Multicast Opportunities Research Articles

Communication-Efficient Coded Computing for Distributed Multi-Task Learning

Distributed multi-task learning (MTL) can jointly learn multiple models and achieve better generalization performance by exploiting relevant information between the tasks. However, distributed MTL suffers from communication bottlenecks, in particular for large-scale learning with a massive number of tasks. This paper considers distributed MTL systems where distributed workers wish to learn different models orchestrated by a central server. To mitigate communication bottlenecks both in the uplink and downlink, we propose coded computing schemes for flexible and fixed data placements, respectively. Our schemes can significantly reduce communication loads by exploiting workers’ local information and creating multicast opportunities for both the server and workers. Moreover, we establish information-theoretic lower bounds on the optimal downlink and uplink communication loads, and prove the approximate optimality of the proposed schemes. For flexible data placement, our scheme achieves the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">optimal</i> downlink communication load, and the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">order optimal</i> uplink communication load that is smaller than 2 times of the information-theoretic optimum. For fixed data placement, the gaps between our communication load and the optimum are within the minimum computation load among all workers, regardless of the number of workers. Experiments demonstrate that our schemes can significantly speed up the training process compared to the traditional approach.

On the Optimality of Data Exchange for Master-Aided Edge Computing Systems

Edge computing has recently garnered significant interest in many Internet of Things (IoT) applications. However, the excessive overhead during data exchange still remains an open challenge, especially for large-scale data processing tasks. This paper considers a master-aided distributed computing system with multiple edge computing nodes and a master node, where the master node helps edge nodes compute output functions. We propose a coded scheme to reduce the communication latency by exploiting computation and communication capabilities of all nodes and creating coded multicast opportunities. More importantly, we prove that the proposed scheme is always optimal, i.e., achieving the minimum communication latency, for arbitrary computing and storage abilities at the master. This extends the previous optimality results in the extreme cases (either the master could compute all input files or compute nothing) to the general case. Finally, numerical results and TeraSort experiments demonstrate that our schemes can greatly reduce the communication latency compared with the existing schemes.

Joint MDS Codes and Weighted Graph-Based Coded Caching in Fog Radio Access Networks

In this paper, we investigate maximum-distance separable (MDS) codes and weighted graph based coded caching in fog radio access networks (F-RANs). In the placement phase, the redundant MDS based coded placement scheme is used to provide redundant coded packets and homogeneous cached contents. The redundant coded packets can be used to construct multicast opportunities for similar requests. In the delivery phase, the weighted graph based coded delivery scheme is conducted based on homogeneous cached contents, which can induce considerable multicast opportunities. By integrating the above two schemes, a joint MDS codes and weighted graph based coded caching policy is proposed to minimize the fronthaul load. Finally, we theoretically analyze the performance of the proposed policy by deriving the lower and upper bounds of the fronthaul load. Simulation results show that our proposed policy can provide 44% savings in the fronthaul load compared to the MDS-based uncoded delivery policy.

Energy-Aware Coded Caching Strategy Design With Resource Optimization for Satellite-UAV-Vehicle-Integrated Networks

The Internet of Vehicles (IoV) can offer safe and comfortable driving experience, by the enhanced advantages of space&#x2013;air&#x2013;ground-integrated networks (SAGINs), i.e., global seamless access, wide-area coverage, and flexible traffic scheduling. However, due to the huge popular traffic volume, limited cache/power resources, and the heterogeneous network infrastructures, the burden of backhaul link will be seriously enlarged, degrading the energy efficiency of IoV in SAGIN. In this article, to implement the popular content severing multiple vehicle users (VUs), we consider a cache-enabled satellite-UAV-vehicle-integrated network (CSUVIN), where the geosynchronous Earth orbit (GEO) satellite is regard as a cloud server, and unmanned aerial vehicles are deployed as edge caching servers. Then, we propose an energy-aware coded caching strategy employed in our system model to provide more multicast opportunities, and to reduce the backhaul transmission volume, considering the effects of file popularity, cache size, request frequency, and mobility in different road sections (RSs). Furthermore, we derive the closed-form expressions of total energy consumption both in single-RS and multi-RSs scenarios with asynchronous and synchronous services schemes, respectively. An optimization problem is formulated to minimize the total energy consumption, and the optimal content placement matrix, power allocation vector, and coverage deployment vector are obtained by well-designed algorithms. We finally show, numerically, our coded caching strategy can greatly improve energy efficient performance in CSUVINs, compared with other benchmarked caching schemes under the heterogeneous network conditions.

