Scheduling Parallel Intrusion Detecting Applications on Hybrid Clouds

Abstract

Recently, Parallel Intrusion Detection (PID) becomes very popular and its procedure of the parallel processing is called a PID application (PIDA). This PIDA can be regarded as a Bag-of-Tasks (BoT) application, consisting of multiple tasks that can be processed in parallel. Given multiple PIDAs (i.e., BoT applications) to be handled, when the private cloud has insufficiently available resources to afford all tasks, some tasks have to be outsourced to public clouds with resource-used costs. The key challenge here is how to schedule tasks on hybrid clouds to minimize makespan given a limited budget. This problem can be formulated as an Integer Programming model, which is generally NP-Hard. Accordingly, in this paper, we construct an Iterated Local Search (ILS) algorithm, which employs an effective heuristic to obtain the initial task sequence and utilizes an insertion-neighbourhood-based local search method to explore better task sequences with lower makespans. A swap-based perturbation operator is adopted to avoid local optimum. With the objective of improving the proposal’s efficiency without loss of any effectiveness, to calculate task sequences’ objectives, we construct a Fast Task Assignment (FTA) method by integrating an existing Task Assignment (TA) method with an acceleration mechanism designed through theoretical analysis. Accordingly, the proposed ILS is named FILS. Experimental results show that FILS outperforms the existing best algorithm for the considered problem, considerably and significantly. More importantly, compared with TA, FTA achieves a 2.42x speedup, which verifies that the acceleration mechanism employed by FTA is able to remarkably improve the efficiency. Finally, impacts of key factors are also evaluated and analyzed, exhaustively.

A Novel Firefly Algorithm for Scheduling Bag-of-Tasks Applications Under Budget Constraints on Hybrid Clouds

“…In the literature, a considerable number of efforts have been made to study BoT scheduling on clouds [2], [5], [9]- [31]. Since the attention of this paper is paid to scheduling BoT application in hybrid cloud environments, in this section we briefly discuss existing scheduling methods related to hybrid clouds.…”

“…Different from the cost-minimization deadline-constrained approaches summarized above, our previous work [5] studied makespan-minimization budget-constrained BoT scheduling problem on hybrid clouds. This scheduling problem was formulated as an IP and was solved by a fast iterated local search (FILS) algorithm.…”

“…Different from SFAs that were originally proposed for solving continuous optimization problems, in order to map real-encoded fireflies to solutions (i.e., task sequences), our proposed NFA employs a distance-based mapping operator, which not only considers the distance between a firefly and the brightest one, but also takes into account the current best solution. The mapped solutions can then be evaluated by an efficient task assignment strategy FTA [5]. For the purpose of giving NFA a good start, we construct an effective composite heuristic to generate a highly-qualified solution that is regarded to be the initial best solution.…”

“…This scheme is for the purpose of maintaining a high probability in the mapping operator to inherit most good genes in the current best solution when they are close to the brightest one. Experimental results show that, by employing the above-mentioned strategies, the proposed NFA outperforms the standard firefly algorithm and the existing best algorithm [5] when solving the considered problem, in terms of scheduling effectiveness and computational efficiency. Specifically, the distancebased mapping operator is verified to be both more effective and more efficient compared with the ROV rule.…”

“…The focus of this paper is to address the above-mentioned BoT scheduling problem under budget constraints on hybrid clouds to minimize the makespan, which can be formulated as a NP-hard integer programm (IP) [5], [6]. We propose a novel firefly algorithm (NFA) to solve the considered problem, in which a task sequence is used to represent a scheduling solution.…”