Edge intelligence (EI) allows resource-constrained edge devices (EDs) to offload computation-intensive AI tasks (e.g., visual object detection) to edge servers (ESs) for fast execution. However, transmitting high-volume raw task data (e.g., 4K video) over bandwidth-limited wireless networks incurs significant latency. While EDs can reduce transmission latency by degrading data before transmission (e.g., reducing resolution from 4K to 720p or 480p), it often deteriorates inference accuracy, creating a critical accuracy-latency tradeoff. The difficulty in balancing this tradeoff stems from the absence of closed-form models capturing content-dependent accuracy-latency relationships. Besides, under bandwidth sharing constraints, the discrete degradation decisions among the EDs demonstrate inherent combinatorial complexity. Mathematically, it requires solving a challengingblack-boxmixed-integer nonlinear programming (MINLP). To address this problem, we propose LAB, a novel learning framework that seamlessly integrates deep reinforcement learning (DRL) and Bayesian optimization (BO). Specifically, LAB employs: (a) a DNN-based actor that maps input system state to degradation actions, directly addressing the combinatorial complexity of the MINLP; and (b) a BO-based critic with an explicit model built from fitting a Gaussian process surrogate with historical observations, enabling model-based evaluation of degradation actions. For each selected action, optimal bandwidth allocation is then efficiently derived via convex optimization. Numerical evaluations on real-world self-driving datasets demonstrate that LAB achieves near-optimal accuracy-latency tradeoff, exhibiting only 1.22% accuracy degradation and 0.07s added latency compared to exhaustive search. Notably, it outperforms conventional DRL with 3.29% higher accuracy and 42.60% lower latency, demonstrating its advantageous performance in handling black-box optimization problems. The complete source code for LAB will be published on GitHub upon acceptance.

This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and re-training the encoder/decoder models. To achieve cost-effective transferable system deployment, we propose an efficient Domain Adaptation method for Semantic Edge INference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09% and 21.33% in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications.

The recent advance of edge computing technology enables significant sensing performance improvement of Internet of Things (IoT) networks. In particular, an edge server (ES) is responsible for gathering sensing data from distributed sensing devices, and immediately executing different sensing tasks to accommodate the heterogeneous service demands of mobile users. However, as the number of users surges and the sensing tasks become increasingly compute-intensive, the huge amount of computation workloads and data transmissions may overwhelm the edge system of limited resources. Accordingly, we propose in this paper a scalable edge sensing framework for multi-task execution, in the sense that the computation workload and communication overhead of the ES do not increase with the number of downstream users or tasks. By exploiting the task-relevant correlations, the proposed scheme implements a unified encoder at the ES, which produces a common low-dimensional message from the sensing data and broadcasts it to all users to execute their individual tasks. To achieve high sensing accuracy, we extend the well-known information bottleneck theory to a multi-task scenario to jointly optimize the information gathering and broadcast processes. We also develop an efficient two-step training procedure to optimize the parameters of the neural network-based codecs deployed in the edge sensing system. Experiment results show that the proposed scheme significantly outperforms the considered representative benchmark methods in multi-task inference accuracy. Besides, the proposed scheme is scalable to the network size, which maintains almost constant computation delay with less than 1% degradation of inference performance when the user number increases by four times.

The emerging multi-access edge computing (MEC) technology effectively enhances the wireless streaming performance of 360-degree videos. By connecting a user's head-mounted device (HMD) to a smart MEC platform, the edge server (ES) can efficiently perform adaptive tile-based video streaming to improve the user's viewing experience. Under constrained wireless channel capacity, the ES can predict the user's field of view (FoV) and transmit to the HMD high-resolution video tiles only within the predicted FoV. In practice, the video streaming performance is challenged by the random FoV prediction error and wireless channel fading effects. For this, we propose in this paper a novel two-stage adaptive 360-degree video streaming scheme that maximizes the user's quality of experience (QoE) to attain stable and high-resolution video playback. Specifically, we divide the video file into groups of pictures (GOPs) of fixed playback interval, where each GOP consists of a number of video frames. At the beginning of each GOP (i.e., the inter-GOP stage), the ES predicts the FoV of the next GOP and allocates an encoding bitrate for transmitting (precaching) the video tiles within the predicted FoV. Then, during the real-time video playback of the current GOP (i.e., the intra-GOP stage), the ES observes the user's true FoV of each frame and transmits the missing tiles to compensate for the FoV prediction errors. To maximize the user's QoE under random variations of FoV and wireless channel, we propose a double-agent deep reinforcement learning framework, where the two agents operate in different time scales to decide the bitrates of inter- and intra-GOP stages, respectively. Experiments based on real-world measurements show that the proposed scheme can effectively mitigate FoV prediction errors and maintain stable QoE performance under different scenarios, achieving over 22.1% higher QoE than some representative benchmark methods.

