Pub Date : 2022-10-01DOI: 10.1109/FNWF55208.2022.00048
Rebeca L. Estrada, Víctor Asanza, Danny Torres, Irving Valeriano, Daniel Alvarado
Data centers consume a large amount of energy to meet the increasing demand for IT infrastructure and software due to the IT equipment and cooling infrastructure involved. Therefore, it is necessary to have energy consumption control strategies for DC computer equipment that will allow infrastructure upgrades to reduce energy consumption and to meet the requirement of Green IT. In this way, energy consumption is reduced and the use of technological resources can be optimized. In this paper, we propose to evaluate several traditional Machine Learning algorithms as prediction models using three different temporal windows (i.e. minute, hour and day) taking into account several features such as voltage, energy, frequency, current, power, power factor, and temperature. A comparison of the root square mean error (RMSE) during the validation stage is carried out in order to select the most appropriate algorithm for each time window. In addition, running times are calculated to determine the feasibility of the selected algorithms. Moreover, the suitable predictive model can be the key to the ensure a fair distribution of the workload among the different servers in a Datacenter.
{"title":"Comparison of Traditional ML Algorithms for Energy Consumption Prediction Models","authors":"Rebeca L. Estrada, Víctor Asanza, Danny Torres, Irving Valeriano, Daniel Alvarado","doi":"10.1109/FNWF55208.2022.00048","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00048","url":null,"abstract":"Data centers consume a large amount of energy to meet the increasing demand for IT infrastructure and software due to the IT equipment and cooling infrastructure involved. Therefore, it is necessary to have energy consumption control strategies for DC computer equipment that will allow infrastructure upgrades to reduce energy consumption and to meet the requirement of Green IT. In this way, energy consumption is reduced and the use of technological resources can be optimized. In this paper, we propose to evaluate several traditional Machine Learning algorithms as prediction models using three different temporal windows (i.e. minute, hour and day) taking into account several features such as voltage, energy, frequency, current, power, power factor, and temperature. A comparison of the root square mean error (RMSE) during the validation stage is carried out in order to select the most appropriate algorithm for each time window. In addition, running times are calculated to determine the feasibility of the selected algorithms. Moreover, the suitable predictive model can be the key to the ensure a fair distribution of the workload among the different servers in a Datacenter.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115437977","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00057
Dylan Cirimelli-Low, J. Garcia-Luna-Aceves
The Scheduling with Interference Removal Established Network-Wide (SIREN) protocol is introduced that eliminates multiple access interference (MAI) in multi-hop networks. SIREN ensures that the receivers of a primary transmitter assigned a transmission turn have no MAI, and allows one or multiple concurrent secondary transmitters to transmit during the same transmission turn, as long as no MAI is created. Simulation experiments in ns-3 are used to illustrate the advantages of SIREN over IEEE 802.11b in terms of goodput, fairness, and delays.
{"title":"Distributed Channel Access with no Multiple Access Interference in Multi-Hop Wireless Networks","authors":"Dylan Cirimelli-Low, J. Garcia-Luna-Aceves","doi":"10.1109/FNWF55208.2022.00057","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00057","url":null,"abstract":"The Scheduling with Interference Removal Established Network-Wide (SIREN) protocol is introduced that eliminates multiple access interference (MAI) in multi-hop networks. SIREN ensures that the receivers of a primary transmitter assigned a transmission turn have no MAI, and allows one or multiple concurrent secondary transmitters to transmit during the same transmission turn, as long as no MAI is created. Simulation experiments in ns-3 are used to illustrate the advantages of SIREN over IEEE 802.11b in terms of goodput, fairness, and delays.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124033075","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00080
Mohammed Farouk Nakmouche, D. Deslandes, G. Gagnon
In this paper, a machine learning-assisted approach is presented for the design of a 3D Printed Metallic Ridge Gap Waveguide-Based array MIMO antenna for inter-cube satellite (CubeSat) communication. The designed antenna has a total dimension of $boldsymbol{15.5 times 10.5 times 5.78} mathbf{mm}^3$ and is based on aluminum alloy powder (AlSi10Mg) with a conductivity of $boldsymbol{2.04times 10^{7}} mathbf{S}/mathbf{m}$. The antenna exhibits wideband operation in V-band (59.3-66.6 GHz) with a stable realized gain of 10.5 dBi and radiation efficiency of 90% over the operating frequency.
