| Summary: | The bursting increase in requesting wireless data has caused several issues in network peak-traffic duration. This negatively results in significant data delivery delay imposed on users that can eventually impact the network's quality of service and users' quality of experience. In this research, regarding mobile edge caching as a potential solution to decrease such delay, we propose a new framework in which we introduce the concept of the flexible user where he requests for a set of multiple files from the library with a unique feature, e.g., 5 movies within comedy genre from the library in the peak-traffic duration. The satisfactory criterion for the flexible user is to receive any of the files within the requested set. This definition of the flexible user indicates a new concept which captures interesting scenarios. In order to model this concept, we generalize the conventional Zipf distribution to a multivariate one as the modeling method for popular data. We formulate the problem of finding the optimal cache data placement, which minimizes the average total delivery delay in the network while satisfying the helpers' cache size constraints. To this end, we derive the average delivery delay per user as well as the average total delivery delay in the network, according to the new generalized Zipf distribution. Finding the optimal solution is proved to be NP-Hard. We leverage on the problem property to propose an efficient approximation method, called greedy algorithm, which performs within a constant factor as good as the optimal solution. Afterwards, we propose an algorithm called speedy-greedy to significantly reduce the computational complexity of the greedy algorithm while achieving the same performance. Simulation results indicate that our proposed framework significantly decreases the average total delivery delay of the system model that can help the network maintain its quality of service in network peak-traffic duration.
|
|---|