Learning Based Content Caching and Sharing for Wireless Networks

To satisfy rapidly increasing multimedia service requests from mobile users, content caching at the network edges (e.g., base stations) has been regarded as a promising technique in future mobile networks. In this paper, by virtue of Deep Reinforcement Learning (DRL) with respect to solving complicated control problems, we propose a framework on Double Deep Q-Network for cooperative edge caching in mobile networks. Particularly, we aim at minimizing the long-term average content fetching delay of mobile users without requiring any priori knowledge of content popularity distribution. Trace-driven simulation results show that our proposed framework outperforms some existing caching algorithms, including Least Recently Used (LRU), Least Frequently Used (LFU) and First-In First-Out (FIFO) caching strategies by 7%, 11% and 9% improvements, respectively. Besides, our proposed work is further shown that only average 4% performance loss exists compared to an omniscient oracle algorithm.

This paper studies base station (BS) cooperation in nonuniform heterogeneous networks. Considering the limited capacity at BS and existence of untrusted small cell BSs (SBSs) in practical scenarios, a novel capacity- and trust-aware BS cooperation strategy is proposed. The BS cooperation is performed in a user centric manner, based on the average received signal strength at users, the capacity of BSs, and the trustworthiness of SBSs. Furthermore, with the proposed BS cooperation, the statistics of aggregate information-signal strength and interference strength are theoretically analyzed, based on stochastic geometry. Then, expressions for spectral efficiency (SE) and area SE (ASE) are analytically derived. In addition, to study the impact of the SBS density on the SE and ASE, the optimal densities of normal SBSs to maximize the SE and ASE are proved to exist and obtained. Finally, simulations and numerical evaluations validate the theoretical analysis and reveal that with the awareness of BS capacity and trustworthiness, optimal cooperative thresholds achieving the maximum SE and ASE exist, which decrease with high path-loss exponent; and in high path-loss fading environment with high existence probability of untrusted SBSs, more normal SBSs are required to be deployed to achieve the maximum SE and ASE performance.

In this paper, we investigate the capacity scaling laws of content-centric hybrid wireless networks, where users aim to retrieve content stored in the network rather than to maintain source-destination communication. A total of $n$ nodes that have limited storage capacities are assumed to be independently and uniformly distributed in the square area. The storage at in each node is used to cache contents according to proposed caching schemes. A total of $m$ -base stations are regularly placed and act as relays during the content retrieving process. Two different content access schemes are considered: 1) homogeneous content access scheme, where each content is requested and cached with equal probability; and 2) heterogenous content access scheme, where the cached probability of each content is different and the requested contents follow a Zipf content popularity distribution. We present the closed form capacity formulae for the two different content access schemes in order sense, respectively. We also discuss the impact of the number of nodes $n$ , the number of base stations $m$ , the storage capacities of nodes $C$ , cached probability of content $q_{j}$ , and content popularity distribution $p_{j}$ on the capacity scaling. The capacity can be improved by increasing the storage capacities of nodes and adding base stations in the networks under homogeneous content access scheme. Under the heterogeneous content access scheme, increasing the cached probability of content and adding the base stations in the networks can effectively improve the capacity. We also present the capacity under different exponent of content popularity distribution. Finally, we compare our results with previous work, which appear as special cases of our work.

We consider a cellular network where base stations can cooperate to determine the signals to be transmitted on the downlink. In such a scenario, it would be possible to use macroscopic transmit beamforming to improve system performance. The downlink beamformer of interest is generalised from some transmit beamformers that have been shown to meet various optimality criteria in the literature. The particular downlink beamformer structure enables us to recast our downlink beamforming problem as a virtual LMMSE estimation problem. Based on this virtual set up, we exploit the structure of the channel and develop distributed beamforming algorithms using local message passing between neighbouring base stations. Two algorithms are outlined, both of which are based on the Kalman smoothing framework. The first algorithm is a forward-backward algorithm that produces optimal performance, but it has the disadvantage of a delay that grows linearly with array size. The second algorithm, which is a limited extent algorithm, solves the delay problem by using only local information

We consider a mobile network consisting of both the wireless access network and the backhaul network. All base stations in the access network and gateways in the backhaul network are equipped with caches, so that routing costs for serving content requests can be reduced by caching the requested content items closer to the users. In this case, user association in the wireless access network must be aware of both the quality of wireless channels and the content caching strategy. In this paper, we propose a framework that jointly optimizes wireless user association and content caching in both access and backhaul networks. The resulting problem is NP-hard. We propose a polynomial-time algorithm based on convex approximation and pipage rounding that produces a solution within a constant factor of 1 − 1/e from the optimal. Simulation results show that the proposed joint algorithm outperforms schemes that combine cache-independent user association methods with traditional caching strategies (e.g. LRU) in terms of minimizing the aggregate routing cost and backhaul traffic while achieving a high data sum rate in the access network.

