4.1 Article

Reinforcement Learning vs. Computational Intelligence: Comparing Service Management Approaches for the Cloud Continuum

Related references

Note: Only part of the references are listed.
Article Mathematics

Quantum Inspired Task Optimization for IoT Edge Fog Computing Environment

Tariq Ahamed Ahanger et al.

Summary: IoT-Edge-Fog Computing proposes a decentralized computing model for time-sensitive tasks. However, task allocation among dispersed Edge Computing nodes remains a challenge with existing techniques. This study presents a Quantum Computing-inspired optimization technique for efficient task allocation in an Edge Computing environment and employs a QC-Neural Network Model for predicting optimal computing nodes. Simulations with 6, 10, 14, and 20 Edge nodes were conducted, showing a 5.02% improvement in prediction efficiency and a 2.03% error reduction compared to state-of-the-art techniques.

MATHEMATICS (2023)

Article Automation & Control Systems

Multisurrogate-Assisted Multitasking Particle Swarm Optimization for Expensive Multimodal Problems

Xinfang Ji et al.

Summary: This article introduces a multisurrogate-assisted multitasking particle swarm optimization algorithm to find multiple optimal solutions of expensive multimodal optimization problems at a low computational cost. The algorithm transforms the problem into a multitasking optimization problem and employs cluster and skill factor strategies to balance computation and prediction accuracy. Experimental results show that the algorithm can find multiple highly competitive optimal solutions.

IEEE TRANSACTIONS ON CYBERNETICS (2023)

Article Computer Science, Artificial Intelligence

Placement of IoT Microservices in Fog Computing Systems: A Comparison of Heuristics

Claudia Canali et al.

Summary: Fog computing is a promising approach to support modern IoT applications by reducing response time and traffic through placing tasks in nodes close to sensors or end users. However, the complex and heterogeneous infrastructure of the fog scenario requires novel and efficient solutions for deploying microservices. This paper addresses this issue by proposing and comparing different heuristics, and evaluates their performance and ability to meet Service Level Agreement in various operating conditions.

ALGORITHMS (2023)

Article Computer Science, Software Engineering

A Novel Real-Time Edge-Cloud Big Data Management and Analytics Framework for Smart Cities

Roberto Cavicchioli et al.

Summary: This article introduces an innovative framework based on a big data system that aims to integrate and analyze city information, providing solutions based on both edge and cloud computing. The article focuses on obstacle detection and tracking for edge processing, as well as traffic density monitoring application for cloud processing, emphasizing the ability of these technologies to enable further services.

JOURNAL OF UNIVERSAL COMPUTER SCIENCE (2022)

Article Chemistry, Analytical

An Intelligent Approach for Cloud-Fog-Edge Computing SDN-VANETs Based on Fuzzy Logic: Effect of Different Parameters on Coordination and Management of Resources

Ermioni Qafzezi et al.

Summary: This paper proposes an intelligent approach to flexibly and efficiently manage resources in SDN-VANETs networks, and verifies the feasibility of the proposed approach through computer simulations.

SENSORS (2022)

Article Computer Science, Information Systems

Particle Swarm Optimization: A Comprehensive Survey

Tareq M. Shami et al.

Summary: This paper provides a comprehensive review of particle swarm optimization (PSO), including its basic concepts, variants, applications, and drawbacks. It also reviews research on utilizing PSO to solve feature selection problems and presents potential research directions.

IEEE ACCESS (2022)

Article Computer Science, Hardware & Architecture

Availability model for edge-fog-cloud continuum: an evaluation of an end-to-end infrastructure of intelligent traffic management service

Paulo Pereira et al.

Summary: The world is evolving with the rise of connectivity and technology, increasing the demand for low latency networks and high availability. Edge and fog computing paradigms have been proposed to supplement cloud computing for latency-sensitive applications. Hierarchical availability models and analytical models are introduced to support planning and enhance system availability in edge, fog, and cloud computing environments.

JOURNAL OF SUPERCOMPUTING (2022)

Article Computer Science, Software Engineering

Model-based fleet deployment in the IoT-edge-cloud continuum

Hui Song et al.

