Mobility and Dependence-aware QoS Monitoring in Mobile Edge Computing

Abstract : Mobile edge computing is a new computing paradigm that performs computing on the edge of a network. Services may be unavailable or do not satisfy the needs of users due to changing edge environments. Quality of service (QoS) is commonly employed as a critical means to indicate qualitative status of services. It is particularly important to monitor QoS of the services timely and effectively in the mobile edge environment. However, user mobility and dependencies among QoS values often cause the monitoring results to deviate from the real results. Existing QoS monitoring approaches have not taken into account these problems. To address them, this paper proposes ghBSRM-MEC, a novel mobility and dependence-aware QoS monitoring approach. This approach assumes that the QoS attribute values of edge servers obey Gaussian distribution. It constructs a parent property for each property, thus reducing the dependence between properties. During the training stage, a Gaussian Hidden Bayesian classier is constructed for each edge server. During the monitoring stage, combining with a KNN algorithm, the classier is changed dynamically based on user mobility to realize QoS monitoring under the mobile edge environment. The experimental results validate the feasibility, effectiveness, and efciency of ghBSRM-M

 EXISTING SYSTEM :

 ? In the existing approaches, there is no interaction between routing layer and resource management system. ? Resource discovery and monitoring system is responsible for discovery of new resources and monitoring of existing resources. ? The existing systems are either developed for mobile ad hoc environments or pre-existing network infrastructure-based environments. ? In mobile edge cloud, multiple mobile and stationary devices interconnected through wireless ad hoc and pre-existing network infrastructure-based local area networks are combined to create a small cloud infrastructure.

 DISADVANTAGE :

 ? Various studies have been performed on the optimization problems relating to task offloading in mobile edge computing. ? Several studies have been proposed to consider the task offloading as joint optimization problem in mobile edge computing. ? A task aggregation and prioritization, technique is proposed in to handle the scalability problem. ? Further exploration of aforesaid studies highlighted some limitations, such as they considered the user allocation problem as a static global optimization problem and focused to determine the optimal or near optimal solutions. ? Deep neural networks are also famous in optimization problems, and several lightweight frameworks have been introduced for modern consumer-based networks such as MEC.

 PROPOSED SYSTEM :

 • The performance of the proposed w-RCA is evaluated and compared with the conventional battery smoothing algorithm (BSA) and Baseline by using MPEG-4 encoder for optimizing m-QoS at the source or the server side. • To overcome these shortcomings, a window-based rate control algorithm for m-QoS optimization in Telemedicine system over 5G network is proposed. • Moreover, they proposed energy-efficient transmission power control algorithm for patient's vital sign signals transmission over wireless body area networks, however, they do not focus at medical video stream with QoS optimization over 5G networks. • A mobile edge computing-based 5G framework for QoS optimization in medical media healthcare is proposed.

 ADVANTAGE :

 ? Delay is one of the most used performance metrics that significantly affects the user experience in MEC. ? Therefore, when the users are highly mobile, the schedules produced for task reallocation can have bad user-perceived performance. ? The execution time of tasks is one of the important performance parameters to be considered while taking offloading decisions in the mobile environments. ? Moreover, existing studies mainly focus on the offloading, caching and mobility management to optimize the network performance using centralized SDN technology. ? Those models consider different performance parameters to optimize the system efficiency.