Design and Analysis of Coded Caching Schemes in Stochastic Wireless Networks

Coded caching is a technique that promises significant reductions in network traffic by exploiting the multicast opportunities among multiple cache-enabled users. Most works in this area investigate the fundamental performance limits of coded caching from an information-theoretic perspective. In this paper, from a practical perspective, we focus on the design and analysis of the coded caching scheme in large-scale stochastic networks with dynamic traffic. Aiming at the challenges of the large number of users, dynamic packet requests, and distance-dependent interference, the packet caching scheme and packet delivery scheme are jointly designed to ensure the availability of the coded caching gain. To characterize the coded caching performance, the queue dynamic of the packet requests and channel state are first analyzed. Then by combining the successive group decoding theory and stochastic geometry approach, the network interference is characterized and the successful transmission probability of the multicast coded signal is further derived. Moreover, the coded caching scheme is optimized to minimize the average delay of the packet request, which is proved to ensure service fairness and reduce the complexities of network performance analysis. The analytical and numerical results provide useful insights for the provisioning and planning of the coded caching network.

An Approach to Reduce the Redundancy of Placement Delivery Array Schemes for Random Demands

Centralized coded caching schemes have been widely studied in wireless networks. Placement delivery array (PDA) can be used to generate a coded caching scheme with low subpacketization when all the requested files are different. However, all existing schemes based on PDA design treat the request of each user as an independent file, without leveraging the multicast opportunities when one file is requested by several users. In this letter, for any existing scheme based on PDA design, after its coded multicast messages generation, we proposed an approach to remove the redundant multicast messages.

Optimal Wireless Streaming of Multi-Quality 360 VR Video By Exploiting Natural, Relative Smoothness-Enabled, and Transcoding-Enabled Multicast Opportunities

In this paper, we would like to investigate the optimal wireless streaming of a multi-quality tiled 360 virtual reality (VR) video from a server to multiple users. To this end, we propose to maximally exploit potential multicast opportunities by effectively utilizing characteristics of multi-quality tiled 360 VR videos and computation resources at the users' side. In particular, we consider two requirements for quality variation in one field-of-view (FoV), i.e., the absolute smoothness requirement and the relative smoothness requirement, and two video playback modes, i.e., the direct-playback mode (without user transcoding) and transcode-playback mode (with user transcoding). Besides natural multicast opportunities, we introduce two new types of multicast opportunities, namely, relative smoothness-enabled multicast opportunities, which allow a flexible tradeoff between viewing quality and communications resource consumption, and transcoding-enabled multicast opportunities, which allow a flexible tradeoff between computation and communications resource consumptions. Then, we establish a novel mathematical model that reflects the impacts of natural, relative smoothness-enabled, and transcoding-enabled multicast opportunities on the average transmission energy and transcoding energy. Based on this model, we optimize the transmission resource allocation, playback quality level selection, and transmission quality level selection to minimize the energy consumption in the four cases with different requirements for quality variation and video playback modes. By comparing the optimal values in the four cases, we prove that the energy consumption reduces when more multicast opportunities can be utilized. Finally, numerical results show substantial gains of the proposed solutions over existing schemes, and demonstrate the importance of exploiting of the three types of multicast opportunities.

