Learning based Content Caching for Wireless Networks

Caching content of small base stations (SBSs) is a promising approach in the fifth generation (5G) wireless networks for decreasing the transmission delay and energy consumption. The key issue in caching is effective cooperation among SBSs for full usage of the caching to reduce the systems cost. In this paper, we first introduce the architecture of wireless cellular networks with caching in 5G. We divide the caching space into two parts: One caches the fixed content purchased by telecom operators from the remote service providers, and the other one caches contents for wireless transmission. Then, we propose the cooperative caching scheme based on content-exchanged, where each user can get its demanded data from either local SBS or purchasing the contents stored in the neighboring cooperative SBSs. We further prove the concavity of system costs regarding to the proportion between the two parts. We also propose a mechanism to search for the minimal system costs. Finally, by simulations, we prove that the performance of our proposed cooperative caching scheme is better than that of the traditional cache schemes without purchasing the contents between SBSs.

Coded caching is able to exploit accumulated cache size in a wireless network by storing fractions of files in each node. In this work, we model, analyze, and optimize coded caching in cache-enabled small-cell networks (SCNs). We first propose a content delivery framework for coded caching, where multiple small base stations (SBSs) that cache different coded packets of a desired file transmit simultaneously upon a user request and the packets are decoded using successive interference cancellation (SIC)-based receiver. A closed-form expression for the successful transmission probability with SIC receiver in the high signal-to-noise ratio (SNR) region is derived by using stochastic geometry. We next optimize the cache placement to maximize the average fraction of offloaded traffic by the cache-enabled SBSs. The coded cache placement problem is formulated as a multiple-choice knapsack problem (MCKP). By exploiting the analytic properties of the average traffic offload fraction, we propose a greedy but optimal algorithm. Numerical results show our proposed coded caching scheme facilitated by simultaneous transmission and SIC-based receiving significantly outperforms uncoded caching. In addition, the coded caching only needs to split each file into a small number of fragments to approach an ideal performance.

This article explores one of the key enablers of beyond 4G wireless networks leveraging small cell network deployments, proactive caching. Endowed with predictive capabilities and harnessing recent developments in storage, context awareness, and social networks, peak traffic demands can be substantially reduced by proactively serving predictable user demands via caching at base stations and users' devices. In order to show the effectiveness of proactive caching, we examine two case studies that exploit the spatial and social structure of the network, where proactive caching plays a crucial role. First, in order to alleviate backhaul congestion, we propose a mechanism whereby files are proactively cached during off-peak periods based on file popularity and correlations among user and file patterns. Second, leveraging social networks and D2D communications, we propose a procedure that exploits the social structure of the network by predicting the set of influential users to (proactively) cache strategic contents and disseminate them to their social ties via D2D communications. Exploiting this proactive caching paradigm, numerical results show that important gains can be obtained for each case study, with backhaul savings and a higher ratio of satisfied users of up to 22 and 26 percent, respectively. Higher gains can be further obtained by increasing the storage capability at the network edge.

In the next generation of wireless networks, small base stations are being adopted to increase the system's speed and capacity. However, this adoption increases the likelihood of inter-cell interference, which can degrade performance the system. This report discusses different approaches to managing interference that can mitigate these effects. Currently, a few techniques are already in use in 4G systems, while others have been suggested but not put into practice. The purpose of this study is to conduct an analytical examination of the different and various interference management methods that could be utilized in Heterogeneous Networks (HetNets), focusing specifically on HetNets with high density of small cells as they are expected to be part of the network topology for 5G networks and beyond. The study involved implementing time-based enhanced inter-cell interference coordination (eICIC) by establishing coordination between macro and small base stations. The results showed that robust communication with low latency is essential, and backhaul connections play a critical role in achieving this. Consequently, the network's sum-rate was increased.

Wireless content caching in small cell networks has recently been considered as a promising way to alleviate the congestion of the backhaul in emerging heterogenous cellular network. However, how to select files which are cached in SBSs and how to make SBSs work together is an important issue for cooperative cache research for the propose of reducing file download time. In this paper, a Cooperative-Greedy strategy (CGS) among cache-enabled small base stations (SBSs) in small cell network is proposed, in order to minimize the download time of files. This problem is formulated as a Chinese restaurant game.Using this game model, we can configure file caching schemes based on file popularity and the spectrum resources allocated to several adjacent SBSs. Both the existence and uniquencess of a Nash equilibrium are proved. In the theoretical analysis section, SBSs cooperate with each other in order to cache popular files as many as possible near UEs. Simulation results show that the CGS scheme outperforms other schemes in terms of the file-download time.

In this work we investigate optimal geographical caching in heterogeneous cellular networks where different types of base stations (BSs) have different cache capacities. Users request files from a content library according to a known probability distribution. The performance metric is the total hit probability, which is the probability that a user at an arbitrary location in the plane will find the content that it requires in one of the BSs that it is covered by. We consider the problem of optimally placing content in all BSs jointly. As this problem is not convex, we provide a heuristic scheme by finding the optimal placement policy for one type of base station conditioned on the placement in all other types. We demonstrate that these individual optimization problems are convex and we provide an analytical solution. As an illustration, we find the optimal placement policy of the small base stations (SBSs) depending on the placement policy of the macro base stations (MBSs). We show how the hit probability evolves as the deployment density of the SBSs varies. We show that the heuristic of placing the most popular content in the MBSs is almost optimal after deploying the SBSs with optimal placement policies. Also, for the SBSs no such heuristic can be used; the optimal placement is significantly better than storing the most popular content. Finally, we show that solving the individual problems to find the optimal placement policies for different types of BSs iteratively, namely repeatedly updating the placement policies, does not improve the performance.

With the increase in the number of wireless end users, the demand for high-speed wireless network has increased by multiple folds. Moreover, most of the data traffic is observed to be generated from the indoor environment. Hence, researchers have come up with the solution of deploying Small Base Stations (SBSs) in the indoor environment, which proves to be immensely effective in providing the last mile connectivity. However, since the deployment of the SBSs is unplanned, there exists a high chance of co-tier interference, which might be mitigated by transmission power control but at the cost of degraded quality of service for some of the end users. Hence, in this work, we propose the concept of mobile SBSs which are connected to power grids located in the ceiling of the deployment region. The mobile SBSs position themselves at the received signal strength-based centroids of the end user clusters, thereby mitigating the co-tier interference as well as conserving power of the handsets by minimizing the distance between the SBS and the end-user handsets. To enhance the security of the system, the SBSs are considered to form a closed group. The proposed system requires about 13% lesser number of SBSs while enhancing the end-user coverage by 9.3%. Moreover, about 10% improvement has been observed in terms of cumulative throughput for mobile SBSs compared to fixed SBSs. Thus, the deployment of mobile SBSs proves to be more effective compared to the fixed SBSs for indoor communication.

With the growth of mobile data traffic in wireless networks, caches are used to bring data closer to mobile users and to minimize the traffic load on macro base station (MBS). Storing data in caches on user terminals (UTs) and small base stations (SBSs) faces challenges on which data to cache and where to cache these data. The process of deciding the cache contents involves multiple objectives regarding the content popularity, contact duration between UT and SBSs, communication ranges between UT and SBSs caches, and contact probability between UT and SBSs. In this paper, we propose a new strategy on cache placement decisions for mobile edge networks based on binary classification technique. The aim is to formulate the cache placement as a classification problem that is solved using machine learning techniques in order to define an optimal decision boundary on cache or not cache decisions. Simulation results show that the performance of cache placement algorithms using classifier based learning techniques can achieve higher hit rate than other algorithms.

As the demands of coverage and bandwidth increases day by day, the power consumption in wireless network becomes serious issue that needs optimization. Mainly, most of the power in wireless network is consumed in the base stations as transmission power. Reducing the transmission power may affect the QoS at the network. In practice, the network base stations load varies according to the traffic density in the region. Therefore, at low traffic density, most of the base stations are operating on partial load. This fact motivates the concept of blossoming and withering of the small base stations to utilize the full capacity of the operating base stations, and preserving more power by withering the rest of base stations. The rate of change of the network traffic density is not flat throughout the day or week. To accommodate the change of the traffic pattern and optimize the network blossomed and withered small base stations, fuzzy logic inference system is proposed. The proposed fuzzy system measures the traffic of the system and its rate of change and accordingly estimates the percentages of the small base stations to blossom and the delay required to avoid the ping-pong phenomena in the base stations. For the proposed fuzzy to keep track of the current status of the network, the percentage of blossomed small base stations is fed back as input. The results show that the capacity of the network can be maintained during different traffic loads while reducing the total power of transmission by withering some small base stations during low traffic load. The proposed system reserved up to 36.37% of the transmission power.

In this paper, the problem of proactive caching is studied for cloud radio access networks (CRANs). In the studied model, the baseband units (BBUs) can predict the content request distribution and mobility pattern of each user and determine which content to cache at remote radio heads and the BBUs. This problem is formulated as an optimization problem, which jointly incorporates backhaul and fronthaul loads and content caching. To solve this problem, an algorithm that combines the machine learning framework of echo state networks (ESNs) with sublinear algorithms is proposed. Using ESNs, the BBUs can predict each user's content request distribution and mobility pattern while having only limited information on the network's and user's state. In order to predict each user's periodic mobility pattern with minimal complexity, the memory capacity of the corresponding ESN is derived for a periodic input. This memory capacity is shown to capture the maximum amount of user information needed for the proposed ESN model. Then, a sublinear algorithm is proposed to determine which content to cache while using limited content request distribution samples. Simulation results using real data from Youku and the Beijing University of Posts and Telecommunications show that the proposed approach yields significant gains, in terms of sum effective capacity, that reach up to 27.8% and 30.7%, respectively, compared with two baseline algorithms: random caching with clustering and random caching without clustering.

