QoS-ensuring distribution of computation load among cloud-enabled small cells

With increasing requirements of mobile users on computational demanding applications, the need for offloading of computation to a cloud is a convenient way to provide high QoS and to lower energy consumption of a User Equipment (UE). However, common centralized cloud can prolong overall application processing time due to high delay of data delivery from the UE to the cloud and back. To reduce data delivery delay, a concept known as Small Cell Cloud (SCC) can be adopted. The SCC is based on equipping small cell base stations by additional computing capacity and enabling distributed computation for mobile cloud application. For proper function of the SCC, offloaded computing tasks must be efficiently and uniformly distributed among all computing cells. In this paper, we design the algorithm for selection of the computing cells that increases user´s satisfaction with experienced delay due to data transmission and computing. The algorithm selects the computing cell based on combination of users´ requirements and the SCC status. As the results show, the proposed algorithm is able to provide higher satisfaction comparing to competitive approaches for all types of backhauls while the balancing of load is not significantly affected.