On the Optimal Load-Memory Tradeoff of Cache-Aided Scalar Linear Function Retrieval

Coded caching has the potential to greatly reduce network traffic by leveraging the cheap and abundant storage available in end-user devices so as to create multicast opportunities in the delivery phase. In the seminal work by Maddah-Ali and Niesen (MAN), the shared-link coded caching problem was formulated, where each user demands one file (i.e., single file retrieval). This article generalizes the MAN caching problem formulation from single file retrieval on the binary filed to general scalar linear function retrieval on an arbitrary finite field. The proposed novel scheme is linear, based on MAN uncoded cache placement, and leverages ideas from interference alignment. Quite surprisingly, the worst-case load of the proposed scheme among all possible demands is the same as the one of the scheme by Yu, Maddah-Ali, and Avestimehr (YMA) for single file retrieval. The proposed scheme has thus the same optimality guarantees as YMA, namely, it is optimal under the constraint of uncoded cache placement, and is optimal to within a factor 2 otherwise. Some extensions of the proposed scheme are then discussed. It is shown that the proposed scheme works not only on arbitrary finite field, but also on any commutative ring. The key idea of this article can be also extended to all scenarios to which the original MAN scheme has been extended, including but not limited to demand-private retrieval and Device-to-Device networks.

Optimal Multi-View Video Transmission in OFDMA Systems

In this letter, we study the transmission of a multi-view video (MVV) to multiple users in an Orthogonal Frequency Division Multiple Access (OFDMA) system. To maximally improve transmission efficiency, we exploit both natural multicast opportunities and view synthesis-enabled multicast opportunities. First, we establish a communication model for transmission of a MVV to multiple users in an OFDMA system. Then, we formulate the minimization problem of the average weighted sum energy consumption for view transmission and synthesis with respect to view selection and transmission power and subcarrier allocation. The optimization problem is a challenging mixed discrete-continuous optimization problem with huge numbers of variables and constraints. A low-complexity algorithm is proposed to obtain a suboptimal solution. Finally, numerical results further demonstrate the value of view synthesis-enabled multicast opportunities for MVV transmission in OFDMA systems.

Optimal Multi-View Video Transmission in Multiuser Wireless Networks by Exploiting Natural and View Synthesis-Enabled Multicast Opportunities

Multi-view videos (MVVs) provide immersive viewing experience, at the cost of traffic load increase for wireless networks. In this paper, we would like to optimize MVV transmission in a multiuser wireless network by exploiting both natural multicast opportunities and view synthesis-enabled multicast opportunities. Specifically, we first establish a mathematical model to specify view synthesis at the server and each user, and characterize its impact on multicast opportunities. This model is highly nontrivial and fundamentally enables the optimization of view synthesis-based multicast opportunities. For given video quality requirements of all users, we consider the optimization of view selection, transmission time and power allocation to minimize the average weighted sum energy consumption for view transmission and synthesis. In addition, under the energy consumption constraints at the server and each user respectively, we consider the optimization of view selection, transmission time and power allocation and video quality selection to maximize the total utility. These two optimization problems are challenging mixed discrete-continuous optimization problems. For the first problem, we propose an algorithm to obtain an optimal solution with reduced computational complexity by exploiting optimality properties. For each problem, to reduce computational complexity, we also propose a low-complexity algorithm to obtain a suboptimal solution, using Difference of Convex (DC) programming. Finally, numerical results show the advantage of the proposed solutions over existing ones, and demonstrate the importance of the optimization of view synthesis-enabled multicast opportunities in MVV transmission.