{"title":"Machine Learning Aided Design of Sub-Array MIMO Antennas for CubeSats Based on 3D Printed Metallic Ridge Gap Waveguides","authors":"Mohammed Farouk Nakmouche, D. Deslandes, G. Gagnon","doi":"10.1109/FNWF55208.2022.00080","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00080","url":null,"abstract":"In this paper, a machine learning-assisted approach is presented for the design of a 3D Printed Metallic Ridge Gap Waveguide-Based array MIMO antenna for inter-cube satellite (CubeSat) communication. The designed antenna has a total dimension of $boldsymbol{15.5 times 10.5 times 5.78} mathbf{mm}^3$ and is based on aluminum alloy powder (AlSi10Mg) with a conductivity of $boldsymbol{2.04times 10^{7}} mathbf{S}/mathbf{m}$. The antenna exhibits wideband operation in V-band (59.3-66.6 GHz) with a stable realized gain of 10.5 dBi and radiation efficiency of 90% over the operating frequency.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114530932","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00017
Marta Miranda Dopico, Irene Saco López, Ignacio Benito Frontelo, Jaime Jesús Ruiz Alonso
5G deployments are proving to have an impact beyond a simple technological change in mobile networks to become a technology that will affect the economy, industry and society alike in a cross-cutting manner. It is a time of significant change where connectivity will become increasingly seamless in cross-border environments and where the design of applications, which rely on low latency and high bandwidth, will become realities. In the case of the automotive sector, it will support the deployment of new autonomous mobility functionalities in the near future. This paper aims to provide an overview of the 5G network deployment and the conclusions obtained after the analysis of the results of two of the use cases carried out in the Spanish-Portuguese cross-border corridor in the framework of the 5G MOBIX Project. The advantages of 5G technology have been demonstrated through the execution of cooperative automated operation and remote driving use cases.
{"title":"5G-MOBIX: The Spain - Portugal Cross - Border Corridor, results of 5G application in shuttle vehicle use cases","authors":"Marta Miranda Dopico, Irene Saco López, Ignacio Benito Frontelo, Jaime Jesús Ruiz Alonso","doi":"10.1109/FNWF55208.2022.00017","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00017","url":null,"abstract":"5G deployments are proving to have an impact beyond a simple technological change in mobile networks to become a technology that will affect the economy, industry and society alike in a cross-cutting manner. It is a time of significant change where connectivity will become increasingly seamless in cross-border environments and where the design of applications, which rely on low latency and high bandwidth, will become realities. In the case of the automotive sector, it will support the deployment of new autonomous mobility functionalities in the near future. This paper aims to provide an overview of the 5G network deployment and the conclusions obtained after the analysis of the results of two of the use cases carried out in the Spanish-Portuguese cross-border corridor in the framework of the 5G MOBIX Project. The advantages of 5G technology have been demonstrated through the execution of cooperative automated operation and remote driving use cases.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121573295","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00111
Shannon K. Gallagher, Austin Whisnant, A. Hristozov, Amit Vasudevan
The next generation of communication networks promises an exponential growth in number, low latency, and heterogeneity of devices. Consequently, we need to be able to trust devices and device-to-device interactions in sections of a 5G+ network, commonly known as slices. Devices must be willing and able to remotely attest to their trustworthiness. Although trust has previously been based upon deterministic and hardware-driven protocols, over recent decades it has become more common to incorporate artificial intelligence and machine learning (AI/ML) modeling to supplement those protocols. In this paper we review some key aspects of models used for trust of devices, including important criteria for model selection, model structure and inputs, and advantages and disadvantages of these models. We also examine how these AI/ML models intersect with 5G network architecture. Following that, we discuss what sort of data are expected for these trust models. Finally, we discuss next steps for AI/ML models for remote attestation in 5G+ networks.
