Characterized by its ease of low-latency response, edge computing is capable of supporting real-time video analytics applications, constituting an edge video analytics paradigm, where the joint knob configuration and network scheduling design has drawn ever-escalating research attention. However, the potential of edge video analytics has not been fully exploited, owing to the limitations of the state-of-the-art as follows. i) The eminent impact of video content on accuracy performance has been ignored. ii) The variables that can be tuned are not fully considered in scheduling. iii) The heuristic algorithm-based solutions are far from the optimal. To fill in this gap, in this paper, we conceive a content-aware joint knob configuration and resource allocation scheme for edge video analytics. Concretely, fed with the features extracted from the video content, a deep neural network (DNN)-based predictor is proposed to predict the configuration-accuracy performance in a real-time manner. With an aid of the predictive results, we formulate an accuracy-maximization problem as an integer programming problem, by optimizing the variables, including resolution, frame rate, video analytic model, network bandwidth, and computational resource subject to the latency constraints. To solve this problem in an efficient manner, we devise a novel low-complexity dynamic programming method. Simulation results verify the efficiency of our content-aware joint knob configuration and resource allocation scheme. Quantitatively, a 3.3% gap is attained towards the upper bound in terms of the accuracy in an object detection scenario, relying on the scheme proposed.

Broadcast plays a vital role in wireless ad hoc networks for information dissemination, while one of the key system parameters for maximizing broadcast performance is the transmission rate. However, due to the entangled impact of various factors on the broadcast performance such as node distribution, interference, transmission rate, and multi-hop links, theoretically modeling of the impact of different parameters on the broadcast performance is intractable, and hence the optimal transmission rate is still unknown. Inspired by the similarity between the process of packet broadcasting and the spreading of contagious diseases, we resort to epidemic theory to propose a tractable approach for modeling the dynamics of message broadcast process in wireless ad hoc networks. To characterize the impact of transmission rate on the broadcast performance, a novel utility function is proposed by jointly considering the packet delivery delay and packet size. Then, we derive the dynamics of packet broadcasting analytically and obtain the approximated expression for the proposed utility function in closed-form. Furthermore, the optimization of the transmission rate is carried out based on our proposed analytical model. Simulation results show that our analytical model can accurately characterize the process of broadcasting under a wide range of system parameters and that optimizing the transmission rate can improve broadcast performance significantly.

Unmanned aerial vehicles (UAVs) are capable of enhancing the coverage of existing cellular networks by acting as aerial base stations (ABSs). Due to the limited on-board battery capacity and dynamic topology of UAV networks, trajectory planning and interference coordination are crucial for providing satisfactory service, especially in emergency scenarios, where it is unrealistic to control all UAVs in a centralized manner by gathering global user information. Hence, we solve the decentralized joint trajectory and transmit power control problem of multi-UAV ABS networks. Our goal is to maximize the number of satisfied users, while minimizing the overall energy consumption of UAVs. To allow each UAV to adjust its position and transmit power solely based on local- rather the global-observations, a multi-agent reinforcement learning (MARL) framework is conceived. In order to overcome the non-stationarity issue of MARL and to endow the UAVs with distributed decision making capability, we resort to the centralized training in conjunction with decentralized execution paradigm. By judiciously designing the reward, we propose a decentralized joint trajectory and power control (DTPC) algorithm with significantly reduced complexity. Our simulation results show that the proposed DTPC algorithm outperforms the state-of-the-art deep reinforcement learning based methods, despite its low complexity.

Data packet routing in aeronauticalad hocnetworks (AANETs) is challenging due to their high-dynamic topology. In this article, we invoke deep learning (DL) to assist routing in AANETs. We set out from the single objective of minimizing the end-to-end (E2E) delay. Specifically, a deep neural network (DNN) is conceived for mapping the local geographic information observed by the forwarding node into the information required for determining the optimal next hop. The DNN is trained by exploiting the regular mobility pattern of commercial passenger airplanes from historical flight data. After training, the DNN is stored by each airplane for assisting their routing decisions during flight relying solely on local geographic information. Furthermore, we extend the DL-aided routing algorithm to a multiobjective scenario, where we aim for simultaneously minimizing the delay, maximizing the path capacity, and maximizing the path lifetime. Our simulation results based on real flight data show that the proposed DL-aided routing outperforms existing position-based routing protocols in terms of its E2E delay, path capacity, as well as path lifetime, and it is capable of approaching the Pareto front that is obtained using global link information.

Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning. The goal is to minimize the accumulated energy consumption of each base station over a complete video streaming session under the constraint that avoids video playback interruptions. To handle the continuous state and action spaces, we resort to deep deterministic policy gradient (DDPG) algorithm for solving the formulated problem. In contrast to previous predictive power allocation policies that first predict future information with historical data and then optimize the power allocation based on the predicted information, the proposed policy operates in an on-line and end-to-end manner. By judiciously designing the action and state that only depend on slowly-varying average channel gains, we reduce the signaling overhead between the edge server and the base stations, and make it easier to learn a good policy. To further avoid playback interruption throughout the learning process and improve the convergence speed, we exploit the partially known model of the system dynamics by integrating the concepts of safety layer, post-decision state, and virtual experiences into the basic DDPG algorithm. Our simulation results show that the proposed policies converge to the optimal policy that is derived based on perfect large-scale channel prediction and outperform the first-predict-then-optimize policy in the presence of prediction errors. By harnessing the partially known model, the convergence speed can be dramatically improved. The code for reproducing the results of this article is available at https://github.com/fluidy/twc2020.

User fairness is an important metric for cellular systems. It has been widely considered for wireless transmission when optimizing radio resource allocation but rarely considered for femto-caching. In this paper, we optimize caching and bandwidth allocation policies to improve long-term user fairness during content placement and content delivery by harnessing heterogeneous user preference. To this end, we maximize the minimal average data rate, where the average is taken over large-and small-scale channel gains as well as individual user requests. This gives rise to a complicated two-timescale optimization problem involving functional optimization. The objective function of the problem does not have closed-form expression due to unknown user preference and channel distributions, and the “variables” to be optimized include a function. To solve such a challenging problem, we first optimize bandwidth allocation policy given arbitrary caching policy, user locations and user requests, whose structure can be found. We next optimize the caching policy given the optimized bandwidth allocation policy. To handle the difficulty of unknown distributions, we resort to stochastic optimization. Simulation results show that optimizing caching policy exploiting user preference can support much higher minimal average rate than optimizing caching policy based on content popularity when user preferences are less similar. Besides, better user fairness can be achieved by optimizing caching policy than by optimizing bandwidth allocation.

Wireless systems are becoming more and more complicated. As a consequence, the expressions of objective function or constraints of many optimization problems are hard or even impossible to derive. In this paper, we propose a model-free framework to learn the mapping from environment parameters to the solutions of generic constrained optimization problems without the labels generated by numerically finding the optimal solution. We use neural networks respectively for parameterizing the policy to be optimized, the Lagrange multiplier function associated with instantaneous constraint, and approximating the unavailable objective function or constraints. We provide learning algorithms to train all the neural networks simultaneously. We reveal the connections of the proposed framework with reinforcement learning, which is a widely recognized tool for model-free problems. Numerical and simulation results demonstrate the efficiency of model-free learning by taking a well-known power control problem as an example.

In this paper, we propose a policy to optimize predictive power allocation for video streaming over mobile networks with deep reinforcement learning. The objective is to minimize the average energy consumption for video transmission under the quality of service constraint that avoids video stalling. To handle the continuous state and action spaces, we resort to deep deterministic policy gradient to solve the formulated problem. In contrast to previous predictive resource policies for video streaming, the proposed policy operates in an on- line and end-to-end manner. By judiciously designing action and state, the policy can exploit future information without explicit prediction. Simulation results show that the proposed policy can converge closely to the optimal policy with perfect prediction of future large-scale channel gains and outperforms the prediction-based optimal policy when prediction errors exist.

The existing proactive caching policies are designed by assuming that all users request contents with identical activity level at uniformly distributed or known locations, among which most of the policies are optimized by assuming that user preference is identical to content popularity. However, these assumptions are not true based on the recent data analysis. In this paper, we investigate what happens without these assumptions. To this end, we establish a framework to optimize caching policy for base stations exploiting heterogeneous user preference, activity level, and spatial locality. We derive success probability and average rate of each user as utility function, respectively, and obtain the optimal caching policy maximizing a weighted sum of average utility (reflecting network performance) and minimal utility of users (reflecting user fairness). To investigate the intertwined impact of individual user request behavior on caching, we provide an algorithm to synthesize user preference from given content popularity and activity level with controlled preference similarity and validate the algorithm with the real datasets. Analysis and simulation results show that exploiting individual user behavior can improve both network performance and user fairness, and the gain increases with the skewness of spatial locality, and the heterogeneity of user preference and activity level.

Recommendation system is able to shape user demands, which can be used for boosting caching gain. In this paper, we jointly optimize content caching and recommendation at base stations to maximize the caching gain meanwhile not compromising the user preference. We first propose a model to capture the impact of recommendation on user demands, which is controlled by a user-specific psychological threshold. We then formulate a joint caching and recommendation problem maximizing the successful offloading probability, which is a mixed integer programming problem. We develop a hierarchical iterative algorithm to solve the problem when the threshold is known. Since the user threshold is unknown in practice, we proceed to propose an ε-greedy algorithm to find the solution by learning the threshold via interactions with users. Simulation results show that the proposed algorithms improve the successful offloading probability compared with prior works with/without recommendation. The ε-greedy algorithm learns the user threshold quickly, and achieves more than 1 - ε of the performance obtained by the algorithm with known threshold.

