The deployment of 5G wireless communication systems is projected to begin in 2020. With new scenarios, new technologies, and new network architectures, the traffic management for 5G networks will present significant technical challenges. In recent years, AI technologies, especially ML technologies, have demonstrated significant success in many application domains, suggesting their potential to help solve the problem of 5G traffic management. In this article, we investigate the new characteristics of 5G wireless network traffic and discuss challenges they present for 5G traffic management. Potential solutions and research directions for the management of 5G traffic, including distributed and lightweight ML algorithms and a novel AI assistant content retrieval algorithm framework, are discussed.

/pdf/artificial-intelligence-to-manage-network-traffic-of-5g-5djszlhfss.pdf

Artificial Intelligence to Manage Network Traffic of 5G Wireless Networks

This paper focuses on the problem of finding a particular data recommendation strategy based on the user preference and a system expected revenue. To this end, we formulate this problem as an optimization by designing the recommendation mechanism as close to the user behavior as possible with a certain revenue constraint. In fact, the optimal recommendation distribution is the one that is the closest to the utility distribution in the sense of relative entropy and satisfies expected revenue. We show that the optimal recommendation distribution follows the same form as the message importance measure (MIM) if the target revenue is reasonable, i.e., neither too small nor too large. Therefore, the optimal recommendation distribution can be regarded as the normalized MIM, where the parameter, called importance coefficient, presents the concern of the system and switches the attention of the system over data sets with different occurring probability. By adjusting the importance coefficient, our MIM based framework of data recommendation can then be applied to systems with various system requirements and data distributions. Therefore, the obtained results illustrate the physical meaning of MIM from the data recommendation perspective and validate the rationality of MIM in one aspect.

Matching Users' Preference under Target Revenue Constraints in Data Recommendation Systems.

User-in-the-loop (UiL) content delivery is a recently proposed scheme for personalized content retrieval over mobile communication networks. It is a promising scheme that can better manage the overall user quality-of-experience (QoE) throughout the entire content retrieval process. The performance of the scheme, however, has only been investigated in a simplified system model that assumed synchronized user behavior, inflexible delay constraint, and identical quality-of-service (QoS) requirement among users. This paper studies the performance of UiL content delivery scheme in a generalized and realistic system model with asynchronous user behavior, flexible outage delay constraint, and customized user QoS. Heuristic algorithms and theoretical bounds are investigated for the UiL content delivery problem. The proposed system is shown to be effective in managing the user QoE in generalized practical scenarios.

User-In-The-Loop Content Delivery in Cellular Communication Networks with Heterogeneous User Behaviors

Personalized content retrieval service has become a major information service that consumes a large portion of mobile Internet traffic. Joint content recommendation and delivery is a promising design philosophy that could effectively improve the overall user experience with personalized content retrieval services. Existing research mostly focused on a push-type design paradigm called proactive caching, which, however, has multiple inherent drawbacks such as high device cost and low energy efficiency. This paper proposes a novel, interactive joint content recommendation and delivery system as an alternative to overcome the drawbacks of proactive caching systems. We present several optimal and heuristic algorithms for the proposed system and analyze the system performance in terms of user interest and transmission outage probability. Some theoretical performance bounds of the system are also derived. The effectiveness of the proposed system and algorithms is validated by simulation results.

Joint Content Recommendation and Delivery in Mobile Wireless Networks with Outage Management.

The invention discloses a virtual backbone network algorithm suitable for a mobile ad hoc network, and the algorithm comprises the steps: employing a TDMA mechanism, and dividing system time into a plurality of continuous time frames; wherein each time frame is composed of a plurality of time slots, which comprise D special data time slots used for real-time data transmission of backbone nodes, Rrandom data time slots used for transmitting signaling by the non-backbone nodes in a competition manner, one random access time slot provided by the network access application and the network time synchronization of the just-started node; after starting up, the initiating node firstly becomes a backbone node, and according to an algorithm rule, the nodes which do not access the network sequentially access the network to become non-backbone nodes or backbone nodes; in the working process of the network, the connectivity and robustness of the network are ensured through corresponding algorithmrules. Time synchronization of network nodes allowed by the method does not depend on a certain special node (a time reference node), and the method has the advantages of being high in convergence speed, high in destroy resistance and the like.

Haibin Shi

Papers

Joint Content Recommendation and Delivery in Mobile Wireless Networks with Outage Management.

Virtual backbone network algorithm suitable for mobile ad hoc network