With the emergence of communication systems and deep learning techniques, the native intelligence has been envisioned as a primary power of future networks. In this work, we investigate the schemes of distributed communication-computation integrated networks and propose a split learning based solution for multi-gNB intelligence, abbreviated as MgCSL. By carrying out a data-model split mechanism, MgC-SL mitigates the computation requirements of each node and enables more gNBs to participate the collaborative learning tasks. The simulation results verify that such distributed scheme significantly saves the communication and computation costs without the degradation of the task performance. A joint indicator is also formulated for performance analysis. Combining the proposed schemes and the corresponding indicator, some insights and guides for the system designs can be obtained to improve the efficiency of the next-generation network intelligence.

Consider a multi-cell mobile edge computing network, in which each user wishes to compute the product of a user-generated data matrix with a network-stored matrix. This is done through task offloading by means of input uploading, distributed computing at edge nodes (ENs), and output downloading. Task offloading may suffer long delay since servers at some ENs may be straggling due to random computation time, and wireless channels may experience severe fading and interference. This paper aims to investigate the interplay among upload, computation, and download latencies during the offloading process in the high signal-to-noise ratio regime from an information-theoretic perspective. A policy based on cascaded coded computing and on coordinated and cooperative interference management in uplink and downlink is proposed and proved to be approximately optimal for a sufficiently large upload time. By investing more time in uplink transmission, the policy creates data redundancy at the ENs, which can reduce the computation time, by enabling the use of coded computing, as well as the download time via transmitter cooperation. Moreover, the policy allows computation time to be traded for download time. Numerical examples demonstrate that the proposed policy can improve over existing schemes by significantly reducing the end-to-end execution time.

A multi-cell mobile edge computing network is studied, in which each user wishes to compute the product of a user-generated data matrix with a network-stored matrix through data uploading, distributed edge computing, and output downloading. Assuming randomly straggling edge servers, this paper investigates the interplay among upload, compute, and download times in high signal-to-noise ratio regimes. A policy based on cascaded coded computing and on coordinated and cooperative interference management in uplink and downlink is proposed and proved to be approximately optimal for sufficiently large upload times. By investing more time in uplink transmission, the policy creates data redundancy at the edge nodes to reduce both computation times by coded computing, and download times via transmitter cooperation. Moreover, it allows computing times to be traded for download times.

Existing works on task offloading in mobile edge computing (MEC) networks often assume a task is executed once at a single edge node (EN). Downloading the computed result from the EN back to the mobile user may suffer long delay if the downlink channel experiences strong interference or deep fading. This paper exploits the idea of computation replication in MEC networks to speed up the downloading phase. Computation replication allows each user to offload its task to multiple ENs for repetitive execution so as to create multiple copies of the computed result at different ENs which can then enable transmission cooperation and hence reduce the communication latency for result downloading. Yet, computation replication may also increase the communication latency for task uploading, despite the obvious increase in computation load. The main contribution of this work is to characterize asymptotically an order-optimal upload-download communication latency pair for a given computation load in a multi-user multi-server MEC network. Analysis shows when the computation load increases within a certain range, the downloading time decreases in an inversely proportional way if it is binary offloading or decreases linearly if it is partial offloading, both at the expense of linear increase in the uploading time.

In this paper, we exploit computation replication to reduce the communication time for task offloading in mobile edge computing networks, by introducing a tradeoff between computation load and communication latency defined as a pair of the Normalized Uploading Time (NUlT) and Normalized Downloading Time (NDlT). The key idea of replication is to allow mobile users to offload their tasks to multiple edge nodes for repetitive execution so as to enable the transmission cooperation in computed results downloading, and consequently interference mitigation across users. We develop an achievable communication latency pair at a given computation load, where the NUlT is optimal and the NDlT is within a multiplicative gap of 2 to an information theoretic lower bound. We show that in a certain interval, the NDlT can be traded by the computation load in an inversely proportional function.

In mobile edge computing (MEC) systems, mobile devices can offload their computation-intensive tasks to edge servers to save energy and shorten latency. However, the extra latency for downloading the computed results back may degrade the benefits of computation offloading if the downlink channel suffers severe fading and interference. In this work, we exploit computation replication in task offloading to reduce the download latency in multi-user multi-server MEC networks. The main idea is to partition the task generated by each user into multiple subtasks, and offload each subtask to a set of MEC servers via the uplink channel for repeated execution. The duplication of computation results on multiple servers thus enables data-sharing based transmission cooperation to send the results back to users. Next, we adopt an asymptotic total latency that accounts the uploading, computing and results downloading phases as the performance metric to capture the tradeoff between the increased computation load and the reduced communication time. We formulate a linear programming problem to optimize the task partition ratios for minimizing the total latency. We show that there exists an optimal degrees of replication (the number of MEC servers to compute the same subtask) and an associated task partition strategy for optimal latency performance. Our finding reveals great advantage of computation replication for latency reduction in multi-server MEC networks where the output data size of each computation task is non-negligible.

In this paper, we study the probabilistic caching for an N-tier wireless heterogeneous network (HetNet) using stochastic geometry. A general and tractable expression of the successful delivery probability (SDP) is first derived. We then optimize the caching probabilities for maximizing the SDP in the high signal-to-noise ratio regime. The problem is proved to be convex and solved efficiently. We next establish an interesting connection between N-tier HetNets and single-tier networks. Unlike the single-tier network where the optimal performance only depends on the cache size, the optimal performance of N-tier HetNets depends also on the base station (BS) densities. The performance upper bound is, however, determined by an equivalent single-tier network. We further show that with uniform caching probabilities regardless of content popularities, to achieve a target SDP, the BS density of a tier can be reduced by increasing the cache size of the tier when the cache size is larger than a threshold; otherwise, the BS density and BS cache size can be increased simultaneously. It is also found analytically that the BS density of a tier is inverse to the BS cache size of the same tier and is linear to BS cache sizes of other tiers.

Mobile edge computing (MEC) is expected to be an effective solution to deliver 360-degree virtual reality (VR) videos over wireless networks. In contrast to previous computation-constrained MEC framework, which reduces the computation-resource consumption at the mobile VR device by increasing the communication-resource consumption, we develop a communications-constrained MEC framework to reduce communication-resource consumption by increasing the computation-resource consumption and exploiting the caching resources at the mobile VR device in this paper. Specifically, according to the task modularization, the MEC server can only deliver the components which have not been stored in the VR device, and then the VR device uses the received components and the corresponding cached components to construct the task, resulting in low communication-resource consumption but high delay. The MEC server can also compute the task by itself to reduce the delay, however, it consumes more communication-resource due to the delivery of entire task. Therefore, we then propose a task scheduling strategy to decide which computation model should the MEC server operates, in order to minimize the communication-resource consumption under the delay constraint. Finally, we discuss the tradeoffs between communications, computing, and caching in the proposed system.