Rapid change in sensitive behaviour and profile of distributed mobile network elements necessitates privacy preserving distributed learning mechanism such as Federated Learning. Moreover, this mechanism needs to be robust that seamlessly sustains the jointly trained model accuracy. In order to provide a automated management of the learning process in FL on datasets that are not independently and identically distributed (non-iid), we propose a Multi-Arm Bandit (MAB) based method that helps the federation to select the nodes that benefits the overall model. This automated selection of the training nodes throughout each round yielded an improvement in accuracy, while decreasing network footprint.
{"title":"Automated Collaborator Selection for Federated Learning with Multi-armed Bandit Agents","authors":"Hannes Larsson, Hassam Riaz, Selim Ickin","doi":"10.1145/3472735.3473388","DOIUrl":"https://doi.org/10.1145/3472735.3473388","url":null,"abstract":"Rapid change in sensitive behaviour and profile of distributed mobile network elements necessitates privacy preserving distributed learning mechanism such as Federated Learning. Moreover, this mechanism needs to be robust that seamlessly sustains the jointly trained model accuracy. In order to provide a automated management of the learning process in FL on datasets that are not independently and identically distributed (non-iid), we propose a Multi-Arm Bandit (MAB) based method that helps the federation to select the nodes that benefits the overall model. This automated selection of the training nodes throughout each round yielded an improvement in accuracy, while decreasing network footprint.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123329283","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 capacity in a communication network is restricted by the famous Shannon-Hartley theorem, which establishes a relationship between maximum achievable capacity, channel bandwidth, and signal-to-noise ratio of the channel. The state-of-the-art in pushing the achievable capacity close to the theoretical limit revolves around coming up with ever more efficient error correction algorithms combined with assigning the proper modulation and encoding scheme to match the conditions of the spectrum at any given point in time. In cable broadband networks, which operate under the DOCSIS protocol, a Profile Management Application (PMA) system uses telemetry collected from cable modems and cable modem termination systems (CMTSs) to dynamically assign DOCSIS profiles that constitute a combination of Forward Error Correction (FEC) configuration, a Quadrature Amplitude Modulation (QAM) level, and other protocol-based configurations. The objective behind this dynamic assignment is twofold: maximizing capacity and keeping the uncorrectable error rate at a minimal level. The current PMA implementation, adopts a rule-based approach, where pre-defined thresholds govern the decisions for adjusting the profiles. This approach, while proven to be successful, limits opportunities to fully realize optimal DOCSIS configurations to bring system performance closer to the Shannon limit. Through a reinforcement learning (RL) implementation of PMA, it is possible to substitute the pre-defined rules for a system that learns to select the optimal configuration at each decision point, based on past outcomes and potential future rewards. In this paper, we focus on designing an RL-based PMA system to manage DOCSIS 3.0 upstream configurations.
{"title":"A Reinforcement Learning Framework for Optimizing Throughput in DOCSIS Networks","authors":"K. Dugan, Maher Harb, D. Rice","doi":"10.1145/3472735.3473389","DOIUrl":"https://doi.org/10.1145/3472735.3473389","url":null,"abstract":"The capacity in a communication network is restricted by the famous Shannon-Hartley theorem, which establishes a relationship between maximum achievable capacity, channel bandwidth, and signal-to-noise ratio of the channel. The state-of-the-art in pushing the achievable capacity close to the theoretical limit revolves around coming up with ever more efficient error correction algorithms combined with assigning the proper modulation and encoding scheme to match the conditions of the spectrum at any given point in time. In cable broadband networks, which operate under the DOCSIS protocol, a Profile Management Application (PMA) system uses telemetry collected from cable modems and cable modem termination systems (CMTSs) to dynamically assign DOCSIS profiles that constitute a combination of Forward Error Correction (FEC) configuration, a Quadrature Amplitude Modulation (QAM) level, and other protocol-based configurations. The objective behind this dynamic assignment is twofold: maximizing capacity and keeping the uncorrectable error rate at a minimal level. The current PMA implementation, adopts a rule-based approach, where pre-defined thresholds govern the decisions for adjusting the profiles. This approach, while proven to be successful, limits opportunities to fully realize optimal DOCSIS configurations to bring system performance closer to the Shannon limit. Through a reinforcement learning (RL) implementation of PMA, it is possible to substitute the pre-defined rules for a system that learns to select the optimal configuration at each decision point, based on past outcomes and potential future rewards. In this paper, we focus on designing an RL-based PMA system to manage DOCSIS 3.0 upstream configurations.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128153519","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}
R. Boutaba, Nashid Shahriar, M. A. Salahuddin, Samir Chowdhury, Niloy Saha, Alexander James
The 5th Generation (5G) mobile networks support a wide range of services that impose diverse and stringent QoS requirements. This will be further exacerbated with the evolution towards 6th Generation mobile networks. Inevitably, 5G and beyond mobile networks must provide stricter, differentiated QoS guarantees to meet the increasing demands of future applications, which cannot be satisfied with traditional human-in-the-loop service orchestration and network management approaches. In this paper, we lay out our vision for closed-loop service orchestration and network management of 5G and beyond mobile networks. We extend the MAPE (i.e., monitor, analyze, plan, and execute) control loop to facilitate closed-loop automation, and discuss the quintessential role of Artificial Intelligence/Machine Learning in its realization. We also instigate open research challenges for closed-loop automation of 5G and beyond mobile networks.
