Résumé

Résumé

With the increasing adoption of cloud computing, the deployment and management of business processes over cloud environments have become an essential operation for most enterprises, leading to the emergence of BPaaS (Business Process as a Service) as a new cloud service model. This SaaS-like service, like its ancestors, should be strategically distributed and managed over multiple cloud zones, while taking into account several constraints and conditions (e.g., sensitivity of BPaaS fragments, insecure and untrusted cloud zones, lack of resources, and workload changes). However, current BPaaS approaches are static, which means that they are no longer suitable to manage such enterprise-oriented cloud service model and to deal with the uncertain and dynamic nature of cloud availability zones. To fill this gap, we adopt a predictive BPaaS management strategy by proposing a model that forecasts the next-short time overload of cloud zones. These latter, as hosting environments for the managed BPaaS, are categorized as overloaded or underloaded, which triggers the migration of BPaaS fragments to high-performance cloud zones. The proposed neural network prediction model (called QGA-NN) is enhanced with a quantum genetic algorithm to optimize the prediction of cloud zones' overload. QGA-NN is evaluated using a BPaaS placement algorithm, which we defined as a triggered management operation. Experimental results have proved the accuracy and effectiveness of our predictive approach, compared with state-of-the-art solutions.

Résumé

Nowadays, companies are more and more adopting cloud technologies in the management of their business processes rising, then, the Business Process as a Service (BPaaS) model. In order to guarantee the consistency of the provisioned BPaaS, cloud providers should ensure a strategical management (e.g., allocation, migration, etc.) of their available resources (e.g., computation, storage, etc.) according to services requirements. Existing researches do not prevent resource provision problems before they occur. Rather, they conduct a real-time allocation of cloud resources. This paper makes use of historical resource usage information for providing enterprises and BPaaS providers with predictions of cloud availability zones’ states. For that, we first propose a Neural Network-based prediction model that exploits the superposition power of Quantum Computing and the evolutionary nature of the Genetic Algorithm, in order to optimize the accuracy of the predicted resource utilization. Second, we define a placement algorithm that, based on the prediction results, chooses the optimal cloud availability zones for each BPaaS fragment, i.e. under-loaded servers. We evaluated our approach using real cloud workload data-sets. The obtained results confirmed the effectiveness and the performance of our NNQGA approach, compared to traditional techniques.

Résumé

Cloud computing is largely adopted by the current computing industry. Not only users can benefit from cloud scalability, but also businesses are more and more attracted by its flexibility. In addition, the number of offered cloud services (e.g., SaaS, BPaaS, mobile services, etc.) is continuously growing. This raises a question about how to effectively arrange and place them in the cloud, in order to offer high-performance services. Indeed, companies’ and providers’ benefits are strongly related to the optimal placement and management of cloud services, together with their related data. This produces various challenges, including the heterogeneity and dynamicity of hosting cloud zones, the cloud/service –specific placement constraints, etc. Recent cloud service placement approaches have dealt with these issues through different techniques, and by fixing various criteria to optimize. Moreover, researchers have considered other specificities, like the cloud environment type, the deployment model and the placement mode. This paper provides a comprehensive survey on service placement schemes in the cloud. We also identify the current challenges for different cloud service models and environments, and we provide our future directions.

Résumé

Cloud computing is an emerging technology that is largely adopted by the current computing industry. With the growing number of Cloud services, Cloud providers' main focus is how to best offer efficient services (eg, SaaS, BPaaS, mobile services, etc) in order to hook the eventual customers. To meet this goal, services arrangement and placement in the cloud is becoming a serious problem because an optimal placement of these applications and their related data in accordance with the available resources can increase companies' benefits. Since there is a widespread deployment of business processes in the cloud, the hereinafter conducted research works aim to enhance the business processes' outsourcing by providing an optimized placement scheme that would attract cloud customers. In the light of these facts, the purpose of this paper is to deal with the BPaaS placement problem while optimizing both the total execution time and cloud resources' usage. To do so, we first determine the redundant BPaaS fragments using a DNA Fragment Assembly technique. We apply a variant of the Genetic Algorithm to resolve it. Then, we propose a placement algorithm, which produces an optimized placement scheme on the basis of the determined fragments relations. We follow that by an implementation of the whole placement process and a set of experimental results that have shown the feasibility and efficiency of the proposed approach.