Abstract
Mobile Edge Computing (MEC) architecture is composed of geographically distributed edge servers, in which computing capabilities are provisioned at the boundary of the network, which is in close proximity to the end users to provide network services with low latency. The planning of MEC edge servers at appropriate locations is the fundamental first step towards the deployment of the MEC system. In the literature, edge servers planning is based on deterministic resource requirements. This assumption largely neglects the pragmatic complexities imposed by the real dynamic world, in which base station (BS) resource demands are stochastic variables with arbitrary pattern. In view of this fact, we formulate the MEC planning problem as a joint optimization problem of MEC edge servers placement and resource allocation with uncertain BS demands through an uncertain programming formulation. Due to the complexity of this joint-uncertain problem, a learning based framework is utilized to practically solve this problem, and the relevance of applying this mechanism in practical usage with sampled arbitrary BS demands data is also discussed. Finally, we conducted intensive real-data driven simulations to evaluate the performance of our proposed mechanism. The results show the effectiveness of our approach with arbitrary BS demands.
Highlights
M OBILE network environments often exhibit changing patterns over time
EVALUATION We implemented the proposed learning-based framework and designed experiments to evaluate the performance of the framework on planning Mobile Edge Computing (MEC) servers
We study the mobile edge server planning problem with the aim of minimizing the latency between edge server and base station (BS) under the condition that the requests of BSs are arbitrary stochastic variables
Summary
M OBILE network environments often exhibit changing patterns over time. For instance, the distribution of mobile data traffic is non-homogeneous for different regions and different times of the day. M Shao et al.: A learning based framework for MEC server planning with uncertain BSs demands latency and server workload, etc.), physical deployment constraints, and various dynamic network information Among all these factors, the uncertain resource requirements rising from mobile end users (such as users’ computing tasks) is the key driven factor for the distribution of edge servers, because the execution resources are deployed to fulfill these requirements. Deep learning based approaches have been proven to offer efficient solutions to problems that are characterized with complex uncertain inner relationships between inputs and outputs It has been widely utilized in multiple areas in the context of intelligent 5G network: such as mobile data analytics [19], network traffic control [20], resource management [21], MEC task offloading [22] and network optimization [23].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
