Pub Date : 2023-06-19DOI: 10.1109/NetSoft57336.2023.10175456
Ákos Leiter, Pál Böõsy, Milán Kis, L. Bokor
The next-generation mobile networks are expected to provide advanced services, which require the network to be more scalable and resilient. A possible approach to solve this would be a cloud-native network, upon which containerized network functions could be deployed: this is why Kubernetes is gaining attention among network software vendors and service providers. Kubernetes has become the de-facto industry standard for orchestrating containerized resources at real-life scales. However, Kubernetes ’s abilities might seem to be limited. Currently, it lacks the toolset for advanced L2/L3 level networking, which would be essential, for example, in the case of IPv6-based mobility management. Furthermore, many types of software architectures can be envisioned on the top of Kubernetes which may have different impacts on performance. This paper examines different microservice approaches in the context of Mobile IPv6 and Proxy Mobile IPv6, including their service automation capabilities. We evaluate them from functional and performance perspectives and provide statements about their usability in mobile networks.
{"title":"Performance costs for IPv6-based mobility management on the top of Kubernetes","authors":"Ákos Leiter, Pál Böõsy, Milán Kis, L. Bokor","doi":"10.1109/NetSoft57336.2023.10175456","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175456","url":null,"abstract":"The next-generation mobile networks are expected to provide advanced services, which require the network to be more scalable and resilient. A possible approach to solve this would be a cloud-native network, upon which containerized network functions could be deployed: this is why Kubernetes is gaining attention among network software vendors and service providers. Kubernetes has become the de-facto industry standard for orchestrating containerized resources at real-life scales. However, Kubernetes ’s abilities might seem to be limited. Currently, it lacks the toolset for advanced L2/L3 level networking, which would be essential, for example, in the case of IPv6-based mobility management. Furthermore, many types of software architectures can be envisioned on the top of Kubernetes which may have different impacts on performance. This paper examines different microservice approaches in the context of Mobile IPv6 and Proxy Mobile IPv6, including their service automation capabilities. We evaluate them from functional and performance perspectives and provide statements about their usability in mobile networks.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127120033","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 : 2023-06-19DOI: 10.1109/NetSoft57336.2023.10175482
E. S. Borges, Vitor Berger Bonella, Abraão Jesus Dos Santos, Gabriel Tetzner Menegueti, C. Dominicini, M. Martinello
This paper presents a scalable and efficient solution for secure network design that involves the selection and verification of network paths. The proposed approach addresses the challenge of extending compliance policies to cover path-aware programmable networks by decoupling the routing/forwarding mechanisms from the Proof-of-Transit (PoT) implementation. Thus, two concepts are bounded: i) a source routing mechanism based on a fixed routeID representing a unique identifier per path, which serves as a key for the PoT lookup table; ii) the “in situ” that allows to collect telemetry information in the packet while the packet traverses a path. The former enables path selection with policy at the edge, while the later allows to perform path verification without extra probe-traffic. A P4 programmable language prototype demonstrates the effectiveness of this approach to protect against deviation attacks with low overhead. The results show a significant reduction in network’s forwarding state for fat-tree topologies depending on the workload per path (flows/path).
{"title":"In-situ Proof-of-Transit for Path-Aware Programmable Networks","authors":"E. S. Borges, Vitor Berger Bonella, Abraão Jesus Dos Santos, Gabriel Tetzner Menegueti, C. Dominicini, M. Martinello","doi":"10.1109/NetSoft57336.2023.10175482","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175482","url":null,"abstract":"This paper presents a scalable and efficient solution for secure network design that involves the selection and verification of network paths. The proposed approach addresses the challenge of extending compliance policies to cover path-aware programmable networks by decoupling the routing/forwarding mechanisms from the Proof-of-Transit (PoT) implementation. Thus, two concepts are bounded: i) a source routing mechanism based on a fixed routeID representing a unique identifier per path, which serves as a key for the PoT lookup table; ii) the “in situ” that allows to collect telemetry information in the packet while the packet traverses a path. The former enables path selection with policy at the edge, while the later allows to perform path verification without extra probe-traffic. A P4 programmable language prototype demonstrates the effectiveness of this approach to protect against deviation attacks with low overhead. The results show a significant reduction in network’s forwarding state for fat-tree topologies depending on the workload per path (flows/path).","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129982263","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 : 2023-06-19DOI: 10.1109/NetSoft57336.2023.10175424
Shwetha Vittal, Unnati Dixit, Siddhesh Pratim Sovitkar, K. Sowjanya, A. Franklin
As network slicing is the chief enabler for future Beyond 5G(B5G) and 6G networks, multiple tenants interoperate cost-effectively to provide a variety of slice services on a common physical infrastructure. However, this opens the doors to cross-slice disruptions with Man-in-the-Middle (MITM) attack which ultimately disrupts the slice services in the data plane. In this paper, we address such possible cross-network slice disruptions in a zero-trust and multi-tenant based 5G network by proposing different design techniques namely, secure communication and Artificial Intelligence (AI)-based anomaly detection to prevent them. Our experiments on a 5G testbed prototype show that in the secure communication method, Attribute-Based Encryption (ABE) provides higher security benefits in confidentiality and implicit authorization. However, symmetric encryption and integrity protection prevent cross-slice disruptions with less communication overhead, but with a weaker security level. On the other hand, with online learning and noise tolerance capabilities, AI-based Hierarchical Temporal Memory (HTM) can proactively detect the occurrences of the identified cross-slice disruptions.