With recent advancements in artificial intelligence (AI), wireless sensing has recently been accepted as an attractive solution to enable accurate detection of human activities by analyzing the radio signal variations of sensor devices (SDs) using a well-trained AI model. However, due to the limited communication and computation resources at SDs, it is impractical to support energy- and delay-sensitive sensing services by solely processing the massive computation workload at local or offloading it to the edge server (ES) for edge inference. To address this problem, we consider in this paper device-edge co-inference in a wireless sensing system where multiple users collaboratively perform a common inference task. In particular, the AI model deployed at each SD can be split into two sequential parts. Each SD executes the former part of AI model at local, and leaves the remaining part computed at the ES. We aim to minimize the energy consumption of SDs subject to a prescribed inference latency requirement. To this end, we formulate a mixed integer non-linear programming (MINLP) to jointly optimize the model splitting point and system resource allocation, where the major difficulty lies in the tight couplings among splitting decisions of collaborative SDs. To solve the problem, we propose an integrated learning and optimization algorithm named LOP, which tackles the combinatorial model splitting by using a deep reinforcement learning (DRL)-based method, and deals with the remaining resource allocation problem via convex optimization. To gain some engineering insights, we study the optimal model splitting design in a practical wireless indoor crowd counting system, where the optimal splitting point exhibits a threshold-based structure related to the user channel gain. Simulation results demonstrate that the proposed LOP algorithm can achieve a near-optimal energy performance with on average 0.8% optimality gap while enjoying a hundredfold reduction in computation delay.

In future B5G/6G broadband communication systems, non-linear signal distortion caused by the impairment of transmit power amplifier (PA) can severely degrade the communication performance, especially when uplink users share the wireless medium using non-orthogonal multiple access (NOMA) schemes. This is because the successive interference cancellation (SIC) decoding technique, used in NOMA, is incapable of eliminating the interference caused by PA distortion. Consequently, each user’s decoding process suffers from the cumulative distortion noise of all uplink users. In this paper, we establish a new and tractable DPD-PA distortion signal model based on real-world measurements, where the distortion noise power is a polynomial function of PA transmit power diverging from the oversimplified linear function commonly employed in existing studies. Applying the proposed signal model, we characterize the capacity rate region of multi-user uplink NOMA by optimizing the user transmit power. Our findings reveal a significant contraction in the capacity region of NOMA, attributable to polynomial distortion noise power. For practical engineering applications, we formulate a general weighted sum rate maximization (WSRMax) problem under individual user rate constraints. We further propose an efficient power control algorithm to attain the optimal performance. Numerical results show that the optimal power control policy under the proposed non-linear PA model achieves on average 13% higher throughput compared to the policies assuming an ideal linear PA model. Overall, our findings demonstrate the importance of accurate PA distortion modeling to the performance of NOMA and provide efficient optimal power control method accordingly.

In future B5G/6G wideband communication systems, non-linear signal distortion caused by the impairment of transmit power amplifier (PA) can severely degrade the communication performance. The performance impact is especially significant when uplink users share the wireless medium using Non-orthogonal Multiple Access (NOMA) scheme. This is because the successive interference cancellation (SIC) information decoding technique of NOMA cannot eliminate the interference caused by the PA non-linear distortion, such that the decoding of each user will suffer from the aggregate distortion noise of all the uplink users. In this paper, we study the impact of PA non-linear distortion on the performance of uplink NOMA. In particular, we first establish a new PA distortion signal model based on real-world measurements, where the distortion noise power is a polynomial function of PA transmit power, instead of a simplified linear function in most existing studies. Under the proposed signal model, we then accurately characterize the capacity region of a two-user uplink NOMA by optimizing the user transmit power. We show that the polynomial distortion noise power significantly shrinks the achievable capacity region of NOMA. This indicates that existing studies may have overestimated the communication performance of NOMA in practical wideband systems. Besides, the non-linear noise power also leads to a rather different optimal power allocation strategy to attain maximum throughput. Simulation results show that, for a PA following the polynomial distortion noise power model, the proposed optimal power allocation method achieves on average 12.2% higher sum throughput than that obtained from ideal PA model. Overall, our results demonstrate the importance of accurate PA distortion modeling to the performance of NOMA and provide an efficient power allocation method to attain the optimal performance.