Summary: With the advancement of computing and networking capabilities, IoT devices and edge gateways have become part of a larger IoT-edge-cloud computing continuum. This paper presents a model-based approach to automatically assigning multiple software deployment plans to edge gateways and IoT devices.

SOFTWARE AND SYSTEMS MODELING (2022)

Article Automation & Control Systems

Benchmarking Continuous Dynamic Optimization: Survey and Generalized Test Suite

Danial Yazdani et al.

Summary: This study provides a comprehensive review of existing benchmarks and investigates their shortcomings in capturing different problem features. It then proposes a highly configurable benchmark suite capable of generating problem instances with various characteristics.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Article Computer Science, Information Systems

BDMaaS plus : Business-Driven and Simulation-Based Optimization of IT Services in the Hybrid Cloud

Walter Cerroni et al.

Summary: The maturity of heterogeneous and hybrid public Cloud environments allows service providers to deploy complex IT services, but evaluating the impact of changes before and during runtime remains challenging. To address this, we developed BDMaaS+, a decision support tool that can evaluate IT service configurations through simulation.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2022)

Article Automation & Control Systems

Scalar reward is not enough: a response to Silver, Singh, Precup and Sutton (2021)

Peter Vamplew et al.

Summary: The paper argues that reward maximisation is sufficient for all intelligence and the development of artificial general intelligence. However, we contest the assumption that reward can be scalar-valued and propose explicitly multi-objective models. We also highlight the risks of using scalar rewards in developing human-aligned artificial general intelligence.

AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS (2022)

Article Multidisciplinary Sciences

Energy-Efficient Task Scheduling and Resource Allocation for Improving the Performance of a Cloud-Fog Environment

V Sindhu et al.

Summary: Inadequate resources and facilities, along with zero latency, impact the efficiency of task scheduling and resource allocation in the fog paradigm. This article proposes an enhanced container-based task scheduling algorithm with intelligent resource allocation, which aims to balance energy efficiency, cost, and the performance-effectiveness of scheduling and allocation.

SYMMETRY-BASEL (2022)

Article Computer Science, Information Systems

Value is King: The MECForge Deep Reinforcement Learning Solution for Resource Management in 5G and Beyond

Filippo Poltronieri et al.

Summary: Multi-access edge computing is a key enabler for low-latency services in 5G and Beyond networks, but the demands for innovative IT services may exceed available resources. To maximize the potential of MEC, AI-based tools and innovative resource management solutions are needed to dynamically allocate resources in a contextual fashion.

JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT (2022)

Article Computer Science, Information Systems

Cloud Continuum: The Definition

Sergio Moreschini et al.

Summary: This work conducts a systematic mapping study of the literature on the concept of cloud continuum, investigating the different definitions and how they have evolved. The main outcome is a complete definition that merges all the common aspects of cloud continuum, providing practitioners and researchers with a better understanding of what it is.

IEEE ACCESS (2022)

Proceedings Paper Computer Science, Hardware & Architecture

ROMA: Resource Orchestration for Microservices-based 5G Applications

Anousheh Gholami et al.

Summary: With the growth of technologies such as 5G, IoT, edge computing, and cloud computing, the infrastructure available to emerging applications has become complex. In this paper, the authors propose a solution called ROMA, which performs resource orchestration for microservices-based 5G applications. They demonstrate through experiments that ROMA can significantly save compute resources and network bandwidth while meeting application performance requirements.

PROCEEDINGS OF THE IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM 2022 (2022)

Article Computer Science, Information Systems

Self-Organizing Networks for 5G and Beyond: A View from the Top

Andreas G. Papidas et al.

Summary: This article describes the potential of self-organizing network (SON) concepts and architectures in 5G and next-generation networks, focusing on the basic use case of self-optimization in radio access networks (RAN). It analyzes the rationale and operation of SON applications, the design and dimensioning of SON systems, as well as possible deficiencies and conflicts that may arise from parallel function operations. The article also highlights the strong reliance on machine learning (ML) and artificial intelligence (AI). Furthermore, it presents and comments on recent proposals for SON deployment in 5G networks.

FUTURE INTERNET (2022)

Article Computer Science, Information Systems

A Survey on Intrusion Detection Systems for Fog and Cloud Computing

Victor Chang et al.

Summary: The rapid advancement of internet technologies has led to an increase in connected devices, resulting in a larger attack surface. To protect network infrastructures, specific security policies and regulations are necessary, and intrusion detection systems are widely adopted solutions. This survey paper analyzes factors that enable the successful deployment of security policies in cloud and fog computing, focusing on Software-as-a-Service (SaaS) and intrusion detection.

FUTURE INTERNET (2022)

Review Computer Science, Information Systems

Digital Twin-Cyber Replica of Physical Things: Architecture, Applications and Future Research Directions

Cheng Qian et al.

Summary: The Internet of Things (IoT) allows for effective monitoring and control of physical systems by connecting smart devices and utilizing machine learning and deep learning techniques. Creating a Digital Twin (DT) as a cyber replica of a physical system offers a viable strategy to mitigate the risks of directly manipulating real systems. However, designing and representing a DT poses challenges to networking, computing, and data analytics in IoT, and also requires considering exceptional requirements. The thoughtful design of DTs provides opportunities for novel and interdisciplinary research efforts.

FUTURE INTERNET (2022)

Article Computer Science, Information Systems

Optimization and Prediction Techniques for Self-Healing and Self-Learning Applications in a Trustworthy Cloud Continuum

Juncal Alonso et al.

Summary: The current IT market is dominated by the cloud continuum, with a shift towards edge computing and fog computing. This shift requires novel solutions and AI-based techniques for optimizing and managing computational resources efficiently. The paper discusses the importance of infrastructure as code (IaC) in creating, optimizing, managing, and automating operations for heterogeneous computing resources in the computing continuum.

INFORMATION (2021)

Article Computer Science, Artificial Intelligence

Reward is enough

David Silver et al.

Summary: In this article, the hypothesis is made that intelligence and its associated abilities serve the maximization of reward, driving behavior that exhibits various abilities. It is suggested that agents learning through trial and error to maximize reward could exhibit most, if not all, of these abilities, potentially constituting a solution to artificial general intelligence.

ARTIFICIAL INTELLIGENCE (2021)

Article Computer Science, Theory & Methods

FRATO: Fog Resource Based Adaptive Task Offloading for Delay-Minimizing IoT Service Provisioning

Hoa Tran-Dang et al.

Summary: This article introduces a framework called FRATO for minimizing service provisioning delay in IoT-fog-cloud systems through an adaptive task offloading mechanism. FRATO is based on fog resource to flexibly select the optimal offloading policy, including a collaborative task offloading solution based on the data fragment concept. Through simulation analysis, the method shows potential advantages in significantly reducing average delay in systems with high rate of service requests and heterogeneous fog environment.

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2021)

Article Computer Science, Software Engineering

Cloud, Fog, or Edge: Where to Compute?

Dragi Kimovski et al.

Summary: The computing continuum expands high-performance cloud data centers with energy-efficient devices at the edge, but faces challenges in managing applications across heterogeneous environments. This article provides a detailed analysis of performance and carbon footprint of selected use case applications with varying resource requirements across the computing continuum, based on a real-life evaluation testbed.

IEEE INTERNET COMPUTING (2021)

Article Computer Science, Artificial Intelligence

A Survey of Evolutionary Continuous Dynamic Optimization Over Two Decades-Part A

Danial Yazdani et al.

Summary: This article provides a comprehensive survey of evolutionary dynamic optimization for single-objective unconstrained continuous problems over the past two decades. It proposes a new taxonomy for dynamic optimization algorithms and covers important components like convergence detection and computational resource allocation. The article also expands and improves classifications of diversity control and multipopulation methods, and suggests future directions for research.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

A Survey of Evolutionary Continuous Dynamic Optimization Over Two Decades-Part B

Danial Yazdani et al.