{"title":"Preventing Cross Network Slice Disruptions in a Zero-Trust and Multi-Tenant Future 5G Networks","authors":"Shwetha Vittal, Unnati Dixit, Siddhesh Pratim Sovitkar, K. Sowjanya, A. Franklin","doi":"10.1109/NetSoft57336.2023.10175424","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175424","url":null,"abstract":"As network slicing is the chief enabler for future Beyond 5G(B5G) and 6G networks, multiple tenants interoperate cost-effectively to provide a variety of slice services on a common physical infrastructure. However, this opens the doors to cross-slice disruptions with Man-in-the-Middle (MITM) attack which ultimately disrupts the slice services in the data plane. In this paper, we address such possible cross-network slice disruptions in a zero-trust and multi-tenant based 5G network by proposing different design techniques namely, secure communication and Artificial Intelligence (AI)-based anomaly detection to prevent them. Our experiments on a 5G testbed prototype show that in the secure communication method, Attribute-Based Encryption (ABE) provides higher security benefits in confidentiality and implicit authorization. However, symmetric encryption and integrity protection prevent cross-slice disruptions with less communication overhead, but with a weaker security level. On the other hand, with online learning and noise tolerance capabilities, AI-based Hierarchical Temporal Memory (HTM) can proactively detect the occurrences of the identified cross-slice disruptions.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126318966","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 : 2023-06-19DOI: 10.1109/NetSoft57336.2023.10175481
Md. Tariqul Islam, Christian Esteve Rothenberg, P. Gomes
The growing popularity of eXtended Reality (XR) is being driven by technological advancements and the demand for advanced immersive digital experiences, including the vision around the metaverse. Within the XR realm, 360-degree immersive video streaming is essential for Virtual Reality (VR) adventures and experiences. The use of E2E encryption for content delivery in 360-VR streaming poses challenges for network operators, making it difficult to manage their networks and assess potential Quality of Experience (QoE) impairments, specifically in 5G and beyond networks. Therefore, we propose a Machine Learning (ML) approach for inferring 360-VR video QoE metrics from network-level encrypted traffic. Our solution uses packet-level information for feature engineering, which serves as input for the ML model to predict target QoE estimators. We evaluate our solution using real 4G and 5G drive test traces with encrypted VR traffic using HTTPS and QUIC protocols. The experimental results show that the trained ML model yields reasonable accuracy with minimal residual error in predicting target VR QoE for both HTTPS and QUIC. Network operators can use such a model to passively monitor the real-time QoE of encrypted VR video sessions and optimize network performance.
