Power-Aware Allocation of Graph Jobs in Geo-Distributed Cloud Networks

Abstract

In the era of big-data, the jobs submitted to the clouds exhibit complicated structures represented by graphs, where the nodes denote the sub-tasks each of which can be accommodated at a slot in a server, while the edges indicate the communication constraints among the sub-tasks. We develop a framework for efficient allocation of graph jobs in geo-distributed cloud networks (GDCNs), explicitly considering the power consumption of the datacenters (DCs). We address the following two challenges arising in graph job allocation: i) the allocation problem belongs to NP-hard nonlinear integer programming; ii) the allocation requires solving the NP-complete sub-graph isomorphism problem, which is particularly cumbersome in large-scale GDCNs. We develop a suite of efficient solutions for GDCNs of various scales. For small-scale GDCNs, we propose an analytical approach based on convex programming. For medium-scale GDCNs, we develop a distributed allocation algorithm exploiting the processing power of DCs in parallel. Afterward, we provide a novel low-complexity (decentralized) sub-graph extraction method, based on which we introduce cloud crawlers aiming to extract allocations of good potentials for large-scale GDCNs. Given these suggested strategies, we further investigate strategy selection under both fixed and adaptive DC pricing schemes, and propose an online learning algorithm for each.

Allocation of Computation-Intensive Graph Jobs Over Vehicular Clouds in IoV

“…in (1)}; 5 // Stage 2 The optimal candidate selection procedure 6 for each candidate in G C do 7 calculate the value of (4); 8 The optimal candidate C * ← the candidate in G C with the minimum value of (4); 9 End…”

“…3) To tackle the aforementioned NIP problem, we first focus on low-traffic IoV scenarios, for which we develop a graph job allocation algorithm to find the optimal solution. This approach relies on addressing the subgraph isomorphism problem 3 , which is known to be NPcomplete [8], [22]. This makes our first proposed algorithm ineffective upon having a high vehicular density or equivalently large network size.…”

“…An idle slot is seen as a resource block that can run one component of a graph job[8],[9] 3. The subgraph isomorphism problem is a computational task in which two graphs H1 and H2 are given as the input, and one must determine whether H1 contains a subgraph that is isomorphic to H2.…”

Energy-aware Allocation of Graph Jobs in Vehicular Cloud Computing-enabled Software-defined IoV

“…Furthermore, advances in computing and sensing techonologies facilitate applications with computation-intensive features (e.g., realtime 3D mapping and road sign recognition), which require massive computational resources. Specifically, graphrepresentation is used to characterize most of the abovementioned computation-intensive applications: each application 1 is modeled as a graph, where the vertices (components) represent either data sources or data processing units while the edges describe the dependency (data flows) between the vertices [1], [2].…”

“…Several works have been dedicated to the study of the architecture of SDIoV [3] and its applications [4], [5]. Furthermore, there are existing studies devoted to graph job allocation which can be roughly divided into three categories according to the dynamism of the network topology: static [1], [6], semi-static [7]- [11], and dynamic [2], [12]. Considering static topologies of users and servers in a cloud-enabled network environment, the authors of [1] presented a framework for energy-efficient graph job allocation in geo-distributed cloud networks, where solutions were provided for data center networks of varying scales.…”