{"title":"AI-driven Closed-loop Automation in 5G and beyond Mobile Networks","authors":"R. Boutaba, Nashid Shahriar, M. A. Salahuddin, Samir Chowdhury, Niloy Saha, Alexander James","doi":"10.1145/3472735.3474458","DOIUrl":"https://doi.org/10.1145/3472735.3474458","url":null,"abstract":"The 5th Generation (5G) mobile networks support a wide range of services that impose diverse and stringent QoS requirements. This will be further exacerbated with the evolution towards 6th Generation mobile networks. Inevitably, 5G and beyond mobile networks must provide stricter, differentiated QoS guarantees to meet the increasing demands of future applications, which cannot be satisfied with traditional human-in-the-loop service orchestration and network management approaches. In this paper, we lay out our vision for closed-loop service orchestration and network management of 5G and beyond mobile networks. We extend the MAPE (i.e., monitor, analyze, plan, and execute) control loop to facilitate closed-loop automation, and discuss the quintessential role of Artificial Intelligence/Machine Learning in its realization. We also instigate open research challenges for closed-loop automation of 5G and beyond mobile networks.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124654207","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}
Time-Sensitive Networking (TSN) is designed for real-time applications, usually pertaining to a set of Time-Triggered (TT) data flows. TT traffic generally requires low packet loss and guaranteed upper bounds on end-to-end delay. To guarantee the end-to-end delay bounds, TSN uses Time-Aware Shaper (TAS) to provide deterministic service to TT flows. Each frame of TT traffic is scheduled a specific time slot at each switch for its transmission. Several factors may influence frame transmissions, which then impact the scheduling in the whole network. These factors may cause frames sent in wrong time slots, namely misbehaviors. To mitigate the occurrence of misbehaviors, we need to find proper scheduling for the whole network. In our research, we use a reinforcement-learning model, which is called Deep Deterministic Policy Gradient (DDPG), to find the suitable scheduling. DDPG is used to model the uncertainty caused by the transmission-influencing factors such as time-synchronization errors. Compared with the state of the art, our approach using DDPG significantly decreases the number of misbehaviors in TSN scenarios studied and improves the delay performance of the network.
{"title":"Mitigation of Scheduling Violations in Time-Sensitive Networking using Deep Deterministic Policy Gradient","authors":"Boyang Zhou, Liang Cheng","doi":"10.1145/3472735.3473385","DOIUrl":"https://doi.org/10.1145/3472735.3473385","url":null,"abstract":"Time-Sensitive Networking (TSN) is designed for real-time applications, usually pertaining to a set of Time-Triggered (TT) data flows. TT traffic generally requires low packet loss and guaranteed upper bounds on end-to-end delay. To guarantee the end-to-end delay bounds, TSN uses Time-Aware Shaper (TAS) to provide deterministic service to TT flows. Each frame of TT traffic is scheduled a specific time slot at each switch for its transmission. Several factors may influence frame transmissions, which then impact the scheduling in the whole network. These factors may cause frames sent in wrong time slots, namely misbehaviors. To mitigate the occurrence of misbehaviors, we need to find proper scheduling for the whole network. In our research, we use a reinforcement-learning model, which is called Deep Deterministic Policy Gradient (DDPG), to find the suitable scheduling. DDPG is used to model the uncertainty caused by the transmission-influencing factors such as time-synchronization errors. Compared with the state of the art, our approach using DDPG significantly decreases the number of misbehaviors in TSN scenarios studied and improves the delay performance of the network.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131327301","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}
Increasing complexity in management of immense number of network elements and their dynamically changing environment necessitates machine learning based recommendation models to guide human experts in setting appropriate network configurations to sustain end-user Quality of Experience (QoE). In this paper, we present and demonstrate a generative Conditional Variational AutoEncoder (CVAE)-based technique to reconstruct realistic underlying QoE factors together with improvement suggestions in a video streaming use case. Based on our experiment setting consisting of a set of what-if scenarios, our approach pinpointed the potential required changes on the QoE factors to improve the estimated video Mean Opinion Scores (MOS).
