dynamic load. Our results suggest the feasibility of reducing the dimensionality of the feature space of operational data significantly, by one to two orders of magnitude in our scenarios, while maintaining prediction accuracy. The findings confirm the Manifold Hypothesis in machine learning, which states that real-world data sets tend to occupy a small subspace of the full feature space. In addition, we investigate the tradeoff between prediction accuracy and prediction overhead, which is crucial for applying the results to operational systems.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"209 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133110169","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 : 2019-09-26DOI: 10.23919/CNSM46954.2019.9012736
Mahya Soleimani Jadidi, Mariusz Zaborski, B. Kidney, J. Anderson
Network services are among the riskiest programs executed by production systems. Such services execute large quantities of complex code and process data from arbitrary — and untrusted — network sources, often with high levels of system privilege. It is desirable to confine system services to a least-privileged environment so that the potential damage from a malicious attacker can be limited, but existing mechanisms for sandboxing services require invasive and system-specific code changes and are insufficient to confine broad classes of network services. Rather than sandboxing one service at a time, we propose that the best place to add sandboxing to network services is in the service manager that starts those services. As a first step towards this vision, we propose CapExec, a process supervisor that can execute a single service within a sandbox based on a service declaration file in which, required resources whose limited access to are supported by Caper services, are specified. Using the Capsicum compartmentalization framework and its Casper service framework, CapExec provides robust application sandboxing without requiring any modifications to the application itself. We believe that this is the first step towards ubiquitous sandboxing of network services without the costs of virtualization.
{"title":"CapExec: Towards Transparently-Sandboxed Services","authors":"Mahya Soleimani Jadidi, Mariusz Zaborski, B. Kidney, J. Anderson","doi":"10.23919/CNSM46954.2019.9012736","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012736","url":null,"abstract":"Network services are among the riskiest programs executed by production systems. Such services execute large quantities of complex code and process data from arbitrary — and untrusted — network sources, often with high levels of system privilege. It is desirable to confine system services to a least-privileged environment so that the potential damage from a malicious attacker can be limited, but existing mechanisms for sandboxing services require invasive and system-specific code changes and are insufficient to confine broad classes of network services. Rather than sandboxing one service at a time, we propose that the best place to add sandboxing to network services is in the service manager that starts those services. As a first step towards this vision, we propose CapExec, a process supervisor that can execute a single service within a sandbox based on a service declaration file in which, required resources whose limited access to are supported by Caper services, are specified. Using the Capsicum compartmentalization framework and its Casper service framework, CapExec provides robust application sandboxing without requiring any modifications to the application itself. We believe that this is the first step towards ubiquitous sandboxing of network services without the costs of virtualization.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130458281","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 : 2019-09-04DOI: 10.23919/CNSM46954.2019.9012727
Trung V. Phan, S. Islam, Tri Gia Nguyen, T. Bauschert
Software-Defined Networking (SDN) introduces a centralized network control and management by separating the data plane from the control plane which facilitates traffic flow monitoring, security analysis and policy formulation. However, it is challenging to choose a proper degree of traffic flow handling granularity while proactively protecting forwarding devices from getting overloaded. In this paper, we propose a novel traffic flow matching control framework called Q-DATA that applies reinforcement learning in order to enhance the traffic flow monitoring performance in SDN based networks and prevent traffic forwarding performance degradation. We first describe and analyse an SDN-based traffic flow matching control system that applies a reinforcement learning approach based on Q-learning algorithm in order to maximize the traffic flow granularity. It also considers the forwarding performance status of the SDN switches derived from a Support Vector Machine based algorithm. Next, we outline the Q-DATA framework that incorporates the optimal traffic flow matching policy derived from the traffic flow matching control system to efficiently provide the most detailed traffic flow information that other mechanisms require. Our novel approach is realized as a REST SDN application and evaluated in an SDN environment. Through comprehensive experiments, the results show that—compared to the default behavior of common SDN controllers and to our previous DATA mechanism—the new Q-DATA framework yields a remarkable improvement in terms of traffic forwarding performance degradation protection of SDN switches while still providing the most detailed traffic flow information on demand.
