Risk-Aware Data Offloading in Multi-Server Multi-Access Edge Computing Environment

Apostolopoulos, Pavlos Athanasios; Tsiropoulou, Eirini Eleni; Papavassiliou, Symeon

doi:10.1109/tnet.2020.2983119

Cited by 138 publications

(40 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimization problem P2 can be solved via well known existing methods for solving constrained nonlinear optimization problems, and accordingly obtain the optimal contracts under the incomplete information scenario. For demonstration purposes, we utilize the Sequential Quadratic Programming (SQP) method [41], along with the fmincon() [42] function implemented by the MATLAB Optimization Toolbox to return the constrained nonlinear optimization problem's solution, the computational complexity of which is denoted as O(K) [43]. We also indicate as IT E the number of the iterations required by the SLA algorithm to converge.…”

Section: Complexity Analysismentioning

confidence: 99%

Unified User Association and Contract-Theoretic Resource Orchestration in NOMA Heterogeneous Wireless Networks

Diamanti

Fragkos

Tsiropoulou

et al. 2020

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

Lately, the deployment of heterogeneous wireless networks has emerged, as part of the 5G vision, to cope with the users' exaggerated service demands. In this context, the application of Non-Orthogonal Multiple Access (NOMA) technique constitutes a promising solution to facilitate a balance between spectral efficiency and system complexity. In this paper, we consider the problem of joint user association and uplink power allocation, in heterogeneous 5G wireless networks, employing NOMA technology. The coupled problem is treated under an incomplete information scenario, where the Base Stations (BSs) have statistical only knowledge of the users' channel conditions. To deal with the incompleteness of Channel State Information (CSI), a Contract Theory (CT) based approach is introduced. A Reinforcement Learning (RL) based methodology, capitalizing on the provided feedback from the communication environment is initially adopted, in order to achieve the users to BS association in an iterative and distributed manner. The problem of uplink power allocation is subsequently formulated as a contract between each BS and its corresponding users. The optimal power is thus obtained as the solution of the optimization of each BS's utility function, while ensuring the optimality of the utility function of each associated user, given the unique communications characteristics and type of each user. Detailed numerical evaluation of the performance of the proposed unified user association and power allocation framework is provided, via modeling and simulation, illustrating its operation, features and benefits, under densely deployed heterogeneous environments.

show abstract

Section: Complexity Analysismentioning

confidence: 99%

Unified User Association and Contract-Theoretic Resource Orchestration in NOMA Heterogeneous Wireless Networks

Diamanti

Fragkos

Tsiropoulou

et al. 2020

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, there are some works that consider the behavior characteristics of user-end side or MEC side about computation offloading. For user-end side an optimal data offloading of multi-users in multi-MEC is proposed in [34] taking into accounting risk-seeking or loss-aversion behavior of users. an optimal data offloading policy based on noncooperative game among the users is formulated and Pure Nash Equilibrium (PNE) is obtained.…”

Section: Computation Modelmentioning

confidence: 99%

Computation Migration and Resource Allocation in Heterogeneous Vehicular Networks: A Deep Reinforcement Learning Approach

Wang

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the development of 5G technology, the requirements for data communication and computation in emerging 5G-enabled vehicular networks are becoming increasingly stringent. Computationintensive or delay-sensitive tasks generated by vehicles need to be processed in real time. Mobile edge computing (MEC) is an appropriate solution. Wireless users or vehicles can offload computation tasks to the MEC server due to it has strong computation ability and is closer to the wireless users or vehicles. However, the communication and computation resources of the single MEC are not sufficient for executing the continuously generated computation-intensive or delay-sensitive tasks. We consider migrating computation tasks to other MEC servers to reduce the computation and communication pressure on current MEC server. In this paper, we construct an MEC-based computation offloading framework for vehicular networks, which considers time-varying channel states and stochastically arriving computation tasks. To minimize the total cost of the proposed MEC framework, which consists of the delay cost, energy computation cost, and bandwidth cost, we propose a deep reinforcement learning-based computation migration and resource allocation (RLCMRA) scheme that requires no prior knowledge. The RLCMRA algorithm can obtain the optimal offloading and migration policy by adaptive learning to maximize the average cumulative reward (minimize the total cost). Extensive numerical results show that the proposed RLCMRA algorithm can adaptively learn the optimal policy and outperform four other baseline algorithms.

