A GRASP-Based Approach for Dynamic Cache Resources Placement in Future Networks

Abstract

Dealing with the ever-increasing video traffic is certainly one of the major challenges facing Internet Service Providers (ISPs). In this context, the strategic placement of caches is seen as one of the most important remedies, especially with recent advances in the field of virtualization. Unlike the existing works, which only focus on the placement issue, we also consider the problem of determining the optimal amount of cache to place at each possible location. We formalize, in this paper, the problem of caches placement as a multi-objective optimization problem, in which we minimize both the average distance from which contents are retrieved and the peering links utilization. As the proposed problem is NP-hard, we propose to solve it using the Greedy Randomized Adaptive Search Procedure (GRASP) meta-heuristic. Simulations results reveal the quality of the obtained solutions compared to an exhaustive search method. At the same time, they reveal that the solution is not to put all resources at the edge or at the core, as some studies claim, but to partition them judiciously, which mainly depends on the objectives of the ISPs.

Heterogeneous CCN Cache Allocation Strategy With Collaboration Support

“…In [22], an adaptive cache management approach with pre-filter queues was introduced, in which the cache hit ratio was employed as the feedback to dynamically adjust the number of pre-filter queues in each CR. In [23], the cache allocation was formalized as a multi-objective optimization problem by minimizing both the average distance from which contents are retrieved and the peering links utilization. In [24], a service-aware caching model framework was proposed, in which the caching service matrix was used to describe the position where each user's request was served for each piece of content.…”

An ICN-based Approach for Service Caching in Edge/Fog Environments

“…More precisely, SPP has been studied from different angles, that led to various proposals, such as integer programming [3], meta-heuristics [4] or constrained optimization [5]. The problem of how to optimize the placement of services in the edge/fog computing environment shares few similarities with the well-investigated problem of cache management [6], [7], which started with computer architecture and continued later with web caching to then regain new interests with the arrival of the ICN paradigm [8]. These similarities led researchers to wisely think about combining both approaches, including the design of specific and efficient network architectures allowing to combine both, such as the one in [9], where the main idea is to handle the "low-level" network communication operations on behalf of applications.…”