{"title":"Predicting XR Services QoE with ML: Insights from In-band Encrypted QoS Features in 360-VR","authors":"Md. Tariqul Islam, Christian Esteve Rothenberg, P. Gomes","doi":"10.1109/NetSoft57336.2023.10175481","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175481","url":null,"abstract":"The growing popularity of eXtended Reality (XR) is being driven by technological advancements and the demand for advanced immersive digital experiences, including the vision around the metaverse. Within the XR realm, 360-degree immersive video streaming is essential for Virtual Reality (VR) adventures and experiences. The use of E2E encryption for content delivery in 360-VR streaming poses challenges for network operators, making it difficult to manage their networks and assess potential Quality of Experience (QoE) impairments, specifically in 5G and beyond networks. Therefore, we propose a Machine Learning (ML) approach for inferring 360-VR video QoE metrics from network-level encrypted traffic. Our solution uses packet-level information for feature engineering, which serves as input for the ML model to predict target QoE estimators. We evaluate our solution using real 4G and 5G drive test traces with encrypted VR traffic using HTTPS and QUIC protocols. The experimental results show that the trained ML model yields reasonable accuracy with minimal residual error in predicting target VR QoE for both HTTPS and QUIC. Network operators can use such a model to passively monitor the real-time QoE of encrypted VR video sessions and optimize network performance.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126320247","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 : 2023-04-27DOI: 10.1109/NetSoft57336.2023.10175453
Anousheh Gholami, Nariman Torkzaban, J. Baras
Constant temporospatial variations in the user demand complicate the end-to-end (E2E) network slice (NS) resource provisioning beyond the limits of the existing best-effort schemes that are only effective under accurate demand forecasts for all NSs. This paper proposes a practical two-time-scale resource allocation framework for E2E network slicing under demand uncertainty. At each macro-scale instance, we assume that only the spatial probability distribution of the NS demands is available. We formulate the NSs resource allocation problem as a stochastic mixed integer program (SMIP) with the objective of minimizing the total CN and RAN resource costs. At each microscale instance, given the exact NSs demand profiles known at operation time, a linear program is solved to jointly minimize the unsupported traffic and RAN cost. We verify the effectiveness of our resource allocation scheme through numerical experiments.
{"title":"Mobile Network Slicing under Demand Uncertainty: A Stochastic Programming Approach","authors":"Anousheh Gholami, Nariman Torkzaban, J. Baras","doi":"10.1109/NetSoft57336.2023.10175453","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175453","url":null,"abstract":"Constant temporospatial variations in the user demand complicate the end-to-end (E2E) network slice (NS) resource provisioning beyond the limits of the existing best-effort schemes that are only effective under accurate demand forecasts for all NSs. This paper proposes a practical two-time-scale resource allocation framework for E2E network slicing under demand uncertainty. At each macro-scale instance, we assume that only the spatial probability distribution of the NS demands is available. We formulate the NSs resource allocation problem as a stochastic mixed integer program (SMIP) with the objective of minimizing the total CN and RAN resource costs. At each microscale instance, given the exact NSs demand profiles known at operation time, a linear program is solved to jointly minimize the unsupported traffic and RAN cost. We verify the effectiveness of our resource allocation scheme through numerical experiments.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130194089","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 : 2023-04-25DOI: 10.1109/NetSoft57336.2023.10175506
Jamila Alsayed Kassem, Li Zhong, Arie Taal, P. Grosso
Digital Twin (DT) is a prominent technology to utilise and deploy within the healthcare sector. Yet, the main challenges facing such applications are: strict health data-sharing policies, high-performance network requirements, and possible infrastructure resource limitations. In this paper, we address all the challenges by provisioning adaptive Virtual Network Functions (VNFs) to enforce security policies associated with different data-sharing scenarios. We define a Cloud-Native Network orchestrator on top of a multi-node cluster mesh infrastructure for flexible and dynamic container scheduling. The proposed framework considers the intended data-sharing use case, the policies associated, and infrastructure configurations, then provisions Service Function Chaining (SFC) and provides routing configurations accordingly with little to no human intervention. As a result, we provide an adaptive network orchestration for digital health twin use cases, that is policy-aware, requirements-aware, and resource-aware.
{"title":"Adaptive Services Function Chain Orchestration For Digital Health Twin Use Cases: Heuristic-boosted Q-Learning Approach","authors":"Jamila Alsayed Kassem, Li Zhong, Arie Taal, P. Grosso","doi":"10.1109/NetSoft57336.2023.10175506","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175506","url":null,"abstract":"Digital Twin (DT) is a prominent technology to utilise and deploy within the healthcare sector. Yet, the main challenges facing such applications are: strict health data-sharing policies, high-performance network requirements, and possible infrastructure resource limitations. In this paper, we address all the challenges by provisioning adaptive Virtual Network Functions (VNFs) to enforce security policies associated with different data-sharing scenarios. We define a Cloud-Native Network orchestrator on top of a multi-node cluster mesh infrastructure for flexible and dynamic container scheduling. The proposed framework considers the intended data-sharing use case, the policies associated, and infrastructure configurations, then provisions Service Function Chaining (SFC) and provides routing configurations accordingly with little to no human intervention. As a result, we provide an adaptive network orchestration for digital health twin use cases, that is policy-aware, requirements-aware, and resource-aware.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116519639","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 : 2023-04-11DOI: 10.1109/NetSoft57336.2023.10175407
Pham Tran Anh Quang, Jérémie Leguay, Xuan Gong, Huiying Xu
In modern SD-WAN networks, a global controller is able to steer traffic on different paths based on application requirements and global intents. However, existing solutions cannot dynamically tune the way bandwidth is shared between flows inside each network, in particular when the available capacity is uncertain due to cross traffic. In this context, we propose a global QoS (Quality of Service) policy optimization model that dynamically adjusts rate limits of applications based on their requirements to follow the evolution of network conditions. It relies on a novel cross-traffic estimator for the available bandwidth of overlay links that only exploits already available measurements. We propose a centralized local search algorithm with cross-traffic estimation and show in packet-level simulations a significant performance improvement in terms of SLA (Service Level Agreement) satisfaction. The adaptive tuning of load balancing and QoS policies based on cross-traffic estimation can improve SLA satisfaction by 40% compared to static policies.
