Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
Machine Learning and Data Analytics for Edge Cloud Computing
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Machine Learning and Data Analytics for Edge Cloud Computing

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (31 August 2023) | Viewed by 18747

Special Issue Editors

Dr. Uttam Ghosh

E-Mail Website1 Website2
Guest Editor
Department of Cybersecurity, School of Applied Computational Sciences (SACS), Meharry Medical College (MMC), Nashville, TN 37208, USA
Interests: cybersecurity; computer networks; wireless networks; information-centric networking and software-defined networking; machine intelligence
Special Issues, Collections and Topics in MDPI journals
Dr. Sahil Verma

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Chandigarh University, Punjab 140413, India
Interests: machine learning; Ad-Hoc networks; cybersecurity; 5G technologies; blockchain
Dr. Gautam Srivastava

E-Mail Website
Guest Editor
Department of Math and Computer Science, Brandon University, Brandon, MB R7A 6A9, Canada
Interests: blockchain technology; cryptography; big data; data mining; social networks; security and privacy; anonymity and graphs
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Mouhammd Alkasassbeh

E-Mail Website
Guest Editor
Computer Science Department, Princess Sumaya University for Technology, Khalil Al Saket St 112, Amman 11941, Jordan
Interests: network traffic analysis; network fault detection; classification network fault and abnormality and Machine learning in the area of computer networking and network security

Special Issue Information

Dear Colleagues,

Cloud computing, as well as cloud-inspired business models, enables on-demand access to a shared pool of resources, namely computing, storage, networks, services, and applications. With the advent of cloud-based systems, cloud operators have been aiming at a reliable, secured, privacy-preserving, and cost-efficient cloud design and management. As the cloud infrastructure aims at offering various IT resources as services, requirements of cloud applications vary based on the resources which are requested as services. Thus, the resources may refer to heavy computation resources, massive storage resources, high-capacity network resources, and so on. The heterogeneity of cloud applications leads to the challenge of the holistic design of a robust cloud system that can oversee and handle the diverse needs of numerous types of applications. On the other hand, the new computation technologies, such as big data analytics, machine learning, and blockchain, have a great influence on the cloud and network.

There are many driving forces behind the rising adoption of edge computing that favor the preparation and examination of information at the edge. Presently, the business has consolidated around seven essential needs that edge processing can meet, namely the requirements for low/ultra-low dormancy, reduced expense of transmission capacity, improved network speed, security, data sovereignty, reliability, and interoperability with legacy frameworks. One of the difficulties in thinking about when, where, why, and how to process and examine information is that ventures and merchants have various meanings of 'the edge' contingent, where information preparation is done right now, and (for sellers specifically) the relative information handling capacities of their current items and administrations. For modern undertakings that have generally handled and broken down most of their information in incorporated datacenters (either on-premises or in the cloud), whatever is not a focal datacenter could honestly be considered 'the edge'. Rather like early stargazers who examined Saturn with moderately powerless telescopes and saw that it was encompassed by a ring, their viewpoint of an edge is characterized by their distance from it. Later, space experts with more impressive telescopes obtained a closer vantage point from which they could recognize that Saturn was, truth be told, surrounded by different rings. Likewise, those with a vantage point that is closer to the edge perceive that it cannot be viewed as a solitary, unmistakable element; instead, it is a range of various edge gadgets. Machine learning (ML) has recently shown good results in a variety of domains, especially when large data quantities are available. It has great potential in the cloud context because it can carry out representation learning by transforming data into hierarchical abstract representations that enable learning good features.

Topics

This Special Issue aims to bring together researchers from academia, industry, and government agencies to understand the innovative technologies such as big data analytics, machine learning, and blockchain in the edge cloud paradigm. Submitted papers are expected to employ state-of-the-art and novel approaches to cover solutions for the edge cloud related to cost-effectiveness, sustainability problems, and other challenges. Potential topics include but are not limited to the following:

  • Cloud computing system and network design;
  • Cloud network protocol design and management;
  • Optimization for cloud computing, networking, and applications;
  • Green cloud system design;
  • Cloud storage design and networking;
  • Cloud system and storage security;
  • Cloud network virtualization techniques;
  • Modeling for cloud system, network, and storage;
  • Performance analysis for cloud system, network, and storage;
  • Big data storage and networking in the clouds;
  • Intra-cloud computing and networking;
  • Mobile cloud system design;
  • Cloud media and storage design;
  • Real-time resource reporting and monitoring for cloud management;
  • Cloud system interoperability;
  • Cloud data center design;
  • Utility computing solutions in cloud systems;
  • Cloud forensics;
  • Networking for cloud computing;
  • Machine learning and data mining for cloud computing;
  • Edge, fog, and mobile edge computing;
  • Security, privacy, and trust for cloud computing;
  • Machine learning for cloud resource management;
  • Machine learning for traffic engineering and congestion control;
  • Machine learning for network measurement;
  • Data-driven methodology and architecture;
  • Networking for machine learning systems;
  • Resource management and device placement for machine learning systems;
  • Measurement and diagnosis for machine learning systems;
  • Blockchain with cloud computing.

