An Online Framework for Joint Network Selection and Service Placement in Mobile Edge Computing
ABSTARCT :
With the rapid development of 5G, Mobile Edge Computing (MEC) paradigm has emerged to enable various devices or servers at the network edge to contribute their computing capacity for reducing communication delay. A fundamental problem is to preserve satisfactory quality-of-service (QoS) for mobile users in light of densely dispersed wireless communication environment and capacity-constrained MEC nodes. Such user-perceived QoS, typically in terms of the end-to-end delay, is highly vulnerable to both access network bottleneck and communication delay. Previous works primarily focused on optimizing the communication delay through dynamic service placement, while ignoring the critical effect of access network selection on the access delay. This paper studies the problem of jointly optimizing the access network selection and service placement for MEC, with the objective of improving QoS in a cost-efficient manner by judiciously balancing the access delay, communication delay, and service switching cost. We propose an efficient online framework to decompose this long-term time-varying optimization problem into a series of one-shot subproblems. To address the NP-hardness of the one-shot problem, we design a computationally-efficient two-phase algorithm, which achieves a near-optimal solution. Both theoretical analysis on the optimality gap and trace-driven simulations are conducted to validate the efficacy of our proposed solution.
EXISTING SYSTEM :
? In computing the maximum sto-d flow in G (line 3), we can leverage existing algorithms for computing the maximum flow in directed graphs. In particular, the Ford-Fulkerson algorithm has guaranteed termination and optimality in this case.
? More importantly, this algorithm gives a maximum flow solution that is integral, i.e., only sending an integral amount of flow per link.
? The set function formulation inspires us to apply existing algorithms for such problems.
? While having received significant attention in recent years, existing solutions mostly assume additive resource consumption, i.e., the total resource consumption on an edge cloud is the sum of all the demands scheduled to it.
DISADVANTAGE :
? A natural problem is how to distribute and place SEs to provide users with satisfactory Quality-of-Service (QoS), while achieving the economic efficiency for the system operators.
? To tackle this challenge, we transform the original problem into a college admission problem, which is a classical problem in matching theory.
? The problem of service placement is a common topic, and has been extensively researched in cloud computing.
? The work takes service placement and request routing into consideration together, and proposes a close-to-optimal algorithm to solve the joint problem by random rounding.
PROPOSED SYSTEM :
• In, a virtual machine placement and migration method is proposed to minimize the consumption of data transmission time by optimizing service placement in the cloud.
• In, in order to realize the efficient computing offload of mobile cloud computing, a game theory method is proposed.
• In, a hybrid artificial bee colony algorithm is proposed in order to solve the parallel batch distributed flow shop problem where the work deteriorated.
• This paper evaluates the computational complexity of the proposed algorithm by measuring the time for the objective function to reach the convergence value.
ADVANTAGE :
? We propose a two-phase approximation algorithm with provable performance, by applying matching and game theory.
? In a long-term issue, future system information (i.e., the user mobility pattern) is required, so that MEC system operator can make the global optimal decisions for users to achieve better performance both in network selection and service placement.
? The locating position, the service-hosted MEC node, and connected radio network are all known to the MEC applications which can help them improve service performance.
? Due to the stability of communication delay and queuing delay in SMCG, overall delay in system sostenuto owns a smooth performance over time.
|