Under the outbreak of the COVID-19 pandemic, respiration state monitoring plays an important role in assisting respiratory disease diagnosis and treatment. Thanks to the nonintrusive nature and low deployment cost, Wi-Fi-based wireless respiration state monitoring methods have gained increasing popularity. By analyzing the variation of channel state information (CSI) of Wi-Fi signals, the respiration states of a target person under the wireless coverage, such as cough, sneeze, and yawn, can be accurately detected. A major problem of the current wireless respiration state monitoring methods is being overly domain-dependent. That is, a sensing algorithm fine-tuned to a specific device placement and background setting (i.e., a domain) can result in drastic drop in detection accuracy when applied to a dissimilar new domain. To enhance the robustness of wireless sensing and reduce the sensing cost across different domains, we propose in this article a domain-adaptive respiration state monitoring system (ResMon) that achieves highly accurate cross-domain detection performance while requiring very limited labeled samples in the new domain. In a nutshell, the proposed ResMon consists of a source domain meta-training stage and a target domain meta-testing stage. In the meta-training stage, we leverage the rich source domain labeled data set to train an embedding model as a feature extractor of high-dimensional CSI data measurements. In particular, we apply the statistical Bayesian deep learning technique to improve the generalization performance of the embedding model in cross-domain applications. In the meta-testing stage, we combine the embedding model with a few-shot learning technique to train a domain-specific classifier using very limited labeled samples in the target domain. Experiment results show that the proposed ResMon can achieve on average 87.26% cross-domain detection accuracy in a 4-class respiration state classification task using only five labeled samples per class, which significantly outperforms the considered benchmark methods.

This paper considers a wireless powered mobile edge computing (MEC) system consisting of multiple wireless devices (WDs) and one hybrid access point (HAP) broadcasting radio frequency (RF) energy to the WDs. Relying on the harvested energy, the WDs senses data from the monitored environment and execute the task data locally or offload the task to the HAP for edge processing. Given an average power constraint at the HAP, we aim to design an energy-efficient online algorithm under random fading channels to maximize the long-term average data sensing rate of WDs while meeting the system data queue stability. We formulate the target problem as a multi-stage stochastic optimization, where the major difficulty lies in the uncertainty of future channel state and the tight couplings among control decisions over different time slots. To solve this problem, we propose a Lyapunov optimization-based online algorithm named LEESE. Specifically, LEESE equivalently transforms the multi-stage stochastic optimization into per-slot deterministic problems. For each per-slot problem, we derive the optimal closed-form solution. We show that the optimal control on WPT and data processing follows an interesting threshold-based manner decided by the battery state and data queue backlog. Numerical simulations show that the proposed LEESE algorithm can achieve more than 21.9% performance improvement over the considered benchmark methods.

Wireless powered multi-access edge computing (MEC) has emerged as a promising paradigm to enable high-performance computation of energy-constrained wireless devices (WDs) in internet of things (IoT) systems. However, to overcome the severe path loss of both energy transfer and data communications, wireless powered MEC suffers from high operating power consumption. To achieve sustainable and economic system operation, this paper focuses on developing energy-efficient online data processing strategy for wireless powered MEC systems under stochastic fading channels. In particular, we consider a hybrid access point (HAP) transmitting RF energy to and processing the sensing data offloaded from multiple WDs. Under an average power constraint of the HAP, we target at maximizing the long-term average data sensing rate of the WDs while maintaining task data queue stability. To this end, we formulate a multi-stage stochastic optimization problem to control the energy transfer and task data processing in sequential time slots. Without the knowledge of future channel fading, it is very challenging to determine the sequential control actions that are tightly coupled by the battery and data buffer dynamics. To solve the problem, we propose a Lyapunov optimization-based online algorithm named LEESE, which decomposes the multi-stage stochastic problem into per-slot deterministic optimization problems. We show that each per-slot problem can be equivalently transformed into a convex optimization problem. To facilitate online implementation in large-scale MEC systems, instead of solving the per-slot problem with off-the-shelf convex algorithms, we propose a block coordinate descent (BCD)-based method that produces a close-to-optimal solution in less than 0.04% of the computation delay. Simulation results demonstrate that the proposed LEESE algorithm can provide 18% higher data sensing rate than the representative benchmark methods considered, while incurring sub-millisecond computation delay suitable for real-time control under fading channel.

