Joint edge caching and dynamic service migration in SDN based mobile edge computing

Li, Chunlin; Zhu, Lei; Weigang, Li; Luo, Yingwei

doi:10.1016/j.jnca.2020.102966

Cited by 26 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the simulations highlight the load balancing and network optimizations authenticated through the edge servers connected to the SDN controllers. Recently, SDN-based mobile edge computing was proposed in [79], where the authors focused on dynamic service migration and joint edge caching through deep Q-learning. This approach considerably reduces the transmission cost and several other service migrations.…”

Section: ) Data Centersmentioning

confidence: 99%

SDN Security Review: Threat Taxonomy, Implications, and Open Challenges

et al. 2022

View full text Add to dashboard Cite

Software-Defined networking (SDN) is a networking paradigm to enable dynamic, flexible, and programmatically efficient configuration of networks to revolutionize network control and management via separation of the control plane and data plane. The SDN technology has evolved in response to the demands from large data centers toward all types of networks, from IoT, enterprise, to ISP networks. On the one hand, SDN has provided solutions for high-demand resources, managing unpredictable data traffic patterns, and rapid network reconfiguration. It is further used to enhance network virtualization and security. On the other hand, SDN is still subject to many traditional network security threats. It also introduces new security vulnerabilities, primarily due to its logically centralized control plane infrastructure and functions. In this paper, we conduct a comprehensive survey on the core functionality of SDN from the perspective of secure communication infrastructure at different scales. A specific focus is put forward to address the challenges in securing SDN-based communications, with efforts taken up to address them. We further categorize the appropriate solutions for specific threats at each layer of SDN infrastructures. Lastly, security implications and future research trends are highlighted to provide insights for future research.INDEX TERMS Software defined networks, OpenFlow, security, threat, attack, vulnerability, network security.• Discussion of the future research directions and open challenges hindering resiliency and security in SDNenabled systems. Different from existing papers, this paper provides an up-to-date discussion about security issues in SDN environments. The presented taxonomy covers security threats ranging from topology discovery, network and app manipulation, flow diversion, teleportation & rootkits, controller placement, access control and authorization, to conventional networking threats. Further, in addition to reviewing existing security solutions and related implications, this paper provides key use cases of SDN technology implementation in smart communication systems. This layout is aimed to enable researchers to focus on the challenges that breach security in SDN communications. Ultimately, this work will provide further insights for future research in the SDN security domain.

show abstract

Section: ) Data Centersmentioning

confidence: 99%

SDN Security Review: Threat Taxonomy, Implications, and Open Challenges

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Similarly, deep Q-learning-based service migration approaches were proposed to maximize the weighted sum reward of load capacity and service migration cost [30], [31]. The algorithm selects the optimal action with the maximum Qvalue from all candidates at each time.…”

Section: B Service Migrationmentioning

confidence: 99%

Dynamic Task Allocation and Service Migration in Edge-Cloud IoT System Based on Deep Reinforcement Learning

Chen

Sun

Wang

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

Edge computing extends the ability of cloud computing to the network edge to support diverse resource-sensitive and performance-sensitive IoT applications. However, due to the limited capacity of edge servers (ESs) and the dynamic computing requirements, the system needs to dynamically update the task allocation policy according to real-time system states. Service migration is essential to ensure service continuity when implementing dynamic task allocation. Therefore, this paper investigates the long-term dynamic task allocation and service migration (DTASM) problem in edge-cloud IoT systems where users' computing requirements and mobility change over time. The DTASM problem is formulated to achieve the long-term performance of minimizing the load forwarded to the cloud while fulfilling the seamless migration constraint and the latency constraint at each time of implementing the DTASM decision. First, the DTASM problem is divided into two sub-problems: the user selection problem on each ES and the system task allocation problem. Then, the DTASM problem is formulated as a Markov Decision Process (MDP) and an approach based on deep reinforcement learning (DRL) is proposed. To tackle the challenge of vast discrete action spaces for DTASM task allocation in the system with a mass of IoT users, a training architecture based on the twin-delayed deep deterministic policy gradient (DDPG) is employed. Meanwhile, each action is divided into a differentiable action for policy training and one mapped action for implementation in the IoT system. Simulation results demonstrate that the proposed DRL-based approach obtains the long-term optimal system performance compared to other benchmarks while satisfying seamless service migration.

show abstract

“…Literature [24] proposes an online active cache scheme using the bidirectional deep recursive neural network (BRNN) model to predict time series content requests and update the edge cache accordingly. Literature [25] proposes a collaborative cache strategy of edge servers based on the softwaredefined network (SDN), in which multilayer sensory neural networks are used to predict video content request probability by mobile users and to construct an objective minimization function to maximize the utilization of edge servers' resources. The approach adopts a branch-andbound algorithm to determine the optimal global solution.…”

Section: Related Workmentioning

confidence: 99%

“…Optimization objective Method Disadvantages [22] Download latency Hungarian algorithm No quantitative benefits [23] Cache hit ratio Greedy algorithm High complexity [24] Cache hit ratio Bidirectional recurrent neural networks Privacy security [25] Energy consumption Branch and bound algorithm Privacy security [26] Estimating content popularity Federated k-means scheme High complexity [27] Minimize traffic cost Federated learning Lower model accuracy [29] User response latency Heuristic algorithm Homogeneous user demand distribution [30] The cost of the video provider Branch and bound algorithm High time consuming The user preference model parameter vector of user u, the user preference model parameter vector learned by user u at the r-th iteration. The parameter vector of the regional integrated model…”

Section: Referencementioning

confidence: 99%

Collaborative Caching in Edge Computing via Federated Learning and Deep Reinforcement Learning

Wang

Chen

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

By deploying resources in the vicinity of users, edge caching can substantially reduce the latency for users to retrieve content and relieve the pressure on the backbone network. Due to the capacity limitation of caching and the dynamic nature of user requests, how to allocate caching resources reasonably must be considered. Some edge caching studies improve network performance by predicting content popularity and actively caching the most popular content, thereby ignoring the privacy and security issues caused by the need to collect user information at the central unit. To this end, a collaborative caching strategy based on federated learning is proposed. First, federated learning is used to make distributed predictions of the preferences of users in the nodes to develop an effective content caching policy. Then, the problem of allocating caching resources to optimize the cost of video providers is formulated as a Markov decision process, and a reinforcement learning method is used to optimize the caching decisions. Compared with several basic caching strategies in terms of cache hit rate, transmission delay, and cost, the simulation results show that the proposed content caching strategy reduces the cost of video providers, and has higher cache hit rate and lower average transmission delay.

show abstract

Joint edge caching and dynamic service migration in SDN based mobile edge computing

Cited by 26 publications

References 20 publications

SDN Security Review: Threat Taxonomy, Implications, and Open Challenges

SDN Security Review: Threat Taxonomy, Implications, and Open Challenges

Dynamic Task Allocation and Service Migration in Edge-Cloud IoT System Based on Deep Reinforcement Learning

Collaborative Caching in Edge Computing via Federated Learning and Deep Reinforcement Learning

Contact Info

Product

Resources

About