When machine learning meets Network Management and Orchestration in Edge-based networking paradigms

Shahraki, Amin; Ohlenforst, Torsten; Kreyß, Felix

doi:10.1016/j.jnca.2022.103558

Cited by 17 publications

(5 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current research conditions and athlete training conditions in universities need improvement. Only 23% of universities have standardized testing laboratories, and most research work remains at the theoretical research stage, primarily due to obstacles such as a lack of funding and facilities [4]. In terms of training conditions, many university sports facilities are aging, with 70% of sports fields lacking shower facilities, making it difficult for athletes to meet their post-competition recovery needs.…”

Section: Current Status and Problems In University Sports Information...mentioning

confidence: 99%

Design of a Cloud-Based University Sports Information Management and Big Data Service Platform

Chi,

Wang,

Zhang

2024

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

This research aims to design and implement a cloud-based university sports information management and big data service platform to enhance the efficiency and quality of sports information management in higher education institutions. Traditional sports information management relies heavily on manual processes, leading to issues such as low efficiency and data isolation. This platform integrates cloud computing and big data technologies to achieve efficient data processing, secure information storage, and convenient data sharing. The platform's processing capacity has been increased from manually handling a few hundred megabytes of data to automatically processing over 5 gigabytes per day, significantly improving the efficiency of sports information management. Additionally, the introduction of encryption and access control mechanisms effectively ensures data security and privacy protection. Through the application of this platform, not only has the quality of sports teaching and research been improved, but it also provides a digital solution for sports facility management. This platform offers a new perspective and approach to the informatization of sports in higher education institutions, demonstrating the potential of modern technology in sports information management.

show abstract

Section: Current Status and Problems In University Sports Information...mentioning

confidence: 99%

Design of a Cloud-Based University Sports Information Management and Big Data Service Platform

Chi,

Wang,

Zhang

2024

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

show abstract

“…Generated tasks will need to be offloaded to the appropriate edge location to achieve low latency and high resource utilization, while more computationally intensive tasks will be sent to the core network, which creates a highly dynamic environment together with the large number of tasks [4]. User mobility necessitates quick service migration and minimal communication overhead to achieve high reliability in applications, such as vehicular networks, while the heterogeneity of edge nodes and limited capacity complicates task offloading further [26]. All these factors complicate the network management and orchestration (NMO) of edge VNFs/CNFs, which will have to make decisions in a decentralized fashion to avoid large delays and traffic congestion while minimizing communication and energy costs.…”

Section: Challenges Relating To Rm In 6gmentioning

confidence: 99%

“…Slicing is composed of several phases [53], but we focus on the end-to-end task of allocating resources for each slice and the relevant runtime. Other aspects of end-to-end management include fault management, performance monitoring, and others [26], which do not fall under the category of RM. For a review of non-distributed RL methodologies on end-to-end slicing, see [54], while for more general ML approaches, see [55].…”

Section: End-to-endmentioning

confidence: 99%

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

Karachalios,

Zafeiropoulos,

Kontovasilis

et al. 2023

Electronics

View full text Add to dashboard Cite

6G targets a broad and ambitious range of networking scenarios with stringent and diverse requirements. Such challenging demands require a multitude of computational and communication resources and means for their efficient and coordinated management in an end-to-end fashion across various domains. Conventional approaches cannot handle the complexity, dynamicity, and end-to-end scope of the problem, and solutions based on artificial intelligence (AI) become necessary. However, current applications of AI to resource management (RM) tasks provide partial ad hoc solutions that largely lack compatibility with notions of native AI enablers, as foreseen in 6G, and either have a narrow focus, without regard for an end-to-end scope, or employ non-scalable representations/learning. This survey article contributes a systematic demonstration that the 6G vision promotes the employment of appropriate distributed machine learning (ML) frameworks that interact through native AI enablers in a composable fashion towards a versatile and effective end-to-end RM framework. We start with an account of 6G challenges that yields three criteria for benchmarking the suitability of candidate ML-powered RM methodologies for 6G, also in connection with an end-to-end scope. We then proceed with a focused survey of appropriate methodologies in light of these criteria. All considered methodologies are classified in accordance with six distinct methodological frameworks, and this approach invites broader insight into the potential and limitations of the more general frameworks, beyond individual methodologies. The landscape is complemented by considering important AI enablers, discussing their functionality and interplay, and exploring their potential for supporting each of the six methodological frameworks. The article culminates with lessons learned, open issues, and directions for future research.

show abstract

“…As one of the key technologies in the design and application of intelligent sports recognition and response APP, the analysis of the application effect of intelligent sports recognition and response APP in university sports teaching can improve the efficiency of intelligent sports recognition and response APP on the one hand, and improve the design ideas and solutions of intelligent sports recognition and response APP on the other hand [4]. Therefore, the analysis method of intelligent sports recognition answering APP and the evaluation method of application effect have been paid attention to and studied by APP software designers, APP teaching and application personnel, scholars and experts [5]. The research of intelligent sports equipment image recognition answering APP teaching application analysis method includes the construction of intelligent sports equipment image recognition answering APP analysis index system and the establishment of effect analysis model algorithm [6].…”

Section: Introductionmentioning

confidence: 99%

Application of Sports Equipment Image Intelligent Recognition Response APP in Sports Training and Teaching

2024

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

INTRODUCTION: The paper addresses the integration of intelligent technology in university physical education, highlighting the need for improved analysis methods for sports equipment image recognition apps to enhance teaching quality.OBJECTIVES: The study aims to develop a more accurate and efficient APP use analysis method for sports equipment image recognition, utilizing intelligent optimization algorithms and kernel limit learning machines.METHODS: The proposed method involves constructing an APP usage effect analysis index system, improving kernel limit learning machines through talent mining algorithms, and validating the model using user behavior data. The method integrates a talent mining algorithm to enhance the kernel limit learning machine (KELM). This integration aims to refine the learning machine’s ability to accurately analyze the large datasets generated by the APP's use, optimizing the parameters to improve prediction accuracy and processing speed.RESULTS: Preliminary tests on the sports equipment image intelligent recognition response APP demonstrate improved accuracy and efficiency in analyzing the APP's usage effects in physical education settings. The study compares the performance of the TDA-KELM algorithm with other algorithms like ELM, KELM, GWO-KELM, SOA-KELM, and AOA-KELM. The TDA-KELM algorithm showed the smallest relative error of 0.025 and a minimal time of 0.0025, indicating higher accuracy and efficiency. The analysis highlighted that the TDA-KELM algorithm outperformed others in analyzing the usage effects of sports equipment image recognition apps, with lower errors and faster processing times.CONCLUSION: The study successfully develops an enhanced APP use analysis method, showcasing potential for more accurate and real-time analysis in the application of sports equipment image recognition in physical education.

show abstract

When machine learning meets Network Management and Orchestration in Edge-based networking paradigms

Cited by 17 publications

References 111 publications

Design of a Cloud-Based University Sports Information Management and Big Data Service Platform

Design of a Cloud-Based University Sports Information Management and Big Data Service Platform

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

Application of Sports Equipment Image Intelligent Recognition Response APP in Sports Training and Teaching

Contact Info

Product

Resources

About