在现代SD-WAN网络中，全局控制器能够根据应用程序需求和全局意图引导不同路径上的流量。然而，现有的解决方案不能动态地调整每个网络中的流之间共享带宽的方式，特别是当可用容量由于交叉流量而不确定时。在此背景下，我们提出了一种全局QoS (Quality of Service)策略优化模型，该模型可以根据应用的需求动态调整速率限制，以适应网络条件的演变。它依赖于一种新的交叉流量估计器，用于覆盖链路的可用带宽，该估计器仅利用已有的测量值。我们提出了一种具有交叉流量估计的集中式本地搜索算法，并在分组级模拟中显示了SLA(服务水平协议)满意度方面的显着性能改进。与静态策略相比，基于交叉流量估计的负载平衡和QoS策略的自适应调优可以将SLA满意度提高40%。
{"title":"Global QoS Policy Optimization in SD-WAN","authors":"Pham Tran Anh Quang, Jérémie Leguay, Xuan Gong, Huiying Xu","doi":"10.1109/NetSoft57336.2023.10175407","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175407","url":null,"abstract":"In modern SD-WAN networks, a global controller is able to steer traffic on different paths based on application requirements and global intents. However, existing solutions cannot dynamically tune the way bandwidth is shared between flows inside each network, in particular when the available capacity is uncertain due to cross traffic. In this context, we propose a global QoS (Quality of Service) policy optimization model that dynamically adjusts rate limits of applications based on their requirements to follow the evolution of network conditions. It relies on a novel cross-traffic estimator for the available bandwidth of overlay links that only exploits already available measurements. We propose a centralized local search algorithm with cross-traffic estimation and show in packet-level simulations a significant performance improvement in terms of SLA (Service Level Agreement) satisfaction. The adaptive tuning of load balancing and QoS policies based on cross-traffic estimation can improve SLA satisfaction by 40% compared to static policies.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672661","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}
Mission-critical systems (MCSs) have embraced new design paradigms such as service-oriented architecture (SOA) and IEEE 802.1 Time-sensitive Networking (TSN). These approaches tackle the static and closed-loop design and configuration of MCSs to address their strict performance and resilience requirements. While SOA enables the dynamic placement of critical services over virtualized hardware, TSN provides several protocols to establish deterministic communication over standard Ethernet equipment. This paper presents a prototype utilizing SOA and TSN to design flexible and fault-tolerant MCSs. It demonstrates the benefits of dynamic service migration and time-sensitive redundancy protocols to increase the resilience of MCSs against node and link failures, respectively. Moreover, it presents additional advanced functionalities like optimal service distribution and security monitoring for new TSN protocols.