软件定义网络SDN (software defined Networking)通过数据平面和控制平面的分离，实现了网络的集中控制和管理，便于流量监控、安全分析和策略制定。然而，如何在主动保护转发设备不过载的同时，选择合适的流量处理粒度是一个挑战。在本文中，我们提出了一种名为Q-DATA的新型流量匹配控制框架，该框架应用强化学习来提高基于SDN网络的流量监控性能并防止流量转发性能下降。我们首先描述和分析了一个基于sdn的交通流匹配控制系统，该系统采用基于q -学习算法的强化学习方法来最大化交通流粒度。它还考虑了基于支持向量机的SDN交换机的转发性能状态。接下来，我们概述了Q-DATA框架，该框架结合了来自交通流匹配控制系统的最优交通流匹配策略，以有效地提供其他机制所需的最详细的交通流信息。我们的新方法作为REST SDN应用程序实现，并在SDN环境中进行了评估。通过综合实验，结果表明，与常见SDN控制器的默认行为和我们之前的DATA机制相比，新的Q-DATA框架在SDN交换机的流量转发性能降级保护方面有了显着改善，同时仍然提供了最详细的流量流信息。
{"title":"Q-DATA: Enhanced Traffic Flow Monitoring in Software-Defined Networks applying Q-learning","authors":"Trung V. Phan, S. Islam, Tri Gia Nguyen, T. Bauschert","doi":"10.23919/CNSM46954.2019.9012727","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012727","url":null,"abstract":"Software-Defined Networking (SDN) introduces a centralized network control and management by separating the data plane from the control plane which facilitates traffic flow monitoring, security analysis and policy formulation. However, it is challenging to choose a proper degree of traffic flow handling granularity while proactively protecting forwarding devices from getting overloaded. In this paper, we propose a novel traffic flow matching control framework called Q-DATA that applies reinforcement learning in order to enhance the traffic flow monitoring performance in SDN based networks and prevent traffic forwarding performance degradation. We first describe and analyse an SDN-based traffic flow matching control system that applies a reinforcement learning approach based on Q-learning algorithm in order to maximize the traffic flow granularity. It also considers the forwarding performance status of the SDN switches derived from a Support Vector Machine based algorithm. Next, we outline the Q-DATA framework that incorporates the optimal traffic flow matching policy derived from the traffic flow matching control system to efficiently provide the most detailed traffic flow information that other mechanisms require. Our novel approach is realized as a REST SDN application and evaluated in an SDN environment. Through comprehensive experiments, the results show that—compared to the default behavior of common SDN controllers and to our previous DATA mechanism—the new Q-DATA framework yields a remarkable improvement in terms of traffic forwarding performance degradation protection of SDN switches while still providing the most detailed traffic flow information on demand.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132943379","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 : 2019-08-08DOI: 10.23919/CNSM46954.2019.9012702
Jaehoon Koo, V. Mendiratta, Muntasir Raihan Rahman, A. Elwalid
Efficient network slicing is vital to deal with the highly variable and dynamic characteristics of traffic in 5G networks. Network slicing addresses a challenging dynamic network resource allocation problem where a single network infrastructure is divided into (virtual) multiple slices to meet the demands of different users with varying requirements, the main challenges being — the traffic arrival characteristics and the job resource requirements (e.g., compute, memory and bandwidth resources) for each slice can be highly dynamic. Traditional model-based optimization or queueing theoretic modeling becomes intractable with the high reliability, and stringent bandwidth and latency requirements imposed by 5G. We propose a deep reinforcement learning approach to address this dynamic coupled resource allocation problem. Model evaluation using synthetic and real workload data demonstrates that our deep reinforcement learning solution improves overall resource utilization, latency performance, and demands satisfied as compared to a baseline equal slicing strategy.
{"title":"Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics","authors":"Jaehoon Koo, V. Mendiratta, Muntasir Raihan Rahman, A. Elwalid","doi":"10.23919/CNSM46954.2019.9012702","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012702","url":null,"abstract":"Efficient network slicing is vital to deal with the highly variable and dynamic characteristics of traffic in 5G networks. Network slicing addresses a challenging dynamic network resource allocation problem where a single network infrastructure is divided into (virtual) multiple slices to meet the demands of different users with varying requirements, the main challenges being — the traffic arrival characteristics and the job resource requirements (e.g., compute, memory and bandwidth resources) for each slice can be highly dynamic. Traditional model-based optimization or queueing theoretic modeling becomes intractable with the high reliability, and stringent bandwidth and latency requirements imposed by 5G. We propose a deep reinforcement learning approach to address this dynamic coupled resource allocation problem. Model evaluation using synthetic and real workload data demonstrates that our deep reinforcement learning solution improves overall resource utilization, latency performance, and demands satisfied as compared to a baseline equal slicing strategy.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125959496","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 : 2019-06-24DOI: 10.23919/CNSM46954.2019.9012711
Nashid Shahriar, Sepehr Taeb, S. R. Chowdhury, M. Zulfiqar, M. Tornatore, R. Boutaba, J. Mitra, Mahdi Hemmati
In 5G networks, slicing allows partitioning of network resources to meet stringent end-to-end service requirements across multiple network segments, from access to transport. These requirements are shaping technical evolution in each of these segments. In particular, the transport segment is currently evolving in the direction of the so-called elastic optical networks (EONs), a new generation of optical networks supporting a flexible optical-spectrum grid and novel elastic transponder capabilities. In this paper, we focus on the reliability of 5G transport-network slices in EON. Specifically, we consider the problem of slicing 5G transport networks, i.e., establishing virtual networks on 5G transport, while providing dedicated protection. As dedicated protection requires a large amount of backup resources, our proposed solution incorporates two techniques to reduce backup resources: (i) bandwidth squeezing, i.e., providing a reduced protection bandwidth with respect to the original request; and (ii) survivable multi-path provisioning. We leverage the capability of EONs to fine tune spectrum allocation and adapt modulation format and Forward Error Correction (FEC) for allocating rightsize spectrum resources to network slices. Our numerical evaluation over realistic case-study network topologies quantifies the spectrum savings achieved by employing EON over traditional fixed-grid optical networks, and provides new insights on the impact of bandwidth squeezing and multi-path provisioning on spectrum utilization.
{"title":"Reliable Slicing of 5G Transport Networks with Dedicated Protection","authors":"Nashid Shahriar, Sepehr Taeb, S. R. Chowdhury, M. Zulfiqar, M. Tornatore, R. Boutaba, J. Mitra, Mahdi Hemmati","doi":"10.23919/CNSM46954.2019.9012711","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012711","url":null,"abstract":"In 5G networks, slicing allows partitioning of network resources to meet stringent end-to-end service requirements across multiple network segments, from access to transport. These requirements are shaping technical evolution in each of these segments. In particular, the transport segment is currently evolving in the direction of the so-called elastic optical networks (EONs), a new generation of optical networks supporting a flexible optical-spectrum grid and novel elastic transponder capabilities. In this paper, we focus on the reliability of 5G transport-network slices in EON. Specifically, we consider the problem of slicing 5G transport networks, i.e., establishing virtual networks on 5G transport, while providing dedicated protection. As dedicated protection requires a large amount of backup resources, our proposed solution incorporates two techniques to reduce backup resources: (i) bandwidth squeezing, i.e., providing a reduced protection bandwidth with respect to the original request; and (ii) survivable multi-path provisioning. We leverage the capability of EONs to fine tune spectrum allocation and adapt modulation format and Forward Error Correction (FEC) for allocating rightsize spectrum resources to network slices. Our numerical evaluation over realistic case-study network topologies quantifies the spectrum savings achieved by employing EON over traditional fixed-grid optical networks, and provides new insights on the impact of bandwidth squeezing and multi-path provisioning on spectrum utilization.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130365653","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 : 2019-05-13DOI: 10.23919/CNSM46954.2019.9012740
Manuel Peuster, Stefan Schneider, H. Karl
More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input data to train their internal models. However, such training data is barely available for the software networking domain and most presented solutions rely on their own, sometimes not even published, data sets. This makes it hard, or even infeasible, to reproduce and compare many of the existing solutions. As a result, it ultimately slows down the adoption of machine learning approaches in softwarised networks.To this end, we introduce the “softwarised network data zoo” (SNDZoo), an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. We present a general methodology to collect, archive, and publish those data sets for use by other researchers and, as an example, eight initial data sets, focusing on the performance of virtualised network functions.
