Metaheuristics for the Virtual Machine Mapping Problem in Clouds

in Informatica (2015), 26(1), 111-134

This article presents sequential and parallel metaheuristics to solve the virtual machines subletting problem in cloud systems, which deals with allocating virtual machine requests into prebooked ... [more ▼]

This article presents sequential and parallel metaheuristics to solve the virtual machines subletting problem in cloud systems, which deals with allocating virtual machine requests into prebooked resources from a cloud broker, maximizing the broker profit. Three metaheuristic are studied: Simulated Annealing, Genetic Algorithm, and hybrid Evolutionary Algorithm. The experimental evaluation over instances accounting for workloads and scenarios using real data from cloud providers, indicates that the parallel hybrid Evolutionary Algorithm is the best method to solve the problem, computing solutions with up to 368.9% profit improvement over greedy heuristics results while accounting for accurate makespan and flowtime values. [less ▲]

Multi-objective evolutionary algorithms for energy-aware scheduling on distributed computing systems

in Applied Soft Computing (2014), 24

The ongoing increase of energy consumption by IT infrastructures forces data center managers to find innovative ways to improve energy efficiency. The latter is also a focal point for different branches ... [more ▼]

The ongoing increase of energy consumption by IT infrastructures forces data center managers to find innovative ways to improve energy efficiency. The latter is also a focal point for different branches of computer science due to its financial, ecological, political, and technical consequences. One of the answers is given by scheduling combined with dynamic voltage scaling technique to optimize the energy consumption. The way of reasoning is based on the link between current semiconductor technologies and energy state management of processors, where sacrificing the performance can save energy. This paper is devoted to investigate and solve the multi-objective precedence constrained application scheduling problem on a distributed computing system, and it has two main aims: the creation of general algorithms to solve the problem and the examination of the problem by means of the thorough analysis of the results returned by the algorithms. The first aim was achieved in two steps: adaptation of state-of-the-art multi-objective evolutionary algorithms by designing new operators and their validation in terms of performance and energy. The second aim was accomplished by performing an extensive number of algorithms executions on a large and diverse benchmark and the further analysis of performance among the proposed algorithms. Finally, the study proves the validity of the proposed method, points out the best-compared multi-objective algorithm schema, and the most important factors for the algorithms performance. [less ▲]

A Power Efficient Genetic Algorithm for Resource Allocation in Cloud Computing Data Centers

in IEEE International Conference on Cloud Networking (CLOUDNET), Luxembourg City, 2014. (2014)

Evolutionary Algorithms for Mobile Ad Hoc Networks

Book published by John Wiley & Sons (2014)

Savant: Automatic parallelization of a scheduling heuristic with machine learning

in Nature and Biologically Inspired Computing (NaBIC), 2013 World Congress on (2013, August 13)

Achieving super-linear performance in parallel multi-objective evolutionary algorithms by means of cooperative coevolution

in Computers and Operations Research (2013), 40(6), 1552-1563

An Overlay Approach for Optimising Small-World Properties in VANETs

in Proceedings of the 16th European Conference on Applications of Evolutionary Computation (EvoApplications) (2013)

Optimisation of the enhanced distance based broadcasting protocol for MANETs

in Journal of Supercomputing (2012), 62(3), 1213-1240

A Multithreading Local Search For Multiobjective Energy-Aware Scheduling In Heterogeneous Computing Systems

in European Conference on Modelling and Simulation (ECMS) (2012)

This article introduces an efficient multithreading local search algorithm for solving the multiobjective scheduling problem in heterogeneous computing systems considering the makespan and energy ... [more ▼]

This article introduces an efficient multithreading local search algorithm for solving the multiobjective scheduling problem in heterogeneous computing systems considering the makespan and energy consumption objectives. The proposed method follows a fully multiobjective approach using a Pareto-based dominance search executed in parallel. The experimental analysis demonstrates that the new multithreading algorithm outperforms a set of deterministic heuristics based on Min-Min. The new method is able to achieve significant improvements in both objectives in reduced execution times for a broad set of testbed instances. [less ▲]

Designing a Self-organized Approach for Scheduling Bag-of-Tasks

in Designing a Self-organized Approach for Scheduling Bag-of-Tasks (2012)

This paper proposes a decentralized and self-organized agent system for dynamically load-balancing tasks arriving in the form of Bags-of-Tasks (BoTs) in large-scale decentralized systems. The approach is ... [more ▼]

This paper proposes a decentralized and self-organized agent system for dynamically load-balancing tasks arriving in the form of Bags-of-Tasks (BoTs) in large-scale decentralized systems. The approach is inspired by the emergent behavior of the sandpile model; a cellular automaton behaving at the edge of chaos. Depending on the state of the cellular automaton, rather different responses may occur when a new task is assigned to a resource. It may change nothing or generate avalanches that reconfigure the state of the system. The proportion between the abundance of avalanches and their sizes shows a power-law relation, a scale-invariant behavior that does not need to be tuned. That means that large –catastrophic– avalanches are very rare but small ones occur very often. Such a smart and emergent behavior fits well with the idea of non-clairvoyant scheduling, where tasks are load balanced into computing resources trying to maximize the performance but without assuming any knowledge on the tasks features. In order to study the viability of the approach, we have conducted an empirical experimentation which shows that the sandpile is able to find near-optimal schedules by reacting differently to different conditions of workloads and architectures. [less ▲]