Mobile edge computing (MEC) has recently become a prevailing technique to alleviate the intensive computation burden in Internet of Things (IoT) networks. However, the limited device battery capacity and stringent spectrum resource significantly restrict the data processing performance of MEC-enabled IoT networks. To address the two performance limitations, we consider in this paper an MEC-enabled IoT system with a wireless device (WD) replenishing its battery by means of energy harvesting (EH) and opportunistically accessing the licensed spectrum of an overlaid primary communication link to offload its sensing data to an MEC server (MS) for edge processing. Under time-varying fading channel, random energy arrivals, and stochastic ON-OFF state of the primary link, we aim to design an online algorithm to jointly control the cognitive data sensing rate and processing method (i.e., local and edge processing) without knowing future system information. In particular, we aim to maximize the long-term average sensing rate of the WD subject to quality of service (QoS) requirement of primary link, average power constraint of MS and data queue stability of both MS and WD. We formulate the problem as a multi-stage stochastic optimization and propose an online algorithm named PLySE that applies the perturbed Lyapunov optimization technique to decompose the original problem into per-slot deterministic optimization problems. For each per-slot problem, we derive the closed-form optimal solution of data sensing and processing control to facilitate low-complexity real-time implementation. Interestingly, our analysis finds that the optimal solution exhibits an threshold-based structure related to the current energy state, secondary queueing backlogs and primary link activity. Simulation results collaborate with our analysis and demonstrate more than 46.7% data sensing rate improvement of the proposed PLySE over representative benchmark methods.

This work considers the design of online transmission policy in a wireless-powered communication system with a given energy budget. The system design objective is to maximize the long-term throughput of the system exploiting the energy storage capability at the wireless-powered node. We formulate the design problem as a constrained Markov decision process (CMDP) problem and obtain the optimal policy of transmit power and time allocation in each fading block via the Lagrangian approach. To investigate the system performance in different scenarios, numerical simulations are conducted with various system parameters. Our simulation results show that the optimal policy significantly outperforms a myopic policy which only maximizes the throughput in the current fading block. Moreover, the optimal allocation of transmit power and time is shown to be insensitive to the change of modulation and coding schemes, which facilitates its practical implementation.

In this paper, we consider the design of online transmission policies in a single-user wireless-powered communication system over an infinite horizon, aiming at maximizing the long-term system throughput for the user equipment (UE) subject to a given energy budget. The problem is formulated as a constrained Markov decision process problem, which is subsequently converted into an equivalent Markov decision process (MDP) problem via the Lagrangian approach. The corresponding optimal resource allocation policy is obtained through jointly solving the corresponding MDP problem and updating the Lagrangian multiplier. To reduce the complexity, a sub-optimal policy named “quasi-best-effort” is proposed, where the transmit power of the UE is structurally designed so that in each block the UE either exhausts its entire battery energy for transmission or suspends its transmission. To validate the effectiveness of our proposed policy, extensive numerical simulations are conducted with various system parameters. The results show that the proposed quasi-best-effort policy requires far less computation time but achieves a similar long-term throughput performance as the optimal policy.

Recently researches show that significant energy saving can be achieved by introducing mobile relays into wireless sensor networks. However, due to the extra transceiver circuit energy and the mobility energy consumed by the mobile relay, it is not always better to pass data through the relay rather than to send it from source to destination directly. In this study, the authors study a novel link selection problem in a two‐hop relay scenario where the relay has the ability to move. In this scenario, data from source can be passed through three kinds of links: the direct link, the initial relay link and the adjusted relay link. From the energy‐saving perspective, the optimal moving direction, the position adjustment criterion and the optimal position of the mobile relay are firstly studied through mathematical analysis. Based on a comprehensive discussion of the energy performances of these three kinds of links, and energy‐efficient link selection scheme is then presented. Both the amount of data to be sent and the distance between source and destination are shown to be closely related to the link selection scheme. Finally numerical simulations are carried out to verify the theoretical results.