In cellular systems, BSs (base stations) are ideally desired to be located in the center of cells, but it is sometimes impossible because of the physical and/or social restrictions on the BS setting space. This paper considers the influence of the displacement of the BS location on BS cooperation (BSC) scheme in MIMO (multiple input multiple output) cellular system. For this aim, BS locations are given on fixed points of circles with different radius and rotation angle. The performances of transmission algorithms with and without BSC are quantitatively evaluated under several typical BS locations through computer simulations. The results show the BS location has certain impact, but the BSC is still effective under the BS displacement.

5G introduces massive multiple-input multiple-output (M-MIMO) with analog beamforming (BF) in millimeter-wave (mmW) bands. 5G Evolution (5GE), which will be actualized around 2025, is expected to replace analog BF with hybrid or fully digital BF that can improve mmW-band downlink and uplink transmission performances. In addition, base station (BS) cooperation technologies are required for 5GE to provide stable and reliable cell-edge transmission in the mmW bands, even when mobile stations (MSs) travel at high speed. This paper introduces our developed 28 GHz-band trial equipment employing our proposed BS cooperation technologies with digital BF and distributed MIMO. It also shows evaluation results of outdoor experimental trials at two MSs' velocity of 90 km/h. Three M-MIMO antennas are deployed in the trials, and the BS cooperation selects one M-MIMO antenna instantly or performs BS cooperative transmission. It is verified that the BS cooperation can improve areal throughput and maintain high throughput in a wider area than non-BS cooperation.

The mobile edge caching is a promising way to reduce the user-perceived delay and improve the transmission data rates for the wireless networks. However, the cache capacities of base stations (BSs) tend to be limited and users’ interests for the contents are diverse, which makes the content placement decision critical for the network performance optimization. Besides, due to the flexible user-BS association, it is more complicated to optimize the content delivery and placement which are coupled with each other. This paper investigates the content placement and content delivery strategies in the cache-enabled wireless networks. In particular, the effective capacity , which can characterize the end-to-end user-perceived delay and data rates simultaneously, is introduced as the user’s utility metric. As the content caching and content delivery operate in different time-scales, they are investigated separately. For the content caching, a content placement problem is formulated, where both users’ different active levels and diverse content preferences are considered. Due to the NP-hard nature, the problem is decomposed into two sub-problems, and an iterative association-aware content placement algorithm is proposed. For the content delivery, the user-BS association problem is formulated, and a cache-aware user-BS association algorithm is designed. The performance of the proposed algorithms is evaluated based on the simulations. The numerical results show that the proposed algorithms have a better capability to cope with users’ diverse active levels, and achieve a better performance in terms of effective capacity and fairness level, compared with the existing algorithms.

In a conventional cellular network, a terminal receives signals not only from the base station of that cell, but also from other cell base stations. This inter-cell interference has more impact on the cell-edge users, in multi cell environment. The inter-cell interference degrades the performance of wireless systems. Using Base Station Cooperation, the ability of a mobile station to receive signals from multiple base stations can be utilized as an opportunity to improve the spectral efficiency and to get higher data rates for cell edge users. In multi cell environment using base station cooperation overall interference can be minimized marginally, whereas the interference within the cooperation region is largely reduced. This leads to a question whether it is worth doing cooperation all the time. However increase in terms of throughput may not always be enough to increase the throughput of each of the user .Hence for such a scenario the distinct cooperation scheme is used. The distinct cooperation is a joint transmission scheme in which the selection criterion is based on user’s signal to interference plus noise ratio (SINR) is proposed and the capacity achieved through cooperation is shared equally among the cell-edge users. Here we will analyze the normal operation, full cooperation and distinct cooperation scheme in the downlink environment for cell edge users in cellular network and we will compare and see which method improves the user capacity and data rate.KeywordsCooperative transmissionfull cooperationDistinct cooperationsignal to interference plus noise ratio (SINR)

Many handover algorithms are proposed in the literature. However, to make a better handover and keep the QoS in wireless networks is very difficult. In this paper, we propose a new handover system based on fuzzy logic. The proposed system uses 3 parameters for handoff decision: the change of signal strength of the present Base Station (BS), signal strength from the neighbor BS, and the distance between Mobile Station (MS) and BS. The performance evaluation via simulations shows that proposed system can avoid ping-pong effect and has a good handover decision.

