A heuristic approach to the multicriteria design of IaaS cloud infrastructures for Big Data applications

Abstract

The rapid growth of new computing paradigms such as Cloud Computing and Big Data has unleashed great opportunities for companies to shift their business model towards a fully digital strategy. A major obstacle in this matter is the requirement of highly specialized ICT infrastructures that are expensive and difficult to manage. It is at this point that the IaaS (infrastructure as a service) model offers an efficient and cost‐affordable solution to supply companies with their required computing resources. In the Big Data context, it is often a hard task to design an optimal IaaS solution that meets user requirements. In this context, we propose a methodology to optimize the definition of IaaS cloud models for hosting Big Data platforms, following a threefold criterion: cost, reliability, and computing capacity. Specifically, the proposed methodology hinges on evolutionary heuristics in order to find IaaS configurations in the cloud that optimally balance such objectives. We also define measures to quantify the aforementioned metrics over a Big Data platform hosted within an IaaS cloud model. The proposed method is validated by using real information from three IaaS providers and three Big Data platforms. The obtained results provide an insightful input for system managers when initially designing cloud infrastructures for Big Data applications.

Construction of a big data platform for infrastructure in the rural revitalisation strategy

“…1) For 0-1 standardization, the data will be linearly transformed to fall within the range of 0 and 1. See equation (16). * min max min…”

“…In addition, the literature [15] through the big data platform to "rural sports material culture factors", "rural folk sports culture intangible factors", "farmers sports culture spiritual factors", "rural sports culture system factors," and "farmers' behavioral sports culture factors" five aspects of sports culture construction influencing factors to analyze, for rural sports construction to improve the theoretical basis. Literature [16] presents a method of following the cost, reliability, and computing ability of three criteria to optimize the IaaS cloud model of the platform. Literature [17] uses Lambda architecture to design a big data platform, proposes a cross-validation merging algorithm to improve the training efficiency of support vector machines on large-scale data, designs a parallelized support vector machine based on cross-validation, and implements the parallelization process of the support vector machine on the Spark platform, and conducts experiments on different datasets.…”

CloudOps: Towards the Operationalization of the Cloud Continuum: Concepts, Challenges and a Reference Framework

“…The literature is scarce in studies centered on the optimal deployment of microservice over heterogeneous cloud services. In [36], a NSGA-II algorithm was used to match the specific requirements of a certain Big Data application to the capabilities provided by an IaaS infrastructure and the Big Data platform deployed therein against three design aspects for the infrastructure of the Big Data application: cost, reliability and net computing capacity. Similarly, in [37], two main objectives were considered for optimization: (1) fulfilment of the microservices' Non-Functional-Requirements (NFRs) (location, availability, cost, performance and legal level), and (2) meeting of the characteristics set by the developers of these microservices (classification, public IP, disk space, RAM and number of cores).…”

Expert systems: Special issue on “New trends and Innovations in Intelligent Distributed Computing”

“…After several rounds of review, five papers have been accepted for publication. The contributions from these papers can be summarized as follows: The paper entitled “A Heuristic Approach to the Multi‐Criteria Design of IaaS Cloud Infrastructures for Big Data Applications,” authored by Arosteguia, Torre‐Bastida, Bilbao, and Ser (), presents a methodology to optimize the definition of IaaS cloud models for hosting Big Data platforms following a threefold criterion: cost, reliability, and computing capacity. The methodology relies on a multiobjective heuristic algorithm that optimizes jointly these conflicting objectives towards the achievement of Pareto‐optimal infrastructure solutions.…”