Suzhi Bi

Boyuan Li, Mingze Gong, Shuoyao Wang et al.

Semantic communication has emerged as a promising paradigm for improving transmission efficiency by conveying task-relevant semantics rather than raw data. Although recent studies have achieved notable gains in communication efficiency and average task performance, reliability remains a fundamental bottleneck in dynamic and uncertain environments. In particular, most existing designs are still optimized mainly for average-case behavior, while lower-tail performance under adverse transmission conditions remains insufficiently understood and inadequately protected. In this article, we present a unified perspective on reliable semantic communication beyond average performance. We first review three reliability-oriented design categories: channel-aware adaptation, robustness-oriented codec design, and hybrid automatic repeat request (HARQ)-based retransmission. We show that these approaches address reliability from complementary perspectives, but each still has inherent limitations. Motivated by these observations, we discuss two solution directions: robust adaptive semantic communication under imperfect CSI, and joint source-channel-check coding with adaptive retransmission for sample-level reliability enhancement. Finally, we outline several future research directions, including the joint design of robustness and retransmission, reliability metrics beyond averages, and compatibility with existing digital wireless networks.

Boyuan Li, Shuoyao Wang, Suzhi Bi et al.

Semantic communication has emerged as a promising paradigm for improving transmission efficiency and task-level reliability, yet most existing reliability-enhancement approaches rely on retransmission strategies driven by semantic fidelity checking that require additional check codewords solely for retransmission triggering, thereby incurring substantial communication overhead. In this paper, we propose S3CHARQ, a Joint Source-Channel-Check Coding framework with hybrid automatic repeat request that fundamentally rethinks the role of check codewords in semantic communications. By integrating the check codeword into the JSCC process, S3CHARQ enables JS3C, allowing the check codeword to simultaneously support semantic fidelity verification and reconstruction enhancement. At the transmitter, a semantic fidelity-aware check encoder embeds auxiliary reconstruction information into the check codeword. At the receiver, the JSCC and check codewords are jointly decoded by a JS3C decoder, while the check codeword is additionally exploited for perceptual quality estimation. Moreover, because retransmission decisions are necessarily based on imperfect semantic quality estimation in the absence of ground-truth reconstruction, estimation errors are unavoidable and fundamentally limit the effectiveness of rule-based decision schemes. To overcome this limitation, we develop a reinforcement learning-based retransmission decision module that enables adaptive, sample-level retransmission decisions, effectively balancing recovery and refinement information under dynamic channel conditions. Experimental results demonstrate that compared with existing HARQ-based semantic communication systems, the proposed S3CHARQ framework achieves a 2.36 dB improvement in the 97th percentile PSNR, as well as a 37.45% reduction in outage probability.

Yuhan Wang, Suzhi Bi, Ying-Jun Angela Zhang

The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, reconstruction fidelity, and perceptual quality. While recent neural compression methods have improved perceptual performance, they typically operate at fixed points on the RDP surface, requiring retraining to target different tradeoffs. In this work, we propose a training-free framework that leverages pre-trained diffusion models to traverse the entire RDP surface. Our approach integrates a reverse channel coding (RCC) module with a novel score-scaled probability flow ODE decoder. We theoretically prove that the proposed diffusion decoder is optimal for the distortion-perception tradeoff under AWGN observations and that the overall framework with the RCC module achieves the optimal RDP function in the Gaussian case. Empirical results across multiple datasets demonstrate the framework's flexibility and effectiveness in navigating the ternary RDP tradeoff using pre-trained diffusion models. Our results establish a practical and theoretically grounded approach to adaptive, perception-aware compression.

Yuhan Wang, Suzhi Bi, Ying-Jun Angela Zhang et al.

The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP framework. However, existing algorithms either prioritize perceptual quality by sacrificing acceptable distortion, or focus on minimizing MSE for faithful restoration. When the goal shifts or noisy measurements vary, adapting to different points on the DP plane needs retraining or even re-designing the model. Inspired by recent advances in solving inverse problems using score-based generative models, we explore the potential of flexibly and optimally traversing DP tradeoffs using a single pre-trained score-based model. Specifically, we introduce a variance-scaled reverse diffusion process and theoretically characterize the marginal distribution. We then prove that the proposed sample process is an optimal solution to the DP tradeoff for conditional Gaussian distribution. Experimental results on two-dimensional and image datasets illustrate that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.

Weiqiang Jiao, Suzhi Bi, Xian Li et al.

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.

Jia Yan, Suzhi Bi, Ying-Jun Angela Zhang

Device-edge co-inference opens up new possibilities for resource-constrained wireless devices (WDs) to execute deep neural network (DNN)-based applications with heavy computation workloads. In particular, the WD executes the first few layers of the DNN and sends the intermediate features to the edge server that processes the remaining layers of the DNN. By adapting the model splitting decision, there exists a tradeoff between local computation cost and communication overhead. In practice, the DNN model is re-trained and updated periodically at the edge server. Once the DNN parameters are regenerated, part of the updated model must be placed at the WD to facilitate on-device inference. In this paper, we study the joint optimization of the model placement and online model splitting decisions to minimize the energy-and-time cost of device-edge co-inference in presence of wireless channel fading. The problem is challenging because the model placement and model splitting decisions are strongly coupled, while involving two different time scales. We first tackle online model splitting by formulating an optimal stopping problem, where the finite horizon of the problem is determined by the model placement decision. In addition to deriving the optimal model splitting rule based on backward induction, we further investigate a simple one-stage look-ahead rule, for which we are able to obtain analytical expressions of the model splitting decision. The analysis is useful for us to efficiently optimize the model placement decision in a larger time scale. In particular, we obtain a closed-form model placement solution for the fully-connected multilayer perceptron with equal neurons. Simulation results validate the superior performance of the joint optimal model placement and splitting with various DNN structures.