This article performs a unified analysis of three coordinated multipoint (CoMP) transmission strategies in the downlink of mmWave cellular networks, including the fixed-number base station (BS) cooperation (FNC), the fixed-region BS cooperation (FRC), and the interference-aware BS cooperation (IAC). We first develop a comprehensive framework for CoMP operation in cellular networks, and investigate the network performance under a Poisson point process (PPP) model together with mmWave spectrum. To show what fraction of users in the network achieve target reliability for a given signal to interference-plus-noise ratio (SINR)/signal-to-interference ratio (SIR), we derive the SINR/SIR meta distributions, and further obtain the coverage probability as well as mean local delay for the three cooperation strategies. A pivotal intermediate step to compute the performance metrics is the derivation of joint distributions of distances between a typical user and cooperative BSs. Our analysis demonstrates that parameters of blockage have a significant influence on the network performance for the three CoMP schemes. We find that the FRC scheme makes more users achieve the given link reliability for the scenario with a low density of BSs, while the IAC scheme provides better performance for the network with a high density of BSs. Moreover, the optimal CoMP scheme can be approximately selected by considering the nearest distance from the serving BS to user and the radius of the approximate line-of-sight (LoS) region in the cellular networks.

The information-centric networking (ICN) is a promising and significant approach towards the host-to-content interaction. Motivated by the fact that nodes are inhomogeneously distributed to a certain extent in wireless networks, e.g., the distribution of vehicles exhibits cluster phenomenon in some bustling places of urban areas, we study the impacts of inhomogeneous node distribution and local node cooperation on information-centric wireless networks with infrastructure support. The distribution of nodes is assumed to be inhomogeneous as a multiclustering topology. The base stations are assumed to have access to all the contents, which are requested following a popularity distribution. We propose a scheme where each node retrieves the requested content from other nodes or base stations. Based on the number of clusters and that of base stations, we divide the network topology into two cases, i.e., the cluster-dense case and cluster-sparse case, and evaluate the corresponding throughput and delay performance. Finally, under the Zipf's law for content popularity distribution, we investigate the optimal caching problem in the two cases, and obtain the optimized throughput and delay performance.

Device-to-device (D2D) caching network is proposed to cope with the explosively growing traffic of next-generation mobile networks. Given the limited mobile users' (MU) caching capacity, it is significant to decide which contents and how much proportion of each content should be cached. Based on the selfish nature and varied content preference of MUs, we propose a mobility aware caching incentive scheme, in which base stations (BS) reward MUs for sharing contents with others through D2D communication. By solving the problem of maximizing MU utility and minimizing BS cost at the same time, we obtain each MU's caching strategy and optimal unit reward provided by BS with adapted gradient projection algorithm. Comparisons are deliberated with several baseline caching schemes without incentive, in order to measure the performance of the proposed scheme. Simulation results show that under our settings, BS serving cost can be reduced by up to 45.6% when the optimal reward is selected compared with the fair caching scheme, the advantage is more obvious when MUs' mobility speed gets higher. Furthermore, the proposed scheme outperforms greedy caching, fair caching and random caching scheme in terms of MU utility under different distributions of content popularity.

Multicell cooperative processing (MCP) can overcome the detrimental effects of inter-cell interference (ICI). However, since mobile terminals (MTs) need to estimate and feed back channel state information (CSI) related to several cooperative base stations (BSs), reductions in CSI feedback overhead and delay are more demanding in MCP enabled networks. In this paper, a novel overlaid-pilot based CSI feedback scheme for multicell cooperative networks is proposed. MTs directly overlay the received downlink pilot data of all the cooperative BSs on the uplink pilot data and then broadcast it to the cooperative BSs. Each cooperative BS can recover multiple CSIs from the overlaid pilot by a presented overlaid-pilot based channel estimation algorithm. Because the overlaid pilot is fed back on the uplink pilot channel, no extra uplink channel is occupied and the downlink CSI feedback process is with zero-overhead regardless of the number of cooperative BSs. In addition, as it just needs one broadcast to feed back multiple CSIs to BSs, the feedback delay is decreased significantly. Numerical simulations show that the performance of the proposed CSI feedback scheme outperforms the traditional feedback scheme.

Deploying small cell base stations (SBS) under the coverage area of a macro base station (MBS), and caching popular contents at the SBSs in advance, are effective means to provide high-speed and low-latency services in next generation mobile communication networks. In this paper, we investigate the problem of content caching (CC) and user association (UA) for edge computing. A joint CC and UA optimization problem is formulated to minimize the content download latency. We prove that the joint CC and UA optimization problem is NP-hard. Then, we propose a CC and UA algorithm (JCC-UA) to reduce the content download latency. JCC-UA includes a smart content caching policy (SCCP) and dynamic user association (DUA). SCCP utilizes the exponential smoothing method to predict content popularity and cache contents according to prediction results. DUA includes a rapid association (RA) method and a delayed association (DA) method. Simulation results demonstrate that the proposed JCC-UA algorithm can effectively reduce the latency of user content downloading and improve the hit rates of contents cached at the BSs as compared to several baseline schemes.