{"title":"Reviewing the role of machine learning and artificial intelligence for remote attestation in 5G+ networks","authors":"Shannon K. Gallagher, Austin Whisnant, A. Hristozov, Amit Vasudevan","doi":"10.1109/FNWF55208.2022.00111","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00111","url":null,"abstract":"The next generation of communication networks promises an exponential growth in number, low latency, and heterogeneity of devices. Consequently, we need to be able to trust devices and device-to-device interactions in sections of a 5G+ network, commonly known as slices. Devices must be willing and able to remotely attest to their trustworthiness. Although trust has previously been based upon deterministic and hardware-driven protocols, over recent decades it has become more common to incorporate artificial intelligence and machine learning (AI/ML) modeling to supplement those protocols. In this paper we review some key aspects of models used for trust of devices, including important criteria for model selection, model structure and inputs, and advantages and disadvantages of these models. We also examine how these AI/ML models intersect with 5G network architecture. Following that, we discuss what sort of data are expected for these trust models. Finally, we discuss next steps for AI/ML models for remote attestation in 5G+ networks.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121629569","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00018
Vassiliki Nikolopoulou, Dan Mandoc, Farid Bazizi, Michaela Klöcker, Sébastien Tardif, Bernd Holfeld, Guillaume Jornod, Nazih Salhab, M. Berbineau, S. Gogos
Future Railway Mobile Communication System (FRMCS) will be the 5G worldwide standard for railway operational communications, designed by the International Union of Railways (UIC), in close cooperation with the railways stakeholders. The EU-funded Horizon 2020 5G for Connected and Automated Mobility (CAM) project 5GRAIL, as part of the FRMCS readiness initiatives, aims to: i) develop the Telecom On-board Prototype (TOBA box), ii) validate the first set of specifications by developing and testing On-board and application prototypes, in lab and field environments and iii) provide feedback and lessons-learned to standardization organizations for consideration in updates of the specifications. In this context, this paper aims to shed some lights on the project and discuss its preliminary results.
{"title":"5GRAIL paves the way to the Future Railway Mobile Communication System Introduction","authors":"Vassiliki Nikolopoulou, Dan Mandoc, Farid Bazizi, Michaela Klöcker, Sébastien Tardif, Bernd Holfeld, Guillaume Jornod, Nazih Salhab, M. Berbineau, S. Gogos","doi":"10.1109/FNWF55208.2022.00018","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00018","url":null,"abstract":"Future Railway Mobile Communication System (FRMCS) will be the 5G worldwide standard for railway operational communications, designed by the International Union of Railways (UIC), in close cooperation with the railways stakeholders. The EU-funded Horizon 2020 5G for Connected and Automated Mobility (CAM) project 5GRAIL, as part of the FRMCS readiness initiatives, aims to: i) develop the Telecom On-board Prototype (TOBA box), ii) validate the first set of specifications by developing and testing On-board and application prototypes, in lab and field environments and iii) provide feedback and lessons-learned to standardization organizations for consideration in updates of the specifications. In this context, this paper aims to shed some lights on the project and discuss its preliminary results.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131362422","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00124
V. Sathya, Lyutianyang Zhang, M. Yavuz
The requirements in terms of security, packet drop, and reliability (i.e., jitter) for the applications such as Augmented Reality/Virtual Reality (AR/VR), Industrial IoT (IIoT) have become more demanding and subsequently, motivate the need for private 5G deployment. In general, 5G NR base stations (gNB) can be either deployed in integrated mode (PHY, MAC, and PDCP layers in one node) or split architecture mode, also known as O-RAN (lower PHY Radio Unit (RU), and the remaining layers from higher MAC to Packet Data Convergence Protocol (PDCP) at Base Band Unit (BBU)). This paper showcases the first private 5G NR Standalone deployment with O-RAN architecture on the shared spectrum i.e., Citizens Broadband Radio Service (CBRS) frequency from 3.55 to 3.7 GHz. Since many private 5G deployments (e.g., warehouses with IoT devices such as IP cameras) are uplink heavy due to the nature of the traffic, we configure the UL-heavy 5G NR network and study the reliability of the system in the loaded and unloaded scenarios for both static and mobile environments.