{"title":"Recommending Changes on QoE Factors with Conditional Variational AutoEncoder","authors":"Selim Ickin","doi":"10.1145/3472735.3473387","DOIUrl":"https://doi.org/10.1145/3472735.3473387","url":null,"abstract":"Increasing complexity in management of immense number of network elements and their dynamically changing environment necessitates machine learning based recommendation models to guide human experts in setting appropriate network configurations to sustain end-user Quality of Experience (QoE). In this paper, we present and demonstrate a generative Conditional Variational AutoEncoder (CVAE)-based technique to reconstruct realistic underlying QoE factors together with improvement suggestions in a video streaming use case. Based on our experiment setting consisting of a set of what-if scenarios, our approach pinpointed the potential required changes on the QoE factors to improve the estimated video Mean Opinion Scores (MOS).","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125029946","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}
We present an approach that uses Reinforcement Learning (RL) with the Random Neural Network (RNN) acting as an adaptive critic, to route traffic in a SDN network, so as to minimize a composite Goal function that includes both packet delay and energy consumption per packet. We directly measure the traffic dependent energy consumption characeristics of the hardware that we use (including energy expended per packet) so as to parametrize the Goal function. The RL based algorithm with the RNN is implemented in a SDN controller that manages a multi-hop network which assigns service requests to specific servers so as to minimize the desired Goal. The overall system's performance is evaluated through experimental measurements of packet delay and energy consumption under different traffic load values, demonstrating the effectiveness of the proposed approach.
{"title":"Reinforcement Learning and Energy-Aware Routing","authors":"Piotr Fröhlich, E. Gelenbe, M. Nowak","doi":"10.1145/3472735.3473390","DOIUrl":"https://doi.org/10.1145/3472735.3473390","url":null,"abstract":"We present an approach that uses Reinforcement Learning (RL) with the Random Neural Network (RNN) acting as an adaptive critic, to route traffic in a SDN network, so as to minimize a composite Goal function that includes both packet delay and energy consumption per packet. We directly measure the traffic dependent energy consumption characeristics of the hardware that we use (including energy expended per packet) so as to parametrize the Goal function. The RL based algorithm with the RNN is implemented in a SDN controller that manages a multi-hop network which assigns service requests to specific servers so as to minimize the desired Goal. The overall system's performance is evaluated through experimental measurements of packet delay and energy consumption under different traffic load values, demonstrating the effectiveness of the proposed approach.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123570652","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}
Aashish Gottipati, A. Stewart, Jiawen Song, Qianlang Chen
In this paper, we propose FedRAN, a mobile edge, federated learning system that incorporates differential privacy to improve the privacy integrity of sensitive edge information, preventing adversarial entities from exploiting the network interactions within a federated ecosystem to access private edge data, while tapping into the vast amounts of data generated from distributed endpoints. We deploy and evaluate FedRAN in a real controlled radio-frequency LTE environment, as opposed to a simulated one. We show that FedRAN's distributed model outperforms locally-constrained models on the MNIST handwritten digits dataset. Additionally, we explore a variety of differential privacy settings, in an effort, to enable a privacy preserving, large scale mobile edge computing ecosystem. To our knowledge, our work is the first evaluation of a federated learning system within a controlled radio-frequency LTE environment.
{"title":"FedRAN","authors":"Aashish Gottipati, A. Stewart, Jiawen Song, Qianlang Chen","doi":"10.1145/3472735.3473392","DOIUrl":"https://doi.org/10.1145/3472735.3473392","url":null,"abstract":"In this paper, we propose FedRAN, a mobile edge, federated learning system that incorporates differential privacy to improve the privacy integrity of sensitive edge information, preventing adversarial entities from exploiting the network interactions within a federated ecosystem to access private edge data, while tapping into the vast amounts of data generated from distributed endpoints. We deploy and evaluate FedRAN in a real controlled radio-frequency LTE environment, as opposed to a simulated one. We show that FedRAN's distributed model outperforms locally-constrained models on the MNIST handwritten digits dataset. Additionally, we explore a variety of differential privacy settings, in an effort, to enable a privacy preserving, large scale mobile edge computing ecosystem. To our knowledge, our work is the first evaluation of a federated learning system within a controlled radio-frequency LTE environment.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114266967","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}
A. Shahraki, Mahmoud Abbasi, Amirhosein Taherkordi, M. Kaosar
Network traffic classification (NTC) has attracted considerable attention in recent years. The importance of traffic classification stems from the fact that data traffic in modern networks is extremely complex and ever-evolving in different aspects, e.g. volume, velocity and variety. The inherent security requirements of Internet-based applications also highlights further the role of traffic classification. Gaining clear insights into the network traffic for performance evaluation and network planning purposes, network behavior analysis, and network management is not a trivial task. Fortunately, NTC is a promising technique to gain valuable insights into the behavior of the network, and consequently improve the network operations. In this paper, we provide a method based on deep ensemble learning to classify the network traffic in communication systems and networks. More specifically, the proposed method combines a set of Convolutional Neural Network (CNN) models into an ensemble of classifiers. The outputs of the models are then combined to generate the final prediction. The results of performance evaluation show that the proposed method provides an average accuracy rate of 98% for the classification of traffic (e.g., FTP-DATA, MAIL, etc.) in the Cambridge Internet traffic dataset.