{"title":"The Softwarised Network Data Zoo","authors":"Manuel Peuster, Stefan Schneider, H. Karl","doi":"10.23919/CNSM46954.2019.9012740","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012740","url":null,"abstract":"More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input data to train their internal models. However, such training data is barely available for the software networking domain and most presented solutions rely on their own, sometimes not even published, data sets. This makes it hard, or even infeasible, to reproduce and compare many of the existing solutions. As a result, it ultimately slows down the adoption of machine learning approaches in softwarised networks.To this end, we introduce the “softwarised network data zoo” (SNDZoo), an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. We present a general methodology to collect, archive, and publish those data sets for use by other researchers and, as an example, eight initial data sets, focusing on the performance of virtualised network functions.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134027393","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 : 2019-02-05DOI: 10.23919/CNSM46954.2019.9012676
Ali Vahdat, Mouloud Belbahri, V. Nia
Erbium-doped fiber amplifier (EDFA) is an optical amplifier/repeater device used to boost the intensity of optical signals being carried through fiber optic communication networks. A highly accurate EDFA model – to predict the signal gain for each channel – is required because of its crucial role in optical network management and optimization. EDFA channel inputs (i.e. features) either carry signal or are idle, therefore they can be treated as binary features. However, channel outputs (and the corresponding signal gains) are continuous values. Labeled training data is very expensive to collect for EDFA devices, therefore we devise an active learning strategy suitable for binary features to overcome this issue. We propose to take advantage of sparse linear models to simplify the predictive model. This approach improves signal gain prediction and accelerates active learning query generation. We show the performance of our proposed active learning strategies on simulated data and real EDFA data.
{"title":"Active Learning for High-Dimensional Binary Features","authors":"Ali Vahdat, Mouloud Belbahri, V. Nia","doi":"10.23919/CNSM46954.2019.9012676","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012676","url":null,"abstract":"Erbium-doped fiber amplifier (EDFA) is an optical amplifier/repeater device used to boost the intensity of optical signals being carried through fiber optic communication networks. A highly accurate EDFA model – to predict the signal gain for each channel – is required because of its crucial role in optical network management and optimization. EDFA channel inputs (i.e. features) either carry signal or are idle, therefore they can be treated as binary features. However, channel outputs (and the corresponding signal gains) are continuous values. Labeled training data is very expensive to collect for EDFA devices, therefore we devise an active learning strategy suitable for binary features to overcome this issue. We propose to take advantage of sparse linear models to simplify the predictive model. This approach improves signal gain prediction and accelerates active learning query generation. We show the performance of our proposed active learning strategies on simulated data and real EDFA data.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123726031","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 : 2019-02-02DOI: 10.23919/CNSM46954.2019.9012709
P. Maillé, B. Tuffin
Sponsored data, where content providers have the possibility to pay wireless providers for the data consumed by customers and therefore to exclude it from the data cap, is getting widespread in many countries, but is forbidden in others for concerns of infringing the network neutrality principles. We present in this paper a game-theoretic model analyzing the consequences of sponsored data in presence of competing wireless providers, where sponsoring decided by the content provider can be different at each provider. We also discuss the impact on the proportion of advertising on the displayed content. We show that, surprisingly, the possibility of sponsored data may actually reduce the benefits of content providers and on the other hand increase the revenue of ISPs in competition, with a very limited impact on user welfare.
{"title":"Wireless Service Providers Pricing Game in Presence of Possible Sponsored Data","authors":"P. Maillé, B. Tuffin","doi":"10.23919/CNSM46954.2019.9012709","DOIUrl":"https://doi.org/10.23919/CNSM46954.2019.9012709","url":null,"abstract":"Sponsored data, where content providers have the possibility to pay wireless providers for the data consumed by customers and therefore to exclude it from the data cap, is getting widespread in many countries, but is forbidden in others for concerns of infringing the network neutrality principles. We present in this paper a game-theoretic model analyzing the consequences of sponsored data in presence of competing wireless providers, where sponsoring decided by the content provider can be different at each provider. We also discuss the impact on the proportion of advertising on the displayed content. We show that, surprisingly, the possibility of sponsored data may actually reduce the benefits of content providers and on the other hand increase the revenue of ISPs in competition, with a very limited impact on user welfare.","PeriodicalId":273818,"journal":{"name":"2019 15th International Conference on Network and Service Management (CNSM)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125164843","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：