show abstract

“…Content may change prior to final publication. [9] Resource exhaustion, hardware failure, and SLA violations No Experimentation [12] Resource revocation risk No Experimentation [13] Data leakage No Graph Theory and heuristic [14] Reduce the risk of co-resident attack No Simulation [15] Reduce the risk of co-resident attack No Simulation [16] Reduce the risk of co-resident attack No Simulation [17] Virtual resources to protect the task execution Yes Semi-Markov Decision Process [18] Virtual resources to protect the task execution No Semi-Markov Decision Process [19] Virtual resources to protect the task execution No Semi-Markov Decision Process [20] Virtual resources to protect the task execution No Markov reward model and simulated annealing [21] Security overhead to protect the task execution Yes Genetic Algorithm [22] Security overhead to protect the task execution Yes Deep Reinforcement Learning [23] Computation and communication uncertainties Yes Game Theory [24] Risk-neutral user, risk-averse user, risk-seeking user Yes Simulation [25] IDS at the edge of the network Yes Stochastic Differential Equation [26] Service failure No Graph Theory [27] Service and server failure No System Optimization and Heuristics Our work…”

Section: Security Risk-aware Edge Server Orchestration a Related mentioning

confidence: 99%

“…Taking the computation and communication uncertainties at each MEC server as the risk figure, Apostolopoulos et al [23] formulated the problem of task offloading as a noncooperative game among the users and solved it by means of the pure Nash Equilibrium. A risk-centric broker mechanism is proposed by Iyer et al [24] in which the decision making problem is formulated to decide about the computing task placement between a cloud data center or a fog data center taking into account the user risk profile, price, and reputation of the cloud and fog service provider.…”

Section: Security Risk-aware Edge Server Orchestration a Related mentioning

confidence: 99%

When Agile Security Meets 5G

et al. 2020

View full text Add to dashboard Cite

5G is a critical infrastructure that will connect the whole society and bridge other critical infrastructure systems. Thus, cybersecurity emerges as crucial tenet within the 5G pathway. In this article, we discuss the concept of agile security within a 5G infrastructure taking into account two of its major technologies: Mobile Edge Computing (MEC) and Network Functions Virtualization (NFV). In this sense, we first discuss the 5G-driven MEC deployment from a NFV perspective. Secondly, we present the concept of agile security and how it can be embedded in the daily activities of mobile network operators (MNOs). Thirdly, we discuss risk management as a key element of the agile security framework. To illustrate its application, we propose the design of an agile security risk-aware edge server mechanism for 5G driven MEC deployment, which uses multiple thresholds and a load-balancing security control to mitigate the risks of resource exhaustion and violation of the service level agreement (SLA) faced by the edge servers while taking advantage of multiple cloud layers to increase the degree of availability and dependability of the system. Numerical results show that the proposed mechanism is able to keep the risk at lower levels. INDEX TERMS 5G Security, Agile Security, Cloud Security, Security Risk Management.

show abstract

Risk-Aware Data Offloading in Multi-Server Multi-Access Edge Computing Environment

Cited by 138 publications

References 27 publications

Unified User Association and Contract-Theoretic Resource Orchestration in NOMA Heterogeneous Wireless Networks

Unified User Association and Contract-Theoretic Resource Orchestration in NOMA Heterogeneous Wireless Networks

Computation Migration and Resource Allocation in Heterogeneous Vehicular Networks: A Deep Reinforcement Learning Approach

When Agile Security Meets 5G

Contact Info

Product

Resources

About