Next generation wireless network (NGWN) will be heterogeneous where different radio access technologies (RATs) coexist. In NGWN, efficient radio resource management and QoS provisioning are major challenges. We propose an optimal joint radio resource management algorithm to minimize call blocking probability in NGWN. The algorithm makes call admission decisions such that overall call blocking probability is minimized in the heterogeneous wireless network. We develop an analytical model for the radio resource management algorithm using a multi-dimensional Markov chain. Based on linear programming optimization technique, we determine the optimal splitting of arriving calls among available RATs. Results show that the proposed algorithm outperforms other algorithm in the heterogeneous wireless network.

The high-paced development of wireless communication technologies brought about the growing need of smart, autonomous, and ultra-high-performance network structures, and the combination of Artificial Intelligence and Machine Learning in the 6G wireless communication networks is a major research issue. The conventional network management techniques cannot support the new demands that include ultra-low latency communications, intelligent spectrum management, mass connectivity, and real-time dynamic resource provision. This paper is a systematically-conducted literature review on the recent research on AI-driven networks, edge AI, federated learning, intelligent radio access network design, and AI-native architecture in next-generation networks based on PRISMA. The review focuses on the possibilities of self-organizing networks, digital twin networks, and smart connectivity that machine learning, deep learning, and autonomous wireless systems provide to the next generation of wireless networks working in terahertz communication ranges and integrated sensing and communication landscape. The findings indicate that AI based resource allocation, intelligent surfaces of reconfigurability, massive mimo optimization and network automation are all effective towards improving spectral efficiency, reliability and energy efficiency of 6G wireless communication. Moreover, the paper has also noted the increased importance of smart security mechanisms, distributed learning, and edge computing in enabling scalable and secure AI-native architectures. The results also indicate that the next generation wireless networks will be based upon intelligent spectrum management, autonomous control, and real-time data analytics to accommodate the new applications in holographic communication, smart cities, extended reality, and connected autonomous systems.

The next generation of wireless networks, 5G, and beyond will bring more complexities and configuration issues to set the new wireless networks, besides requirements for important and new services. These new generations of wireless networks, to be implemented, are in extreme dependence on the adoption of artificial intelligence techniques. The integration of unmanned aerial vehicles (UAV) in wireless communication networks has opened several possibilities with increased flexibility and performance. Besides, they are considered as one of the most promising technologies to be used in the new wireless networks. Thus, UAVs are expected to be one of the most important applications to provide a new way of connectivity to the 5G network, and it is expected to grow from being a 19.3 billion USD industry in 2019 to 45.8 billion USD by 2025. In this paper, we provide a proposal of handover management on aerial 5G network utilizing the fuzzy system. The simulations performed prove the benefits of our proposal by QoS/QoE (quality of service/quality of experience) metrics.

The past three decades have experienced a phenomenal emergence of several wireless networks and technologies. This next generation of wireless networks (4G) will be integrated into one IP-backbone to offer improved services to the user. The features of 4G include: wide coverage, high data rates, seamless roaming and personalisation. This paper presents a personalised handoff decision method to offer personalisation in seamless roaming for the next generation of wireless networks. This is done by assigning profiles to different users with different preferences and using these profiles to offer personalised handoff. The integration of these two important features of 4G networks will provide the end user the ability to choose their own preferred networks while they roam freely between heterogeneous networks.

SummaryWith increase in the number of smart wireless devices, the demand for higher data rates also grows which puts immense pressure to the network. A vast majority of this demand comes from video files, and it is observed that only a few popular video files are requested more frequently during any specified time interval. Recent studies have shown that caching provides a better performance as it minimizes the network load by avoiding the fetching of same files multiple times from the server. In this paper, we propose to combine two ideas; proactive caching of files and content‐based pricing in macro‐femto heterogeneous networks. The femtocell access point (FAP) is allowed to manipulate its users' demand through content‐based pricing and serve the users' requests by proactively downloading suitable content into its cache memory which reduces the load of the femtocell. In addition, an incentive mechanism is also proposed which encourages the FAP to help macrocell users under its coverage zone by allowing access to its cached content and thereby reduces the macrocell load. The proposed content‐based pricing and proactive caching scheme for femtocells is modeled as a Stackelberg game among the macrocell base station and the FAP to jointly maximize both of their utilities. Performance analysis of the scheme is presented for a single femtocell scenario and compared with the conventional flat pricing‐based scheme via numerical examples. The results demonstrate significant reduction in network load using our proposed scheme.