{"title":"Internet Traffic Classification Using an Ensemble of Deep Convolutional Neural Networks","authors":"A. Shahraki, Mahmoud Abbasi, Amirhosein Taherkordi, M. Kaosar","doi":"10.1145/3472735.3473386","DOIUrl":"https://doi.org/10.1145/3472735.3473386","url":null,"abstract":"Network traffic classification (NTC) has attracted considerable attention in recent years. The importance of traffic classification stems from the fact that data traffic in modern networks is extremely complex and ever-evolving in different aspects, e.g. volume, velocity and variety. The inherent security requirements of Internet-based applications also highlights further the role of traffic classification. Gaining clear insights into the network traffic for performance evaluation and network planning purposes, network behavior analysis, and network management is not a trivial task. Fortunately, NTC is a promising technique to gain valuable insights into the behavior of the network, and consequently improve the network operations. In this paper, we provide a method based on deep ensemble learning to classify the network traffic in communication systems and networks. More specifically, the proposed method combines a set of Convolutional Neural Network (CNN) models into an ensemble of classifiers. The outputs of the models are then combined to generate the final prediction. The results of performance evaluation show that the proposed method provides an average accuracy rate of 98% for the classification of traffic (e.g., FTP-DATA, MAIL, etc.) in the Cambridge Internet traffic dataset.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132699613","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}
Bingzhe Liu, Kuan-Yen Chou, Pramod A. Jamkhedkar, M. B. Anwer, R. Sinha, K. Oikonomou, M. Caesar, Brighten Godfrey
Managing service provider infrastructures (SPI) is ever more challenging with increasing scale and complexity. Network and container orchestration systems alleviate some manual tasks, but they are generally narrow solutions, with controllers for specific subsystems that do not coordinate on high-level goals, and fall far short of automating the full range of tasks that engineers face day to day. We seek to highlight the need for "practical automation" to manage SPIs. Via realistic examples, we argue that practical automation should provide cross-controller coordination, and should work within the reality that many tasks will involve humans. We describe a proof-of-concept system that leverages AI planning to synthesize management steps to move the system towards a goal state. A preliminary implementation shows that our approach can accurately generate plans for complex management tasks, while scalability and modeling diverse controllers remain as future challenges.
{"title":"Practical Automation for Management Planes of Service Provider Infrastructure","authors":"Bingzhe Liu, Kuan-Yen Chou, Pramod A. Jamkhedkar, M. B. Anwer, R. Sinha, K. Oikonomou, M. Caesar, Brighten Godfrey","doi":"10.1145/3472735.3473391","DOIUrl":"https://doi.org/10.1145/3472735.3473391","url":null,"abstract":"Managing service provider infrastructures (SPI) is ever more challenging with increasing scale and complexity. Network and container orchestration systems alleviate some manual tasks, but they are generally narrow solutions, with controllers for specific subsystems that do not coordinate on high-level goals, and fall far short of automating the full range of tasks that engineers face day to day. We seek to highlight the need for \"practical automation\" to manage SPIs. Via realistic examples, we argue that practical automation should provide cross-controller coordination, and should work within the reality that many tasks will involve humans. We describe a proof-of-concept system that leverages AI planning to synthesize management steps to move the system towards a goal state. A preliminary implementation shows that our approach can accurately generate plans for complex management tasks, while scalability and modeling diverse controllers remain as future challenges.","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131926634","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}
{"title":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","authors":"","doi":"10.1145/3472735","DOIUrl":"https://doi.org/10.1145/3472735","url":null,"abstract":"","PeriodicalId":130203,"journal":{"name":"Proceedings of the 4th FlexNets Workshop on Flexible Networks Artificial Intelligence Supported Network Flexibility and Agility","volume":"27 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120910403","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：