Santiago Iturriaga

Efficient Heuristics for Profit Optimization of Virtual Cloud Brokers

This article introduces a new kind of broker for cloud computing, whose business relies on outsourcing virtual machines (VMs) to its customers. More specifically, the broker owns a number of reserved instances of different VMs from several cloud providers and offers them to its customers in an on-demand basis, at cheaper prices than those of the cloud providers. The essence of the business resides in the large difference in price between on-demand and reserved VMs. We define the Virtual Machine Planning Problem, an optimization problem to maximize the profit of the broker. We also propose a number of efficient smart heuristics (seven two-phase list scheduling heuristics and a reordering local search) to allocate a set of VM requests from customers into the available pre-booked ones, that maximize the broker earnings. We perform experimental evaluation to analyze the profit and quality of service metrics for the resulting planning, including a set of 400 problem instances that account for realistic workloads and scenarios using real data from cloud providers.

A parallel local search in CPU/GPU for scheduling independent tasks on large heterogeneous computing systems

This article presents the parallel implementation on CPU/GPU of two variants of a stochastic local search method to efficiently solve the scheduling problem in heterogeneous computing systems. Both methods are based on a set of simple operators to keep the computational complexity as low as possible, thus allowing large instances of the scheduling problem to be efficiently addressed. The experimental analysis demonstrates that both versions of the parallel CPU/GPU stochastic local search are able to compute accurate suboptimal schedules in significantly shorter execution times than state-of-the-art schedulers, while also outperforming a recently published GPU parallel evolutionary scheduler in terms of both efficiency and solution quality.

Multiobjective grid scheduling using a domain decomposition based parallel micro evolutionary algorithm

This work studies the problem of scheduling independent tasks in heterogeneous computing grid systems. A new bi-objective formulation of the scheduling problem is introduced, which aims at minimising the makespan and weighted response ratio objectives. A novel parallel micro evolutionary algorithm is developed in order to efficiently solve the problem. By using a domain decomposition approach, the proposed method allows to efficiently deal with the multiobjective optimisation version of the scheduling problem. The new decomposition-based parallel micro evolutionary algorithm is implemented over MALLBA, a general-purpose library for combinatorial optimisation. The experimental analysis performed on both well-known and new large problem instances that model medium-sized grid environments demonstrate that the new parallel micro evolutionary algorithm achieves a high problem-solving efficacy and shows very good scalability behaviour when facing high-dimensional instances.

A Parallel Hybrid Evolutionary Algorithm for the Optimization of Broker Virtual Machines Subletting in Cloud Systems

This article presents a new parallel hybrid evolutionary algorithm to solve the problem of virtual machines subletting in cloud systems. The problem deals with the efficient allocation of a set of virtual machine requests from customers into available pre-booked resources from a cloud broker, in order to maximize the broker profit. The proposed parallel algorithm uses a distributed subpopulations model, and a Simulated Annealing operator. The experimental evaluation analyzes the profit and make span results of the proposed methods over a set of problem instances that account for realistic workloads and scenarios using real data from cloud providers. A comparison with greedy heuristics indicates that the proposed method is able to compute solutions with up to 133.8% improvement in the profit values, while accounting for accurate make span results.

Multiobjective scheduling of green-powered datacenters considering QoS and budget objectives

This article presents a multiobjective approach for scheduling green-powered datacenters. We consider a bag of independent deadline-constrained tasks to be executed in a datacenter partially powered by green energy where machines and be powered on/off. The problem consists in scheduling machine state, task execution, and cooling devices to follow an energy consumption profile while simultaneously minimizing the operational budget and the QoS degradation, subject to maintaining the datacenter temperature below its maximum operational threshold. We propose an Evolutionary Algorithm empowered by a Local Search for tackling this problem. Preliminary results show promising budget reductions when compared to a greedy scheduling approach.

An Empirical Study of the Robustness of Energy-Aware Schedulers for High Performance Computing Systems under Uncertainty

This article presents an empirical evaluation of energy-aware schedulers under uncertainties in both the execution time of tasks and the energy consumption of the computing infrastructure. We address an important problem with direct application in current clusters and distributed computing systems, by analyzing how the list scheduling techniques proposed in a previous work behave when considering errors in the execution time estimation of tasks and realistic deviations in the power consumption. The experimental evaluation is performed over realistic workloads and scenarios, and validated by in-situ measurements using a power distribution unit. Results demonstrate that errors in real-world scenarios have a significant impact on the accuracy of the scheduling algorithms. Different online and offline scheduling approaches were evaluated, and online approach showed improvements of up to 32% in computing performance and up to 18% in energy consumption over the offline approach using the same scheduling algorithm.

A Parallel Multi-objective Local Search for AEDB Protocol Tuning

Mobile ad hoc networks are infrastructure less communication networks that are spontaneously created by a number of mobile devices. Due to the highly fluctuating topology of such networks, finding the optimal configuration of communication protocols is a complex and crucial task. Additionally, different objectives must be usually considered. Small changes in the values of the parameters directly affects the performance of the protocol, promoting one objective while reducing another. Therefore, multi-objective optimisation is needed for fine tuning the protocol. In this work, we propose a novel parallel multi-objective local search that optimises an energy efficient broadcasting algorithm in terms of coverage, energy used, broadcasting time, and network resources. The proposed method looks for appropriate values for a set of 5 variables that markedly influence the behavior of the protocol to provide accurate tradeoff configurations in a reasonable short execution time. The new proposed algorithm is validated versus two efficient multi-objective evolutionary algorithms from the state of the art, offering comparable quality results in much shorter times.

Solving Very Large Optimization Problems (Up to One Billion Variables) with a Parallel Evolutionary Algorithm in CPU and GPU

This article presents the application of a parallel evolutionary algorithm implemented in both CPU and Graphic Processing Units (GPU), to solve large instances of the noisy OneMax problem with up to one billion variables. Actually, new GPU platforms provide the computing power needed to apply massively parallel strategies to solve large problems. We report here the experimental evaluation of both CPU and GPU implementations for a compact evolutionary algorithm. the proposed method demonstrates a high problem solving efficacy and shows a good scalability behavior when facing high dimension instances of the noisy OneMax problem, improving the computational efficiency and the results reported in previous similar approaches developed on CPU.

Multiobjective Scheduling on Distributed Heterogeneous Computing and Grid Environments Using a Parallel Micro-CHC Evolutionary Algorithm

This work presents the application of a parallel micro-CHC evolutionary algorithm to the scheduling problem in heterogeneous computing environments, to minimize the make span and weighted response ratio objectives. The studied problem is NP-hard, and significant effort has been made to develop efficient methods to compute accurate schedules in reduced execution times. Efficient numerical results are reported in the experimental analysis performed on both well-known and new large problem instances that model medium-sized grid environments. The parallel micro-CHC achieves a high problem solving efficacy and shows a good scalability behavior when facing high dimension instances.

Multiobjective Workflow Scheduling in a Federation of Heterogeneous Green-Powered Data Centers

The energy consumption of large data centers has been increasing for the last decades and currently is a major concern for economic and environmental reasons. Accurate scheduling of the data center operation and use of renewable energy sources present themselves as promising solutions for this problem. In this paper we study the problem of scheduling workflows of tasks in distributed heterogeneous data centers which are partially powered by renewable energy sources. This problem takes into account quality of service, infrastructure usage, and power consumption of machines and cooling devices. We propose a mathematical model for accurate scheduling solutions.