Joint Pushing and Caching for Bandwidth Utilization Maximization in Wireless Networks

Joint pushing and caching is recognized as an efficient remedy to the problem of spectrum scarcity incurred by tremendous mobile data traffic. In this paper, we design the optimal joint pushing and caching policy to maximize bandwidth utilization, which is of fundamental importance to mobile telecom carriers. In particular, we consider a multiuser wireless network with multicast opportunities where each user is equipped with a cache of limited size. First, we formulate the stochastic optimization problem as an infinite horizon average cost Markov decision process. By the structural analysis, we show that how the optimal policy achieves a balance between the current transmission cost and the future average transmission cost. We also show that the optimal average transmission cost decreases with the cache sizes, revealing a tradeoff between storage and bandwidth. Then, due to the fact that obtaining a numerical optimal solution suffers the curse of dimensionality and implementing it requires a centralized controller and global system information, we develop a low-complexity decentralized policy (LDP) by using a linear approximation of the value function and transforming challenging discrete optimization problems into difference of convex (DC) problems, which can be efficiently solved by using DC algorithms. We also obtain an upper bound on the performance gap between the average cost of LDP and the minimum average cost, which can be easily evaluated. Next, we propose an online decentralized algorithm to implement the proposed LDP, when priori knowledge of user demand processes is not available. Finally, using numerical results, we demonstrate the advantage of the proposed solutions over some existing designs. The results in this paper offer useful guidelines for designing practical cache-enabled multiuser wireless networks.

Decentralized Caching Schemes and Performance Limits in Two-Layer Networks

We study the decentralized caching scheme in a two-layer network, which includes a server, multiple helpers, and multiple users. Basically, the proposed caching scheme consists of two phases, i.e., placement phase and delivery phase. In the placement phase, each helper/user randomly and independently selects contents from the server and stores them into its memory. In the delivery phase, the users request contents from the server, and the server satisfies each user through a helper. Different from the existing caching scheme, the proposed caching scheme takes into account the pre-stored contents at both helpers and users in the placement phase to design the delivery phase. Meanwhile, the proposed caching scheme exploits index coding in the delivery phase and leverages multicast opportunities, even when different users request distinct contents. Besides, we analytically characterize the performance limit of the proposed caching scheme, and show that the achievable rate region of the proposed caching scheme lies within constant margins to the information-theoretic optimum. In particular, the multiplicative and additive factors are carefully sharpened to be $\frac{1}{48}$ and 4, respectively, both of which are better than the state of arts. Finally, simulation results demonstrate the advantage of the proposed caching scheme compared with the state of arts.

Coded Caching Under Arbitrary Popularity Distributions

Caching plays an important role in reducing the backbone traffic when serving high-volume multimedia content. Recently, a new class of coded caching schemes have received significant interest, because they can exploit coded multi-cast opportunities to further reduce backbone traffic. Without considering file popularity, prior works have characterized the fundamental performance limits of coded caching through a deterministic worst-case analysis. However, when heterogeneous file popularity is considered, there remain open questions regarding the fundamental limits of coded caching performance. In this paper, for an arbitrary popularity distribution, we first derive a new information-theoretic lower bound on the expected transmission rate of any coded caching schemes. We then show that a simple coded-caching scheme attains an expected transmission rate that is at most a constant factor away from the lower bound. Unlike other existing studies, the constant factor that we derived is independent of the popularity distribution.

Opportunistic Scheduling of Randomly Coded Multicast Transmissions at Half-Duplex Relay Stations

We consider the multicast scheduling problem for the block transmission of packets in a heterogeneous network using a half-duplex relay station (RS). The RS uses random linear coding to efficiently transmit packets over time-varying multicast channels. Our goal is to minimize the average decoding delay. Because of the half-duplex operation, at each time slot, the RS must decide to either: 1) fetch a new packet for encoding from the base station or 2) multicast a coded packet to wireless users. Thus, optimal scheduling hinges on exploiting multicast opportunities while persistently supplying the encoder (at the RS) with new packets. We formulate an associated fluid control problem and show that the optimal policy incorporates opportunism across multicast channels, i.e., the RS performs a multicast transmission only if the collection of channel conditions is favorable; otherwise, it performs a fetch. Based on the fluid policy, we propose an online algorithm. We prove that our algorithm asymptotically incurs no more than 4/3 and 2 times the optimal delay, for two-user and arbitrary number of user system, respectively. Simulation results show that, in fact, our algorithm’s performance is very close to theoretical bounds.