{"title":"Towards Developing Resilient and Service-oriented Mission-critical Systems","authors":"Doğanalp Ergenç, Cornelia Brülhart, Mathias Fischer","doi":"10.1109/NetSoft57336.2023.10175408","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175408","url":null,"abstract":"Mission-critical systems (MCSs) have embraced new design paradigms such as service-oriented architecture (SOA) and IEEE 802.1 Time-sensitive Networking (TSN). These approaches tackle the static and closed-loop design and configuration of MCSs to address their strict performance and resilience requirements. While SOA enables the dynamic placement of critical services over virtualized hardware, TSN provides several protocols to establish deterministic communication over standard Ethernet equipment. This paper presents a prototype utilizing SOA and TSN to design flexible and fault-tolerant MCSs. It demonstrates the benefits of dynamic service migration and time-sensitive redundancy protocols to increase the resilience of MCSs against node and link failures, respectively. Moreover, it presents additional advanced functionalities like optimal service distribution and security monitoring for new TSN protocols.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"613 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124629725","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 : 2023-03-02DOI: 10.1109/NetSoft57336.2023.10175507
Kaushik Dey, Satheesh K. Perepu, P. Dasgupta, Abir Das
The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL) agents for controlling the growing portfolio of network services. Infusion of many new types of services is anticipated with future adoption of 6G networks, and sometimes these services will be defined by applications that are external to the network. An RL agent trained for managing the needs of a specific service type may not be ideal for managing a different service type without domain adaptation. We provide a simple heuristic for evaluating a measure of proximity between a new service and existing services, and show that the RL agent of the most proximal service rapidly adapts to the new service type through a well defined process of domain adaptation. Our approach enables a trained source policy to adapt to new situations with changed dynamics without retraining a new policy, thereby achieving significant computing and cost-effectiveness. Such domain adaptation techniques may soon provide a foundation for more generalized RL-based service management under the face of rapidly evolving service types.
{"title":"Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity","authors":"Kaushik Dey, Satheesh K. Perepu, P. Dasgupta, Abir Das","doi":"10.1109/NetSoft57336.2023.10175507","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175507","url":null,"abstract":"The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL) agents for controlling the growing portfolio of network services. Infusion of many new types of services is anticipated with future adoption of 6G networks, and sometimes these services will be defined by applications that are external to the network. An RL agent trained for managing the needs of a specific service type may not be ideal for managing a different service type without domain adaptation. We provide a simple heuristic for evaluating a measure of proximity between a new service and existing services, and show that the RL agent of the most proximal service rapidly adapts to the new service type through a well defined process of domain adaptation. Our approach enables a trained source policy to adapt to new situations with changed dynamics without retraining a new policy, thereby achieving significant computing and cost-effectiveness. Such domain adaptation techniques may soon provide a foundation for more generalized RL-based service management under the face of rapidly evolving service types.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116362176","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 : 2023-02-14DOI: 10.1109/NetSoft57336.2023.10175461
Jiaming Cheng, Duong Thuy Anh Nguyen, Lele Wang, D. Nguyen, V. Bhargava
Edge Computing (EC) offers a superior user experience by positioning cloud resources in close proximity to end users. The challenge of allocating edge resources efficiently while maximizing profit for the EC platform remains a sophisticated problem, especially with the added complexity of the online arrival of resource requests. To address this challenge, we propose to cast the problem as a multi-armed bandit problem and develop two novel online pricing mechanisms, the Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm and the Min-Max Optimal algorithm, for heterogeneous edge resource allocation. These mechanisms operate in real-time and do not require prior knowledge of demand distribution, which can be difficult to obtain in practice. The proposed posted pricing schemes allow users to select and pay for their preferred resources, with the platform dynamically adjusting resource prices based on observed historical data. Numerical results show the advantages of the proposed mechanisms compared to several benchmark schemes derived from traditional bandit algorithms, including the Epsilon-Greedy, basic UCB, and Thompson Sampling algorithms.
{"title":"A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation","authors":"Jiaming Cheng, Duong Thuy Anh Nguyen, Lele Wang, D. Nguyen, V. Bhargava","doi":"10.1109/NetSoft57336.2023.10175461","DOIUrl":"https://doi.org/10.1109/NetSoft57336.2023.10175461","url":null,"abstract":"Edge Computing (EC) offers a superior user experience by positioning cloud resources in close proximity to end users. The challenge of allocating edge resources efficiently while maximizing profit for the EC platform remains a sophisticated problem, especially with the added complexity of the online arrival of resource requests. To address this challenge, we propose to cast the problem as a multi-armed bandit problem and develop two novel online pricing mechanisms, the Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm and the Min-Max Optimal algorithm, for heterogeneous edge resource allocation. These mechanisms operate in real-time and do not require prior knowledge of demand distribution, which can be difficult to obtain in practice. The proposed posted pricing schemes allow users to select and pay for their preferred resources, with the platform dynamically adjusting resource prices based on observed historical data. Numerical results show the advantages of the proposed mechanisms compared to several benchmark schemes derived from traditional bandit algorithms, including the Epsilon-Greedy, basic UCB, and Thompson Sampling algorithms.","PeriodicalId":223208,"journal":{"name":"2023 IEEE 9th International Conference on Network Softwarization (NetSoft)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122523102","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：