This document provides updates to IEEE Std 802.16's MIB for the MAC, PHY and asso- ciated management procedures in order to accommodate recent extensions to the standard.

IEEE Standard for Local and Metropolitan Area Networks Part 16: Air Interface for Fixed Broadband Wireless Access Systems Draft Amendment: Management Information Base Extensions

In this paper, we introduce distributed caching of videos at the base stations of the Radio Access Network (RAN) to significantly improve the video capacity and user experience of mobile networks. To ensure effectiveness of the massively distributed but relatively small-sized RAN caches, unlike Internet content delivery networks (CDNs) that can store millions of videos in a relatively few large-sized caches, we propose RAN-aware reactive and proactive caching policies that utilize User Preference Profiles (UPPs) of active users in a cell. Furthermore, we propose video-aware backhaul and wireless channel scheduling techniques that, in conjunction with edge caching, ensure maximizing the number of concurrent video sessions that can be supported by the end-to-end network while satisfying their initial delay requirements and minimize stalling. To evaluate our proposed techniques, we developed a statistical simulation framework using MATLAB and performed extensive simulations under various cache sizes, video popularity and UPP distributions, user dynamics, and wireless channel conditions. Our simulation results show that RAN caches using UPP-based caching policies, together with video-aware backhaul scheduling, can improve capacity by 300% compared to having no RAN caches, and by more than 50% compared to RAN caches using conventional caching policies. The results also demonstrate that using UPP-based RAN caches can significantly improve the probability that video requests experience low initial delays. In networks where the wireless channel bandwidth may be constrained, application of our videoaware wireless channel scheduler results in significantly (up to 250%) higher video capacity with very low stalling probability.

Video-aware scheduling and caching in the radio access network

Coded caching is effective in leveraging the accumulated storage size in wireless networks by distributing different coded segments of each file in multiple cache nodes. This paper aims to find a wireless coded caching policy to minimize the total discounted network cost, which involves both transmission delay and cache replacement cost, using tools from deep learning. The problem is known to be challenging due to the unknown, time-variant content popularity as well as the continuous, high-dimensional action space. We first propose a clustering based long short-term memory (C-LTSM) approach to predict the number of content requests using historical request information. This approach exploits the correlation of the historical request information between different files through clustering. Based on the predicted results, we then propose a supervised deep deterministic policy gradient (SDDPG) approach. This approach, on one hand, can learn the caching policy in continuous action space by using the actor-critic architecture. On the other hand, it accelerates the learning process by pre-training the actor network based on the solution of an approximate problem that minimizes the per-slot cost. Real-world trace-based numerical results show that the proposed prediction and caching policy using deep learning outperform the considered existing methods.

Deep Learning for Wireless Coded Caching With Unknown and Time-Variant Content Popularity

In heterogeneous wireless networks, different radio access technologies are integrated and may be jointly managed. To optimize composite network performance and capacity, Common Radio Resource Management (CRRM) mechanisms need to be defined. This paper tackles the access technology selection -- a key CRRM functionality -- and proposes a hybrid decision framework to dynamically integrate operator objectives and user preferences. Mobile users make their selection decision based on their needs and preferences as well as on the cost and QoS information signaled by the network. Appropriate decisional information should then be derived so that the network better utilizes its radio resources, while mobile users maximize their own utility. We thus present two tuning policies, namely the staircase and the slope tuning policies, to dynamically modulate this information. Simulation results illustrate the gain from using our tuning policies in comparison with a static one: they lead to better network performance, larger operator gain and higher user satisfaction.

https://hal.archives-ouvertes.fr/hal-01018232/document

A Hybrid Approach for Radio Access Technology Selection in Heterogeneous Wireless Networks

The cache replacement policy is a crucial phase in caching-based systems that deal with the process of selecting applicable cache contents. In this paper, we propose two novel cache replacement algorithms based on the dataset obtained from a typical wireless femto network. In the first algorithm, called Weighted Least Frequently used with an Adaptive Time Window (WLF-ATW), we aim to make a balance between the network's traffic and the recognition of popular contents. The WLF-ATW algorithm takes the frequency and the recency information of files into account to ascertain the popularity of contents. We suggest another new cache replacement policy namely Fairness Scheduling-based with an Adaptive Time Window (FS-ATW) that is based on fairness scheduling in order to minimize the user's access delay. The novelty of our proposed FS-ATW lies in ranking clients according to their last situations that lead to a further user's experience. The effectiveness of these new algorithms is evaluated from the cache hit ratio, transferred byte volume, user's access delay, user's experience, and load balance. A comprehensive numerical evaluation shows that the performance of the proposed WLF-ATW and FS-ATW algorithms is significantly better than some existing cache replacement strategies.

