Special Issue on Prediction-based caching and computing in cognitive communications
摘要截稿:
全文截稿: 2019-05-01
影响因子: 2.816
期刊难度:
CCF分类: C类
中科院JCR分区:
• 大类 : 计算机科学 - 3区
• 小类 : 计算机:信息系统 - 3区
• 小类 : 工程:电子与电气 - 3区
• 小类 : 电信学 - 3区
Overview
The unprecedented proliferation of mobile devices and the emerging mobile applications call for advanced resource allocation schemes in order to achieve an economical and sustainable operation of cognitive wireless communications. Conventional resource allocation schemes that use iterative or alternative algorithms have critical drawbacks due to their high implementation complexity and long processing delay for managing communication, caching and computation resources. The analysis and prediction of 5G network behavior via AI technologies, including the multi-media traffic load, network overhead, and network collision, have paved the way for flexible caching and computing in cognitive communications, which tremendous potential to reduce the implementation complexity and to enable real-time performance for implementation and it has attracted tremendous research interests.
Due to the extreme range of requirements for user experience, efficiency, performance and complex network environments, the design and optimization of networks becomes very challenging. The future networks are considered to involve robust intelligent algorithms to adapt network protocols and resource management for different services in the corresponding scenarios. Thus, predictive and self-aware network technologies, i.e., resource allocation for caching and computing based on the analysis and prediction of user behavior, have become hot topics. By the implementation of content offloading and/or computation offloading, users’ quality of experience is improved with shorter delay. However, existing solutions cannot fully consider the user behavior, so the prediction-based caching and computing technologies for resource allocation are still a great challenge. Novel design of deep-learning methods and the joint optimization of computation, caching, and communication in cognitive communications remain to be addressed.
The objective of this special section is to focus on state-of-the-art research on resource allocation in cognitive wireless communication networks, machine-learning-based resource allocation frameworks, novel solutions and innovative approaches for prediction-based caching and computing and etc.
The topics of interest include, but are not limited to:
Novel design of deep-learning and convolutional neural network approaches for prediction-based caching and computing.
Resource allocation based on the analysis and prediction of user behavior via AI technologies.
Data analytics and behavior prediction for caching and computing in cognitive communications.
AI-based joint optimization of caching and computing frameworks in cognitive communications.
Transfer learning and reinforcement learning for caching and computing in networking and communications.
Artificial intelligence and machine learning techniques and their applications for caching and computing.
Open-source AI algorithms and software for networking prediction-based caching and computing.