Dear Colleagues,

Information and communication technology has evolved substantially in recent years, and high-tech equipment is now accessible to help us do our work more efficiently. These gadgets are smarter since they are outfitted with numerous sensors and can collect data from their surroundings. The internet links these gadgets with one another, resulting in the Internet of Things (IoT). Each sensor captures large amounts of data and sends them into the network. The widespread use of IoT in the real world has resulted in a dense network of IoT devices that need effective network management. This paper will look at how machine learning approaches may help us with network management.

Artificial intelligence and machine learning algorithms are designed to be used in network management when a large volume of data are handled. It improves network performance by balancing load and traffic and distributing the bandwidth spectrum based on demand. The machine learning system's sophisticated learning capabilities, cognitive analysis algorithms, and intelligence recognition abilities assist with determining the most efficient data transfer channel. Its high learning ability and predictive analysis aid in forecasting network traffic congestion and allocating extra resources to protect the network from delay and lower latency. More data are pumped into the network when more IoT devices join the network, increasing the volume of data. An ML-powered mobile edge computing model performs the analysis at the source end to avoid redundant data from being pushed into the network. ML-based network management combines varied network topologies such as software-defined networks (SDN), network function virtualisation (NFV), and network slicing with the cognitive intelligence system to increase overall system performance. Future generations will install smart apps, transportation, industries, and smart cities thanks to network virtualization technologies and an effective machine learning methodology. Machine learning approaches for network management come with a slew of issues. The machine learning approach is a time-consuming concept; the model must analyze a large amount of data to comprehend network operation, and network topology optimization is not an immediate outcome. Even though machine learning-based network administration is faster and more effective than manual approaches, it still requires the assistance of a professional to tackle major issues. ML quickly detects network faults and alerts the appropriate team, reducing the manual intervention required to resolve infrastructure-related problems. A portion of the network bandwidth and processing resources should be dedicated to the ML to administer the network properly.

This Special Issue explores how machine learning may help network managers to manage their networks more effectively and the issues they face in implementing it. We encourage machine learning specialists and network professionals to develop new solutions to the problems presented.

Related Topics:

• Energy management of IoMT devices using deep learning techniques;
• Analysis of medical big data using machine learning algorithms;
• Enhancement of deep learning algorithms and techniques in health informatics;
• 5G/6G networks beyond wireless virtualization and its industrial applications;
• Virtual infrastructure management for dense wireless sensor networks;
• Implementation of cyber-physical systems using network virtualization;
• Mobile edge computing for low latency, high transfer rates, and traffic prediction;
• AI-developed networks for network virtualization;
• Networks that enable smart manufacturing and logistics;
• Digital twin-based disaster management systems and their applications;
• Optimized spectrum management for ultra-dense wireless heterogeneous networks;
• ML-based spectrum sharing and traffic handling in wireless virtualization.

Dr. Dilbag Singh
Prof. Dr. Robertas Damaševičius
Dr. Vijay Kumar
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. Journal of Sensor and Actuator Networks 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 1600 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.

• machine learning
• network management
• artificial intelligence
• network virtualization
• cyber-physical systems