Summary: This article reviews evolutionary dynamic optimization (EDO) for single-objective unconstrained continuous problems over the last two decades, with a focus on benchmark problems, performance analysis methods, static optimization methods, and real-world applications. The article provides a new taxonomy for benchmark problems and classifies performance indicators into fitness/error-based and efficiency-based categories. Additionally, it covers static optimization algorithms utilized in the framework of DOAs and reviews real-world dynamic problems optimized by EDO methods.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Information Systems

Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning

Stefan Schneider et al.

Summary: Traditional service coordination methods rely on custom approaches designed by experts, while our proposed DeepCoord is a novel deep reinforcement learning approach that can better coordinate services, adapt to various objectives and traffic patterns, and significantly improve flow throughput and overall network utility.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2021)

Article Computer Science, Information Systems

Online Service Function Chain Deployment for Live-Streaming in Virtualized Content Delivery Networks: A Deep Reinforcement Learning Approach

Jesus Fernando Cevallos Moreno et al.

Summary: This research proposes a multi-objective optimization framework for service function chain deployment in virtualized content delivery networks, focusing on live-streaming. They use deep reinforcement learning and enhance exploration and reward mechanisms. Through simulation tests, they demonstrate that their algorithm significantly improves quality of service and user experience under limited network resource conditions.

FUTURE INTERNET (2021)

Review Computer Science, Information Systems

A review on genetic algorithm: past, present, and future

Sourabh Katoch et al.

Summary: This paper discusses recent advances in genetic algorithms, analyzing selected algorithms of interest in the research community. It helps new and demanding researchers gain a broader understanding of genetic algorithms. The review covers well-known algorithms, genetic operators, research domains, and future research directions in genetic algorithms.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

Article Computer Science, Artificial Intelligence

Population size in Particle Swarm Optimization

Adam P. Piotrowski et al.

SWARM AND EVOLUTIONARY COMPUTATION (2020)

Review Computer Science, Software Engineering

STEP-ONE: Simulated testbed for Edge-Fog processes based on the Opportunistic Network Environment simulator

Jakob Mass et al.

JOURNAL OF SYSTEMS AND SOFTWARE (2020)

Article Engineering, Electrical & Electronic

Digital Twin in the IoT Context: A Survey on Technical Features, Scenarios, and Architectural Models

Roberto Minerva et al.

PROCEEDINGS OF THE IEEE (2020)

Article Computer Science, Information Systems

Energy-Efficient Resource Allocation in Cognitive Radio Networks Under Cooperative Multi-Agent Model-Free Reinforcement Learning Schemes

Amandeep Kaur et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2020)

Article Computer Science, Information Systems

Efficient task allocation approach using genetic algorithm for cloud environment

P. M. Rekha et al.

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS (2019)

Article Computer Science, Information Systems

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

Pham Tran Anh Quang et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2019)

Article Computer Science, Information Systems

RLXSS: Optimizing XSS Detection Model to Defend Against Adversarial Attacks Based on Reinforcement Learning

Yong Fang et al.

FUTURE INTERNET (2019)

Article Computer Science, Information Systems

Task Caching, Offloading, and Resource Allocation in D2D-Aided Fog Computing Networks

Yanwen Lan et al.

IEEE ACCESS (2019)

Article Computer Science, Information Systems

Business-Driven Service Placement for Highly Dynamic and Distributed Cloud Systems

Mauro Tortonesi et al.

IEEE TRANSACTIONS ON CLOUD COMPUTING (2018)

Article Computer Science, Information Systems

The Internet of Things, Fog and Cloud continuum: Integration and challenges

Luiz Bittencourt et al.

INTERNET OF THINGS (2018)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Computer Science, Interdisciplinary Applications

Grey Wolf Optimizer

Seyedali Mirjalili et al.

ADVANCES IN ENGINEERING SOFTWARE (2014)

Review Engineering, Electrical & Electronic

A Review of Quantum-behaved Particle Swarm Optimization

Wei Fang et al.

IETE TECHNICAL REVIEW (2010)

Article Computer Science, Artificial Intelligence

Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients

A Ratnaweera et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2004)