增强现实/虚拟现实(AR/VR)、工业物联网(IIoT)等应用在安全性、丢包和可靠性(即抖动)方面的要求变得更加苛刻，从而激发了对私有5G部署的需求。一般来说，5G NR基站(gNB)可以采用集成模式(PHY、MAC和PDCP层在一个节点上)或拆分架构模式(也称为O-RAN(较低的PHY Radio Unit (RU)，而从较高的MAC到分组数据融合协议(PDCP)的其余层在基带单元(BBU))部署。本文展示了在共享频谱(即3.55至3.7 GHz的公民宽带无线电服务(CBRS)频率)上采用O-RAN架构的第一个私有5G NR独立部署。由于许多私有5G部署(例如，带有IP摄像机等物联网设备的仓库)由于流量的性质而需要重上行链路，因此我们配置了重ul的5G NR网络，并研究了系统在静态和移动环境下加载和卸载场景下的可靠性。
{"title":"Towards Private 5G O-RAN Implementation: Performance and Business Validation","authors":"V. Sathya, Lyutianyang Zhang, M. Yavuz","doi":"10.1109/FNWF55208.2022.00124","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00124","url":null,"abstract":"The requirements in terms of security, packet drop, and reliability (i.e., jitter) for the applications such as Augmented Reality/Virtual Reality (AR/VR), Industrial IoT (IIoT) have become more demanding and subsequently, motivate the need for private 5G deployment. In general, 5G NR base stations (gNB) can be either deployed in integrated mode (PHY, MAC, and PDCP layers in one node) or split architecture mode, also known as O-RAN (lower PHY Radio Unit (RU), and the remaining layers from higher MAC to Packet Data Convergence Protocol (PDCP) at Base Band Unit (BBU)). This paper showcases the first private 5G NR Standalone deployment with O-RAN architecture on the shared spectrum i.e., Citizens Broadband Radio Service (CBRS) frequency from 3.55 to 3.7 GHz. Since many private 5G deployments (e.g., warehouses with IoT devices such as IP cameras) are uplink heavy due to the nature of the traffic, we configure the UL-heavy 5G NR network and study the reliability of the system in the loaded and unloaded scenarios for both static and mobile environments.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130172178","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00065
Geoffrey Chollon, D. Ayed, Rodrigo Asensio Garriga, Alejandro Molina Zarca, A. Gómez-Skarmeta, M. Christopoulou, Wissem Soussi, Gürkan Gür, U. Herzog
This paper presents a security management framework driven by Zero-Touch Network and Service Management (ZSM) paradigm and embedded in the High-Level Architecture (HLA) developed in the INSPIRE-5Gplus project. This project work also included design and implementation of different smart 5G security methods and techniques that are essential for achieving security management in future networks. Moreover, the paper provides a summary of lessons learned and guidelines gathered during the practical validation activities for bringing closed loop and smart security management into Beyond 5G systems. Finally we discuss the key challenges and future work needed to enable integrating closed-loop security management in future networks.
{"title":"ETSI ZSM Driven Security Management in Future Networks","authors":"Geoffrey Chollon, D. Ayed, Rodrigo Asensio Garriga, Alejandro Molina Zarca, A. Gómez-Skarmeta, M. Christopoulou, Wissem Soussi, Gürkan Gür, U. Herzog","doi":"10.1109/FNWF55208.2022.00065","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00065","url":null,"abstract":"This paper presents a security management framework driven by Zero-Touch Network and Service Management (ZSM) paradigm and embedded in the High-Level Architecture (HLA) developed in the INSPIRE-5Gplus project. This project work also included design and implementation of different smart 5G security methods and techniques that are essential for achieving security management in future networks. Moreover, the paper provides a summary of lessons learned and guidelines gathered during the practical validation activities for bringing closed loop and smart security management into Beyond 5G systems. Finally we discuss the key challenges and future work needed to enable integrating closed-loop security management in future networks.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133252825","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00114
Jose Alvaro Fernandez-Carrasco, Lander Segurola-Gil, Francesco Zola, Raul Orduna Urrutia
5G ecosystem is shaping the future of communication networks enabling innovation and digital transformation not only for individual users but also for companies, industries, and communities. In this scenario, technologies such as Software Defined Networking (SDN) represent a solution for telecommunications providers to create agile, scalable, efficient platforms capable of meeting the requirements in the 5G ecosystem. However, as network environments and systems become increasingly complex, both in terms of size and dynamic behavior, the number of vulnerabilities in them can be very high. In addition, hackers are continuously improving intrusion methods, which are becoming more difficult to detect. For this reason, in this study, we deploy a system based on a Reinforcement Learning (RL) agent capable of applying different countermeasures to defend a network against intrusion and DDoS attacks using SDN. The approach is drawn like a serious game in which a defender and an attacker carry out actions based on the observations they get from the environment, i.e., network current status. In this study, defenders and attackers are trained using the Deep Q-Learning (DQN) algorithm with some variations, like Prioritized Replay, Dueling, and Double DQN, comparing their results in order to get the best strategy for attack mitigation. The results of this paper show that RL algorithms can be successfully used to create more versatile agents able of interpreting and adapting themselves to different situations and so run the best countermeasure to protect the network. According to the results, it is also shown that the Complete strategy, which includes the three DQN variations analyzed, is the one that allows obtaining agents with the best decision making to respond to attacks.