In this paper, we investigate the optimal caching policy, respectively, maximizing the success probability and area spectral efficiency (ASE) in a cache-enabled heterogeneous network (HetNet), where a tier of multi-antenna macro base stations (MBSs) is overlaid with a tier of helpers with caches. Under the probabilistic caching framework, we resort to stochastic geometry theory to derive the success probability and ASE. After finding the optimal caching policies, we analyze the impact of critical system parameters and compare the ASE with traditional HetNet where the MBS tier is overlaid by a tier of pico BSs (PBSs) with limited-capacity backhaul. Analytical and numerical results show that the optimal caching probability is less skewed among helpers to maximize the success probability when the ratios of MBS-to-helper density, MBS-to-helper transmit power, user-to-helper density, or the rate requirement are small, but is more skewed to maximize the ASE in general. Compared with traditional HetNet, the helper density is much lower than the PBS density to achieve the same target ASE. The helper density can be reduced by increasing cache size. With given total cache size within an area, there exists an optimal helper node density that maximizes the ASE.

Caching at base stations (BSs) is a promising way to offload traffic and eliminate backhaul bottleneck in heterogeneous networks (HetNets). In this paper, we investigate the optimal content placement maximizing the successful offloading probability in a cache- enabled HetNet where a tier of multi-antenna macro BSs (MBSs) is overlaid with a tier of helpers with caches. Based on probabilistic caching framework, we resort to stochastic geometry theory to derive the closed-form successful offloading probability and formulate the caching probability optimization problem, which is not concave in general. In two extreme cases with high and low user-to-helper density ratios, we obtain the optimal caching probability and analyze the impacts of BS density and transmit power of the two tiers and the signal-to-interference-plus-noise ratio (SINR) threshold. In general case, we obtain the optimal caching probability that maximizes the lower bound of successful offloading probability and analyze the impact of user density. Simulation and numerical results show that when the ratios of MBS-to-helper density, MBS-to-helper transmit power and user-to- helper density, and the SINR threshold are large, the optimal caching policy tends to cache the most popular files everywhere.

Caching popular contents at base stations (BSs) is a promising way to unleash the potential of cellular heterogeneous networks (HetNets), where backhaul has become a bottleneck. In this paper, we compare a cache-enabled HetNet where a tier of multi-antenna macro BSs is overlaid by a tier of helper nodes having caches but no backhaul with a conventional HetNet where the macro BSs tier is overlaid by a tier of pico BSs with limited-capacity backhaul. We resort stochastic geometry theory to derive the area spectral efficiencies (ASEs) of these two kinds of HetNets and obtain the closed-form expressions under a special case. We use numerical results to show that the helper density is only 1/4 of the pico BS density to achieve the same target ASE, and the helper density can be further reduced by increasing cache capacity. With given total cache capacity within an area, there exists an optimal helper node density that maximizes the ASE.

Caching popular contents at base stations (BSs) can reduce the backhaul cost and improve the network throughput. Yet whether locally caching at the BSs can improve the energy efficiency (EE), a major goal for fifth generation cellular networks, remains unclear. Due to the entangled impact of various factors on EE such as interference level, backhaul capacity, BS density, power consumption parameters, BS sleeping, content popularity, and cache capacity, another important question is what are the key factors that contribute more to the EE gain from caching. In this paper, we attempt to explore the potential of EE of the cache-enabled wireless access networks and identify the key factors. By deriving closed-form expression of the approximated EE, we provide the condition when the EE can benefit from caching, find the optimal cache capacity that maximizes the network EE, and analyze the maximal EE gain brought by caching. We show that caching at the BSs can improve the network EE when power efficient cache hardware is used. When local caching has EE gain over not caching, caching more contents at the BSs may not provide higher EE. Numerical and simulation results show that the caching EE gain is large when the backhaul capacity is stringent, interference level is low, content popularity is skewed, and when caching at pico BSs instead of macro BSs.

Coordinated multi-point (CoMP) transmission can significantly improve the spectral efficiency of cellular networks. To reduce the training overhead and the complexity for implementing CoMP, an effective way is to divide base stations (BSs) into cooperative clusters. However, with disjointed clusters, the cluster-edge users suffer from inter-cluster interference. In this paper, a scheme is designed to select a set of BSs to serve each user with CoMP coordinated beamforming, where the clusters of different users may overlap. To reduce the signaling overhead, the average net throughput of the network is maximized considering the training overhead. The proposed scheme depends on large-scale channel gains and can be operated in a semi-dynamic manner. A low complexity algorithm is proposed to form the clusters, which achieves similar performance to the optimal solution with exhaustive searching. Simulation results show the proposed algorithm outperforms the existing CoMP joint transmission with dynamic clustering and the Non-CoMP system.