Merging mobile edge computing (MEC) functionality with the dense deploymentof base stations (BSs) provides enormous benefits such as a real proximity, lowlatency access to computing resources. However, the envisioned integrationcreates many new challenges, among which mobility management (MM) is a criticalone. Simply applying existing radio access oriented MM schemes leads to poorperformance mainly due to the co-provisioning of radio access and computingservices of the MEC-enabled BSs. In this paper, we develop a novel user-centricenergy-aware mobility management (EMM) scheme, in order to optimize the delaydue to both radio access and computation, under the long-term energyconsumption constraint of the user. Based on Lyapunov optimization andmulti-armed bandit theories, EMM works in an online fashion without futuresystem state information, and effectively handles the imperfect system stateinformation. Theoretical analysis explicitly takes radio handover andcomputation migration cost into consideration and proves a bounded deviation onboth the delay performance and energy consumption compared to the oraclesolution with exact and complete future system information. The proposedalgorithm also effectively handles the scenario in which candidate BSs randomlyswitch on/off during the offloading process of a task. Simulations show thatthe proposed algorithms can achieve close-to-optimal delay performance whilesatisfying the user energy consumption constraint.
展开▼