Dr. Uttam Ghosh
Dr. Sahil Verma
Dr. Gautam Srivastava
Prof. Dr. Mouhammd Alkasassbeh
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

31 pages, 3102 KiB  
Article
Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency
by Hussein Al-Bazzaz, Muhammad Azam, Manar Amayri and Nizar Bouguila
Sensors 2023, 23(19), 8296; https://doi.org/10.3390/s23198296 - 7 Oct 2023
Cited by 1 | Viewed by 1324
Abstract
Smart meter datasets have recently transitioned from monthly intervals to one-second granularity, yielding invaluable insights for diverse metering functions. Clustering analysis, a fundamental data mining technique, is extensively applied to discern unique energy consumption patterns. However, the advent of high-resolution smart meter data [...] Read more.
Smart meter datasets have recently transitioned from monthly intervals to one-second granularity, yielding invaluable insights for diverse metering functions. Clustering analysis, a fundamental data mining technique, is extensively applied to discern unique energy consumption patterns. However, the advent of high-resolution smart meter data brings forth formidable challenges, including non-Gaussian data distributions, unknown cluster counts, and varying feature importance within high-dimensional spaces. This article introduces an innovative learning framework integrating the expectation-maximization algorithm with the minimum message length criterion. This unified approach enables concurrent feature and model selection, finely tuned for the proposed bounded asymmetric generalized Gaussian mixture model with feature saliency. Our experiments aim to replicate an efficient smart meter data analysis scenario by incorporating three distinct feature extraction methods. We rigorously validate the clustering efficacy of our proposed algorithm against several state-of-the-art approaches, employing diverse performance metrics across synthetic and real smart meter datasets. The clusters that we identify effectively highlight variations in residential energy consumption, furnishing utility companies with actionable insights for targeted demand reduction efforts. Moreover, we demonstrate our method’s robustness and real-world applicability by harnessing Concordia’s High-Performance Computing infrastructure. This facilitates efficient energy pattern characterization, particularly within smart meter environments involving edge cloud computing. Finally, we emphasize that our proposed mixture model outperforms three other models in this paper’s comparative study. We achieve superior performance compared to the non-bounded variant of the proposed mixture model by an average percentage improvement of 7.828%. Full article
(This article belongs to the Special Issue Machine Learning and Data Analytics for Edge Cloud Computing)
►▼ Show Figures

Figure 1

21 pages, 3113 KiB  
Article
Energy Aware Load Balancing Framework for Smart Grid Using Cloud and Fog Computing
by Saurabh Singhal, Senthil Athithan, Madani Abdu Alomar, Rakesh Kumar, Bhisham Sharma, Gautam Srivastava and Jerry Chun-Wei Lin
Sensors 2023, 23(7), 3488; https://doi.org/10.3390/s23073488 - 27 Mar 2023
Cited by 8 | Viewed by 3043
Abstract
Data centers are producing a lot of data as cloud-based smart grids replace traditional grids. The number of automated systems has increased rapidly, which in turn necessitates the rise of cloud computing. Cloud computing helps enterprises offer services cheaply and efficiently. Despite the [...] Read more.
Data centers are producing a lot of data as cloud-based smart grids replace traditional grids. The number of automated systems has increased rapidly, which in turn necessitates the rise of cloud computing. Cloud computing helps enterprises offer services cheaply and efficiently. Despite the challenges of managing resources, longer response plus processing time, and higher energy consumption, more people are using cloud computing. Fog computing extends cloud computing. It adds cloud services that minimize traffic, increase security, and speed up processes. Cloud and fog computing help smart grids save energy by aggregating and distributing the submitted requests. The paper discusses a load-balancing approach in Smart Grid using Rock Hyrax Optimization (RHO) to optimize response time and energy consumption. The proposed algorithm assigns tasks to virtual machines for execution and shuts off unused virtual machines, reducing the energy consumed by virtual machines. The proposed model is implemented on the CloudAnalyst simulator, and the results demonstrate that the proposed method has a better and quicker response time with lower energy requirements as compared with both static and dynamic algorithms. The suggested algorithm reduces processing time by 26%, response time by 15%, energy consumption by 29%, cost by 6%, and delay by 14%. Full article
(This article belongs to the Special Issue Machine Learning and Data Analytics for Edge Cloud Computing)
►▼ Show Figures