Hong Xing, Osvaldo Simeone, Suzhi Bi

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.

Shuoyao Wang, Suzhi Bi, Ying Jun et al.

The rapid emergence of electric vehicles (EVs) demands an advanced infrastructure of publicly accessible charging stations that provide efficient charging services. In this paper, we propose a new charging station operation mechanism, the JoAP, which jointly optimizes the EV admission control, pricing, and charging scheduling to maximize the charging station's profit. More specifically, by introducing a tandem queueing network model, we analytically characterize the average charging station profit as a function of the admission control and pricing policies. Based on the analysis, we characterize the optimal JoAP algorithm. Through extensive simulations, we demonstrate that the proposed JoAP algorithm on average can achieve 330% and 531% higher profit than a widely adopted benchmark method under two representative waiting-time penalty rates.

Suzhi Bi, Ying Jun Zhang

Smart power grid enables intelligent automation at all levels of power system operation, from electricity generation at power plants to power usage at households. The key enabling factor of an efficient smart grid is its built-in information and communication technology (ICT) that monitors the real-time system operating state and makes control decisions accordingly. As an important building block of the ICT system, power system state estimation is of critical importance to maintain normal operation of the smart grid, which, however, is under mounting threat from potential cyber attacks. In this article, we introduce a graph-based framework for performing cyber-security analysis in power system state estimation. Compared to conventional arithmetic-based security analysis, the graphical characterization of state estimation security provides intuitive visualization of some complex problem structures and enables efficient graphical solution algorithms, which are useful for both defending and attacking the ICT system of smart grid. We also highlight several promising future research directions on graph-based security analysis and its applications in smart power grid.

Wanrong Tang, Suzhi Bi, Ying Jun et al.

As an environment-friendly substitute for conventional fuel-powered vehicles, electric vehicles (EVs) and their components have been widely developed and deployed worldwide. The large-scale integration of EVs into power grid brings both challenges and opportunities to the system performance. On one hand, the load demand from EV charging imposes large impact on the stability and efficiency of power grid. On the other hand, EVs could potentially act as mobile energy storage systems to improve the power network performance, such as load flattening, fast frequency control, and facilitating renewable energy integration. Evidently, uncontrolled EV charging could lead to inefficient power network operation or even security issues. This spurs enormous research interests in designing charging coordination mechanisms. A key design challenge here lies in the lack of complete knowledge of events that occur in the future. Indeed, the amount of knowledge of future events significantly impacts the design of efficient charging control algorithms. This article focuses on introducing online EV charging scheduling techniques that deal with different degrees of uncertainty and randomness of future knowledge. Besides, we highlight the promising future research directions for EV charging control.

Suzhi Bi, Ying Jun Zhang

Accurate state estimation is of paramount importance to maintain the power system operating in a secure and efficient state. The recently identified coordinated data injection attacks to meter measurements can bypass the current security system and introduce errors to the state estimates. The conventional wisdom to mitigate such attacks is by securing meter measurements to evade malicious injections. In this paper, we provide a novel alternative to defend against false-data injection attacks using covert power network topological information. By keeping the exact reactance of a set of transmission lines from attackers, no false data injection attack can be launched to compromise any set of state variables. We first investigate from the attackers' perspective the necessary condition to perform injection attack. Based on the arguments, we characterize the optimal protection problem, which protects the state variables with minimum cost, as a well-studied Steiner tree problem in a graph. Besides, we also propose a mixed defending strategy that jointly considers the use of covert topological information and secure meter measurements when either method alone is costly or unable to achieve the protection objective. A mixed integer linear programming (MILP) formulation is introduced to obtain the optimal mixed defending strategy. To tackle the NP-hardness of the problem, a tree pruning-based heuristic is further presented to produce an approximate solution in polynomial time. The advantageous performance of the proposed defending mechanisms is verified in IEEE standard power system testcases.

Suzhi Bi, Xiaojun Yuan, Ying Jun Zhang

Conventionally, secrecy is achieved using cryptographic techniques beyond the physical layer. Recent studies raise the interest of performing encryption within the physical layer by exploiting some unique features of the physical wireless channel. Following this spirit, we present a novel physical layer encryption (PLE) scheme that randomizes the radio signal using a secret key extracted from the wireless channel under the assumption of channel reciprocity. Specifically, we propose to jointly design the encryption function and the secret-key generation method. On one hand, we establish a sufficient and necessary condition for the encryption function to achieve perfect secrecy. Based on that, several candidate encryption functions are proposed and compared. We show that, given the secret key available to the legitimate users, perfect secrecy can be achieved without compromising the capability of the communication channel. On the other hand, we study the practical design of the secret-key generation method based on the channel reciprocity. We show that, by introducing marginal system overhead, the key agreement between the legitimate users can be done with a high success probability. The performance advantages of the proposed PLE method is verified through comparisons against other existing PLE methods.