Cache Replacement Schemes Based on Adaptive Time Window for Video on Demand Services in Femtocell Networks

We present the ECOFRAME metro ring network and how we can provide virtual circuit emulation with QoS guarantee at a subwavelegth level. The architecture is based on a centralized HUB and reservations. The scheduler in the HUB reserves a set of rectangles, called a pattern to describe the slots allocated to a node. We study the tradeoff between the complexity of the reservation at the HUB level and the performance of the network: distribution of the end to end delay and utilization of the ring.

Virtual circuit allocation with QoS guarantees in the ECOFRAME optical ring

In this paper, the method UCB-RS, which resorts to recommendation system (RS) for enhancing the upper-confidence bound algorithm UCB, is presented. The proposed method is used for dealing with non-stationary and large-state spaces multi-armed bandit problems. The proposed method has been targeted to the problem of the product recommendation in the online advertising. Through extensive testing with RecoGym, an OpenAI Gym-based reinforcement learning environment for the product recommendation in online advertising, the proposed method outperforms the widespread reinforcement learning schemes such as $\epsilon$-Greedy, Upper Confidence (UCB1) and Exponential Weights for Exploration and Exploitation (EXP3).

Recommendation System-based Upper Confidence Bound for Online Advertising.

Caching is an effective technique to improve the quality of streaming multimedia services. In this paper, we propose a novel content caching scheme referred as “Cache Management using Temporal Pattern based Solicitation” (CMTPS), to further minimize both service delays and load in the network for Video on Demand (VoD) applications. CMPTS is based on the analysis of clients' requests over passed time intervals to predict the contents that will be solicited in the near future. By means of experimental tests, the CMTPS protocol is evaluated. The obtained results show that CMTPS outperforms LRU, in terms of peak traffic reduction and number of cache hits.

Cache management using temporal pattern based solicitation for content delivery

In order to achieve high data rates in future wireless packet switched cellular networks, aggressive frequency reuse is inevitable due to the scarcity of the radio resources. While intra-cell interference is mostly mitigated and can be ignored, inter-cell interference can severely degrade performances with bad channel quality. Hence, Inter-Cell Interference Coordination (ICIC) is commonly identified as a key radio resource management mechanism to enhance system performance of 4G networks. This paper addresses the problem of ICIC in the downlink of Long Term Evolution (LTE) systems where the resource selection process is apprehended as a potential game. Proving the existence of Nash Equilibriums (NE) shows that stable resource allocations can be reached by selfish Base Stations (BS). We put forward a fully decentralized algorithm based on replicator dynamics to attain the pure NEs of the modeled game. Each BS will endeavor to select a set of favorable resources with low interference based on local knowledge only making use of signaling messages already present in the downlink of LTE systems.

Replicator dynamics for distributed Inter-Cell Interference Coordination

In 5G networks, Mobile Edge Computing (MEC) has been proposed to enable computation and storage capabilities at the edge of Radio Access Networks. Proactive content caching in MEC is crucial to guarantee users' Quality of Experience thanks to the reduction of traffic latency. Predicting content popularity plays a key role in the effectiveness of proactive caching. In this paper, we propose a generic and flexible recommendation framework which allows recommending suitable learning and prediction algorithms among available ones, in order to predict content popularity. The investigated algorithms are categorized into two main classes: tree-based regressors and recurrent neural networks. Through the study case of YouTube video solicitation profiles, our proposed method, called Imputation-Boosted Collaborative-Filtering based Recommending Prediction Method (IBCF-RPM) shows its effectiveness in the prediction of content popularity for various popularity profiles. By running only 30% of the prediction algorithms, randomly chosen, on a given content profile, the proposed recommending method is able to estimate the accuracy of the other predictors and recommend a well-suited predictor for content popularity.

Dana Marinca

Papers

Virtual circuit allocation with QoS guarantees in the ECOFRAME optical ring

Recommendation System-based Upper Confidence Bound for Online Advertising.

Cache management using temporal pattern based solicitation for content delivery

Replicator dynamics for distributed Inter-Cell Interference Coordination

Multimedia Content Popularity: Learning and Recommending a Prediction Method