Due to the long latency of accessing services from cloud datacenters, mobile edge computing (MEC) has been proposed to provide the capability of cloud computing in close proximity to mobile users. Mobile devices can offload computation-intensive applications to MEC servers to achieve better performance and reduce power consumption. Owing to user mobility, workloads of MEC servers would vary severely to cause imbalanced loads and incur hotspot servers. Previous studies of power saving and hotspot management apply mechanisms for cloud datacenters to MEC servers, but these studies may not be suitable for MEC servers due to the limited computation and communication capacity. We are motivated to propose a scheme, complementary offloading for hotspot mitigation (COHM), for MEC. COHM consists of mechanisms for MEC servers with different states, namely busy, idle, and available. These mechanisms jointly consider the computation tasks for MEC servers with different states to mitigate hotspots. The simulation results show that COHM can decrease the number of hotspot servers without degrading the quality of service for applications.

Cloud applications such as virtualized network functions usually rely on static or dynamic replication mechanisms to achieve high service reliability and satisfy the requirements of service level agreement. Because replicas are allocated in geographically distributed datacenters, their updates increase the difficulty of maintaining consistency among replicas in different datacenters. The consistency overheads among replicas increase bandwidth consumption and transmission latencies to degrade the quality of service (QoS) performance and service reliability. Although previous mechanisms attempt to shorten response time, reduce bandwidth consumption, or maintain high service reliability with minimized storage cost, they do not consider the overhead of data consistency. In this paper, we study the problem of replica placement with consistency overheads by analyzing the latency and reliability for different types of operations. A replication algorithm, write-aware replica placement (WARP), is then presented based on the analysis. The simulation results show that WARP can shorten response time and improve QoS without degrading reliability.

Mobile edge computing (MEC) has been proposed to complement the limitations of cloud computing. Allocating replicas in MEC servers can shorten transmission latency and improve the quality of service (QoS). However, cloud-based replication schemes may not be suitable for MEC servers due to their limited resources and the varied traffic in RANs. In this paper, we analyze the revenue, cost, and profit for the replicas in MEC servers. Accordingly, we present algorithms of adaptive replication for MEC. Our algorithms dynamically allocate replicas based on the number of read/write operations in each time interval. We also employ an algorithm that adaptively forwards requests to replicas in the neighboring MEC servers to balance the load of MEC servers. The simulation results show that our scheme can effectively shorten the average response time and improve the QoS of packets for better profit.