ABSTRACT. With a continuous increase in their electricity consumption, data centres (DCs) represent nowadays, as well as for the whole Information and Communication sector, a considerable environmental impact. The number of applications and services hosted in the cloud is significant, and the associated number of infrastructure is steadily increasing. Cloud Service Providers need to respond to this growing demand and size their infrastructures accordingly. But users expectations in terms of service quality as well as their misbehaviour lead to oversized infrastructures, resulting in poor resource utilization and additional power consumption. To address these issues, various techniques such as virtualization, shutdown techniques, elasticity or consolidation enable improved energy efficiency of Cloud infrastructures. But as their behaviour can increase DC energy consumption and environmental footprint, users can also help reducing them. In this paper, we study how users provided with a simple tool can reduce the power consumption of a virtualization cluster in a cloud company. Using a Virtual Machine (VM) shutdown policy, users can directly contribute to the mitigation of the power consumption of the infrastructure. Part of the paper is dedicated to profile the users and understand their behaviour when it comes to powering off their VMs. To further reduce the energy consumption of the cluster, we combine the VM shutdown policy with a simple consolidation heuristic. Simulations show a 23.95% power consumption reduction, with an additional 8.72% reduction thanks to the users. A production implementation was conducted and results in a 12.58% power consumption reduction over one week.

ABSTRACT. Serverless computing is a paradigm that allows application developers to focus on defining functions triggered by events, while the service provider handles resource allocation, isolation, scalability, and orchestration. Function-as-a-Service (FaaS) is a popular implementation of serverless computing, characterized by short-lived stateless functions. However, current FaaS platforms suffer from high overheads of bootstrapping the process for function execution, which degrade the performance of applications that require low latency and high throughput. Moreover, current FaaS platforms do not support sharing memory among function instances of the same workflow, which limits the efficiency and functionality of applications that rely on data dependencies. In this paper, we propose Ataru, a native function execution virtualization construct that exploits full hardware potential with the provision for shared memory and minimal process bootstrapping overhead, without sacrificing the security offered by virtualization technologies. Ataru consists of two components: Ataru-KVM, a lightweight virtual machine monitor (VMM) based on KVM that supports fast bootup and dynamic suspension of virtual CPUs (vCPUs), and Ataru Runtime, a runtime system that manages the execution of an application defined by Directed Acyclic Graph~(DAG) of functions and memory sharing within the virtual machine (VM). We evaluate Ataru against a process-based solution over Firecracker that offers similar VM isolation as Ataru, and show that Ataru outperforms Firecracker significantly in terms of bootup time, function execution time, and vCPU utilization, especially when the functions have execution times in the order of tens of microseconds.

ABSTRACT. This paper introduces a framework to integrate Financial Operations (FinOps) practices in Kubernetes, addressing the challenge of managing cloud services' costs across multi-cloud environments. The framework automates the collection of service providers' costs by deploying Prometheus exporters and scrapers, then standardizes cost data according to the FinOps Cost and Usage Specification (FOCUS) through Large Language Models (LLMs). It enables automatic data analysis, implemented by a metrics aggregator, to compute insightful cost and quality of service optimizations. We present the experimental results on three standard cloud service providers. The obtained accuracy corroborates that the framework helps simplify cloud cost management and promote FinOps principles.

ABSTRACT. The increasing availability of Web APIs has brought about a revolution in software development. Developers can now create innovative web applications by combining existing services. However, with so many APIs available, it can take time to identify the most suitable ones for a particular task. Many existing recommendation systems rely on keyword matching and historical data, which can limit their effectiveness when dealing with complex functional requirements and new mashup creation scenarios. This paper presents a new method for recommending web APIs to developers for mashup composition. Our goal is to improve the accuracy of recommendations, particularly when developers need more domain knowledge or encounter ambiguous functional descriptions. To achieve this, we propose a solution driven by natural text descriptions, which utilizes advanced techniques such as semantic enrichment and deep learning. The approach to recommendation methods combines content-based and quality-of-service (QoS) techniques with the advanced capabilities of BERT (Bidirectional Encoder Representations from Transformers) Variants and Graph Generative Adversarial Networks (Graph GAN). BERT's Variant's contextual understanding of text allows us to capture more comprehensive functional descriptions, overcoming the limitations of traditional keyword matching. Meanwhile, Graph GAN helps us learn from existing mashup-service invocation records, leading to more accurate and relevant service recommendations. Our framework consists of a robust data and semantic enrichment component that employs paraphrase mining to extend the vocabulary and enhance semantic similarity measures. As a result, our recommendation system can handle various natural language queries and identify subtle contextual nuances in service descriptions.

ABSTRACT. The Internet of Things (IoT) revolutionizes smart city domains such as healthcare, transportation, industry, and education. The Internet of Medical Things (IoMT) is gaining prominence, particularly in smart hospitals and Remote Patient Monitoring (RPM). The vast volume of data generated by IoMT devices should be analyzed in real-time for health surveillance and prognosis and prediction of diseases in an integrated patient-centric end-to-end healthcare system. Current approaches relying on Cloud computing to provide the necessary computing and storage capabilities do not scale for these latency-sensitive applications due to the communication delays induced by the distance between the monitoring devices and the Cloud. Edge computing emerges as a solution by bringing cloud services closer to IoMT devices. This paper introduces SmartEdge, a smart healthcare end-to-end integrated edge and cloud computing system for diabetes prediction. This work addresses latency concerns and demonstrates the efficacy of edge resources in healthcare applications within an end-to-end system. The system leverages various risk factors for diabetes prediction, showcasing its potential for early intervention and complication prevention. We propose an edge- and cloud-enabled framework to deploy the proposed diabetes prediction models on various configurations using edge devices and main cloud servers. Performance parameters are evaluated using network bandwidth, latency, accuracy, and execution time. By using ensemble machine learning voting algorithms we can improve the prediction accuracy by 4% versus a single model prediction.