{"title":"Security and 5G: Attack mitigation using Reinforcement Learning in SDN networks","authors":"Jose Alvaro Fernandez-Carrasco, Lander Segurola-Gil, Francesco Zola, Raul Orduna Urrutia","doi":"10.1109/FNWF55208.2022.00114","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00114","url":null,"abstract":"5G ecosystem is shaping the future of communication networks enabling innovation and digital transformation not only for individual users but also for companies, industries, and communities. In this scenario, technologies such as Software Defined Networking (SDN) represent a solution for telecommunications providers to create agile, scalable, efficient platforms capable of meeting the requirements in the 5G ecosystem. However, as network environments and systems become increasingly complex, both in terms of size and dynamic behavior, the number of vulnerabilities in them can be very high. In addition, hackers are continuously improving intrusion methods, which are becoming more difficult to detect. For this reason, in this study, we deploy a system based on a Reinforcement Learning (RL) agent capable of applying different countermeasures to defend a network against intrusion and DDoS attacks using SDN. The approach is drawn like a serious game in which a defender and an attacker carry out actions based on the observations they get from the environment, i.e., network current status. In this study, defenders and attackers are trained using the Deep Q-Learning (DQN) algorithm with some variations, like Prioritized Replay, Dueling, and Double DQN, comparing their results in order to get the best strategy for attack mitigation. The results of this paper show that RL algorithms can be successfully used to create more versatile agents able of interpreting and adapting themselves to different situations and so run the best countermeasure to protect the network. According to the results, it is also shown that the Complete strategy, which includes the three DQN variations analyzed, is the one that allows obtaining agents with the best decision making to respond to attacks.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133742909","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 : 2022-10-01DOI: 10.1109/FNWF55208.2022.00073
S. Kukliński
Network slicing management and orchestration typically use centralised OSS/BSS combined with ETSI MANO orchestrator. In [6] there has been proposed the In-Slice Management (ISM) concept in which network slicing system management is autonomic, distributed, and slice management is a part of the Network Slice (NS). There were published several papers that explored this topic. Still, none provided implementation details and issues related to unified NS reconfiguration, including NS run-time orchestration combined with classical management and the impact of NS reconfiguration on IMS components. The paper addresses these issues by defining ISM services and proposing, common for all ISM services, cooperative monitoring and actuating sublayers to handle reconfigurations smoothly. The mutual impact of ISM management services responsible for performance, fault, and security management is also addressed. The presented concept can be a basis for a generic ISM template that can be adapted to many NS types with marginal efforts.
{"title":"In-Slice Management Decomposition and Implementation Issues","authors":"S. Kukliński","doi":"10.1109/FNWF55208.2022.00073","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00073","url":null,"abstract":"Network slicing management and orchestration typically use centralised OSS/BSS combined with ETSI MANO orchestrator. In [6] there has been proposed the In-Slice Management (ISM) concept in which network slicing system management is autonomic, distributed, and slice management is a part of the Network Slice (NS). There were published several papers that explored this topic. Still, none provided implementation details and issues related to unified NS reconfiguration, including NS run-time orchestration combined with classical management and the impact of NS reconfiguration on IMS components. The paper addresses these issues by defining ISM services and proposing, common for all ISM services, cooperative monitoring and actuating sublayers to handle reconfigurations smoothly. The mutual impact of ISM management services responsible for performance, fault, and security management is also addressed. The presented concept can be a basis for a generic ISM template that can be adapted to many NS types with marginal efforts.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124239076","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：