Figure 1

20 pages, 2015 KiB  
Article
Hybrid Recommendation Network Model with a Synthesis of Social Matrix Factorization and Link Probability Functions
by Balraj Kumar, Neeraj Sharma, Bhisham Sharma, Norbert Herencsar and Gautam Srivastava
Sensors 2023, 23(5), 2495; https://doi.org/10.3390/s23052495 - 23 Feb 2023
Cited by 5 | Viewed by 2067
Abstract
Recommender systems are becoming an integral part of routine life, as they are extensively used in daily decision-making processes such as online shopping for products or services, job references, matchmaking for marriage purposes, and many others. However, these recommender systems are lacking in [...] Read more.
Recommender systems are becoming an integral part of routine life, as they are extensively used in daily decision-making processes such as online shopping for products or services, job references, matchmaking for marriage purposes, and many others. However, these recommender systems are lacking in producing quality recommendations owing to sparsity issues. Keeping this in mind, the present study introduces a hybrid recommendation model for recommending music artists to users which is hierarchical Bayesian in nature, known as Relational Collaborative Topic Regression with Social Matrix Factorization (RCTR–SMF). This model makes use of a lot of auxiliary domain knowledge and provides seamless integration of Social Matrix Factorization and Link Probability Functions into Collaborative Topic Regression-based recommender systems to attain better prediction accuracy. Here, the main emphasis is on examining the effectiveness of unified information related to social networking and an item-relational network structure in addition to item content and user-item interactions to make predictions for user ratings. RCTR–SMF addresses the sparsity problem by utilizing additional domain knowledge, and it can address the cold-start problem in the case that there is hardly any rating information available. Furthermore, this article exhibits the proposed model performance on a large real-world social media dataset. The proposed model provides a recall of 57% and demonstrates its superiority over other state-of-the-art recommendation algorithms. Full article
(This article belongs to the Special Issue Machine Learning and Data Analytics for Edge Cloud Computing)
►▼ Show Figures

Figure 1

17 pages, 587 KiB  
Article
A Joint Model Provisioning and Request Dispatch Solution for Low-Latency Inference Services on Edge
by Anish Prasad, Carl Mofjeld and Yang Peng
Sensors 2021, 21(19), 6594; https://doi.org/10.3390/s21196594 - 2 Oct 2021
Cited by 1 | Viewed by 1796
Abstract
With the advancement of machine learning, a growing number of mobile users rely on machine learning inference for making time-sensitive and safety-critical decisions. Therefore, the demand for high-quality and low-latency inference services at the network edge has become the key to modern intelligent [...] Read more.
With the advancement of machine learning, a growing number of mobile users rely on machine learning inference for making time-sensitive and safety-critical decisions. Therefore, the demand for high-quality and low-latency inference services at the network edge has become the key to modern intelligent society. This paper proposes a novel solution that jointly provisions machine learning models and dispatches inference requests to reduce inference latency on edge nodes. Existing solutions either direct inference requests to the nearest edge node to save network latency or balance edge nodes’ workload by reducing queuing and computing time. The proposed solution provisions each edge node with the optimal number and type of inference instances under a holistic consideration of networking, computing, and memory resources. Mobile users can thus be directed to utilize inference services on the edge nodes that offer minimal serving latency. The proposed solution has been implemented using TensorFlow Serving and Kubernetes on an edge cluster. Through simulation and testbed experiments under various system settings, the evaluation results showed that the joint strategy could consistently achieve lower latency than simply searching for the best edge node to serve inference requests. Full article
(This article belongs to the Special Issue Machine Learning and Data Analytics for Edge Cloud Computing)
►▼ Show Figures

Figure 1

Review

Jump to: Research

20 pages, 630 KiB  
Review
A Survey on Graph Neural Networks for Microservice-Based Cloud Applications
by Hoa Xuan Nguyen, Shaoshu Zhu and Mingming Liu
Sensors 2022, 22(23), 9492; https://doi.org/10.3390/s22239492 - 5 Dec 2022
Cited by 10 | Viewed by 6908
Abstract
Graph neural networks (GNNs) have achieved great success in many research areas ranging from traffic to computer vision. With increased interest in cloud-native applications, GNNs are increasingly being investigated to address various challenges in microservice architecture from prototype design to large-scale service deployment. [...] Read more.
Graph neural networks (GNNs) have achieved great success in many research areas ranging from traffic to computer vision. With increased interest in cloud-native applications, GNNs are increasingly being investigated to address various challenges in microservice architecture from prototype design to large-scale service deployment. To appreciate the big picture of this emerging trend, we provide a comprehensive review of recent studies leveraging GNNs for microservice-based applications. To begin, we identify the key areas in which GNNs are applied, and then we review in detail how GNNs can be designed to address the challenges in specific areas found in the literature. Finally, we outline potential research directions where GNN-based solutions can be further applied. Our research shows the popularity of leveraging convolutional graph neural networks (ConGNNs) for microservice-based applications in the current design of cloud systems and the emerging area of adopting spatio-temporal graph neural networks (STGNNs) and dynamic graph neural networks (DGNNs) for more advanced studies. Full article
(This article belongs to the Special Issue Machine Learning and Data Analytics for Edge Cloud Computing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop