Time-varying Channel Conditions Research Articles

Progressive Unsupervised Domain Adaptation for Radio Frequency Signal Attribute Recognition across Communication Scenarios

As the development of low-altitude economies and aerial countermeasures continues, the safety of unmanned aerial vehicles becomes increasingly critical, making emitter identification in remote sensing practices more essential. Effective recognition of radio frequency (RF) signal attributes is a prerequisite for identifying emitters. However, due to diverse wireless communication environments, RF signals often face challenges from complex and time-varying wireless channel conditions. These challenges lead to difficulties in data collection and annotation, as well as disparities in data distribution across different communication scenarios. To address this issue, this paper proposes a progressive maximum similarity-based unsupervised domain adaptation (PMS-UDA) method for RF signal attribute recognition. First, we introduce a noise perturbation consistency optimization method to enhance the robustness of the PMS-UDA method under low signal-to-noise conditions. Subsequently, a progressive label alignment training method is proposed, combining sample-level maximum correlation with distribution-level maximum similarity optimization techniques to enhance the similarity of cross-domain features. Finally, a domain adversarial optimization method is employed to extract domain-independent features, reducing the impact of channel scenarios. The experimental results demonstrate that the PMS-UDA method achieves superior recognition performance in automatic modulation recognition and RF fingerprint identification tasks, as well as across both ground-to-ground and air-to-ground scenarios, compared to baseline methods.

Deep Learning-Assisted Online Task Offloading for Latency Minimization in Heterogeneous Mobile Edge

With the proliferation of smart devices in recent years, many applications requiring high computing capability and low latency have emerged. Edge computing is one of the promising paradigms to support such applications. Due to the high volatility of edge environments, e.g., frequent movements of mobile devices, varying task sizes, and time-variant channel conditions, we have to make the offloading and resource management decisions on the fly. This paper formulates and studies the problem of online task offloading and resource management in heterogeneous mobile edge environments. The goal of the problem is to minimize the overall system latency. We prove that the problem is NP-hard. Moreover, traditional algorithms needing long decision-making times are insufficient to support applications with high volatility. This paper proposes a deep learning-assisted online algorithm that can make fast decisions. In particular, we design an offline solver for the proposed problem and use a deep neural network to emulate the solver. We conduct extensive simulations to evaluate the proposed approach. Results show that the proposed approach is around <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$50,000\times$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$500\times$</tex-math></inline-formula> faster than the commercial Gurobi solver for the optimal solution and the proposed offline approximation solver, respectively. Moreover, the overall latency under the proposed approach is near-optimal.

Downlink Scheduler for Delay Guaranteed Services Using Deep Reinforcement Learning

In this paper, we propose a novel scheduling scheme to guarantee per-packet delay in single-hop wireless networks for delay-critical applications. We consider several classes of packets with different delay requirements, where high-class packets yield high utility after successful transmission. Considering the correla-tionship of delays among competing packets, we apply a delay-laxity concept and introduce a new output gain function for scheduling decisions. Particularly, the selection of a packet takes into account not only its output gain but also the delay-laxity of other packets. In this context, we formulate a multi-objective optimization problem aiming to minimize the average queue length while maximizing the average output gain under the constraint of guaranteeing per-packet delay. However, due to the uncertainty in the environment (e.g., time-varying channel conditions and random packet arrivals), it is difficult and often impractical to solve this problem using traditional optimization techniques. We develop a deep reinforcement learning (DRL)-based framework to solve it. Specifically, we decompose the original optimization problem into a set of scalar optimization subproblems and model each of them as a partially observable Markov Decision Process (POMDP). We then resort to a Double Deep Q Network (DDQN)-based algorithm to learn an optimal scheduling policy for each subproblem, which can overcome the large-scale state space and reduce Q-value overestimation. Simulation results show that our proposed DDQN-based algorithm outperforms the conventional Q-learning algorithm in terms of reward and learning speed. In addition, our proposed scheduling scheme can achieve significant reductions in average delay and delay outage drop rate compared to other benchmark schemes.

Mapping-varied modulation with labeling optimization for secure transmission in mode-division-multiplexed fiber-optic systems

To improve the physical-layer security of mode-division multiplexing (MDM) systems, a simple security scheme named mapping-varied modulation (MVM) is proposed in this paper by combining cryptographic and information-theoretic security. Specifically, on top of the information-theoretic security provided by the less-conditioned wiretap channel due to the larger mode-dependent loss induced by fiber-bend tapping, the proposed MVM security method varies the mapping rules of the adopted constellations for the subchannels (one subchannel corresponds to one mode) by using the inherently time-varying random channel state information (CSI) of the MDM fiber, under the assumption that an eavesdropper does not know the exact instantaneous CSI of the legitimate link. To maximize the difference among the binary labels of the constellation points in the same position for each subchannel, a labeling optimization method is proposed as well. Numerical results demonstrate the effectiveness of the proposed MVM method via bit-error ratio performance and secrecy rate, showing a potential way to improve the security of the MDM link for high-speed data transmission.

Performance Assessment of an ITU-T Compliant Machine Learning Enhancements for 5G RAN Network Slicing

Network slicing is a technique introduced by 3GPP to enable multi-tenant operation in 5 G systems. However, the support of slicing at the air interface requires not only efficient optimization algorithms operating in real time but also its tight integration into the 5 G control plane. In this paper, we first present a priority-based mechanism enabling defined performance isolation among slices competing for resources. Then, to speed up the resource arbitration process, we propose and compare several supervised machine learning (ML) techniques. We show how to embed the proposed approach into the ITU-T standardized ML architecture. The proposed ML enhancement is evaluated under realistic traffic conditions with respect to the performance criteria defined by GSMA while explicitly accounting for 5 G millimeter wave channel conditions. Our results show that ML techniques are able to provide suitable approximations for the resource allocation process ensuring slice performance isolation, efficient resource use, and fairness. Among the considered algorithms, polynomial regressions show the best results outperforming the exact solution algorithm by 5–6 orders of magnitude in terms of execution time and both neural network and random forest algorithms in terms of accuracy (by 20–40 %), sensitiveness to workload variations and training sample size. Finally, ML algorithms are generally prone to service level agreements (SLA) violation under high load and time-varying channel conditions, implying that an SLA enforcement system is needed in ITU-T's 5 G ML framework.

Dynamic User-Scheduling and Power Allocation for SWIPT Aided Federated Learning: A Deep Learning Approach

Federated learning (FL) has been considered as a promising paradigm for enabling distributed machine learning (ML) in wireless networks. To address the limited energy capacity of wireless devices, we propose a simultaneous wireless information and power transfer (SWIPT) aided FL, in which one FL server (FLS) co-located at a cellular base station (BS) uses SWIPT to simultaneously broadcast the global model to wireless user-devices (UDs) and provide wireless power transfer to them. The UDs then use the harvested energy to train their local models and further transmit the local models to the FLS for aggregation. To improve the spectrum efficiency, we consider that the UDs form a non-orthogonal multiple access (NOMA) group for simultaneously sending their local models over the same spectrum channel. Taking the UDs&#x0027; time-varying available energy and channel conditions into account, we propose a dynamic optimization of the UDs-scheduling, the BS&#x0027;s transmit-power allocation, and the UDs&#x0027; power-splitting factors for SWIPT, with the objective of minimizing the long-term energy consumption while ensuring the FL convergence. The optimization problem, however, is challenging to solve since it is a finite-horizon dynamic programming problem but with an unknown stopping time, and moreover, the action space covers both discrete and continuous variables. To address these difficulties, we first execute a series of equivalent transformations to reduce the number of decision variables and then formulate the problem as a stochastic shortest path problem, based on which we propose an actor-critic deep reinforcement learning algorithm with the proximal policy optimization to efficiently learn the policy that dynamically adjusts the UDs-scheduling for FL as well as the BS&#x0027;s transmit-power for SWIPT. Numerical results validate the effectiveness and performance of our proposed algorithm. The results demonstrate that our proposed algorithm can effectively reduce the long-term energy consumption in comparison with two baseline algorithms.

SlimFL: Federated Learning With Superposition Coding Over Slimmable Neural Networks

Federated learning (FL) is a key enabler for efficient communication and computing, leveraging devices’ distributed computing capabilities. However, applying FL in practice is challenging due to the local devices’ heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions. To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN). Integrating FL with SNNs is challenging due to time-varying channel conditions and data distributions. In addition, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, which makes SNN ill-suited for FL. Motivated by this, we propose a communication and energy-efficient SNN-based FL (named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SlimFL</i> ) that jointly utilizes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">superposition coding (SC)</i> for global model aggregation and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">superposition training (ST)</i> for updating local models. By applying SC, SlimFL exchanges the superposition of multiple-width configurations decoded as many times as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations while avoiding inter-width interference during backpropagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also deals with non-IID data distributions and poor channel conditions, which is also corroborated by data-intensive simulations.

Joint AP Selection and Task Offloading Based on Deep Reinforcement Learning for Urban-Micro Cell-Free UAV Network

The flexible mobility feature of unmanned aerial vehicles (UAVs) leads to frequent handovers and serious inter-cell interference problems in UAV-assisted cellular networks. Establishing a cell-free UAV (CF-UAV) network without cell boundaries effectively alleviates frequent handovers and interference problems and has been an important topic of 6G research. However, in existing CF-UAV networks, a large amount of backhaul data increases the computational pressure on the central processing unit (CPU), which also increases system delay. Meanwhile, the mobility of UAVs also leads to time-varying channel conditions. Therefore, designing dynamic resource allocation schemes with the help of edge computing can effectively alleviate this problem. Thus, aiming at partial network breakdown in an urban-micro (UMi) environment, an urban-micro CF-UAV (UMCF-UAV) network architecture is proposed in this paper. A delay minimization problem and a dynamic task offloading (DTO) strategy that jointly optimizes access point (AP) selection and task offloading is proposed to reduce system delay in this paper. Considering the coupling of various resources and the non-convex feature of the proposed problem, a dynamic resource cooperative allocation (DRCA) algorithm based on deep reinforcement learning (DRL) to flexibly deploy AP selection and task offloading of UAVs between the edge and locally is proposed to solve the problem. Simulation results show fast convergence behavior of the proposed algorithm compared with classical reinforcement learning. Decreased system delay is obtained by the proposed algorithm compared with other baseline resource allocation schemes, with the maximize improvement being 53%.

A Tutorial on Cross-layer Optimization Wireless Network System Using TOPSIS Method

Each other, leading to issues such as interference, limited bandwidth, and varying channel conditions. These challenges require specialized optimization techniques tailored to the wireless environment. In wireless communication networks is to maximize the overall system throughput while ensuring fairness among users and maintaining quality of service requirements. This objective can be achieved through resource allocation optimization, where the available network resources such as bandwidth, power, and time slots are allocated to users in an optimal manner. Optimization-based approaches in wireless resource allocation typically involve formulating the resource allocation problem as an optimization problem with certain constraints.. These techniques provide practical solutions with reduced computational complexity, although they may not guarantee optimality. In summary, optimization-based approaches have been instrumental in studying resource allocation problems in communication networks, including the wireless domain. While techniques from the Internet setting have influenced the understanding of congestion control and protocol design, specific challenges in wireless networks necessitate tailored optimization techniques that account for interference, limited bandwidth, and varying channel conditions. power allocation problem in wireless ad hoc networks Cross-layer optimization refers to the process of jointly optimizing the allocation of resources across different layers of wireless networks, the interactions between different layers become more complex due to the shared medium and time-varying channel conditions. Nash equilibrium, where no user can unilaterally improve its own performance by changing its strategy. Game theory can capture the distributed nature of wireless networks and provide insights into the behavior of users in resource allocation scenarios Additionally, heuristics and approximation algorithms are often employed in wireless resource allocation due to the complexity of the optimization problems involved. In traditional cellular systems, each user is allocated a fixed time slot for transmission, regardless of their channel conditions. However, in opportunistic scheduling. Alternative parameters for “Data rate Ž kbps, Geographic coverage , Service requirements , cost ” Evaluation parameter for “Circuit-switched cell, CDPD, WLAN, Paging, Satellite.” “the first ranking training is obtained with the lowest quality of compensation.”

Double Threshold Structure of Sensor Scheduling Policy Over a Finite-State Markov Channel.

In this article, we consider the optimal sensor scheduling for remote state estimation in cyber-physical systems (CPSs). Different from the existing works concerning the time-invariant channel state in the wireless communication network, our work considers the time-varying channel state modeled by a finite-state Markov channel (FSMC). We focus on the problem of how to schedule the transmission of the sensor to minimize the estimation error at the remote side with less communication cost. Using the framework of the Markov decision process (MDP), the optimal scheduling policy is shown to be deterministic stationary (DS). We further derive its double threshold structure with respect to remote estimation errors and channel states. Moreover, a necessary and sufficient condition guaranteeing the mean-square stability of the remote estimator is given based on the structured scheduling policy. Numerical simulations are provided to verify the theoretical results.

Joint Gradient Sparsification and Device Scheduling for Federated Learning

Federated learning is an attractive distributed learning framework where edge server coordinates edge devices to collaboratively train an artificial intelligence (AI) model while training data stays in edge devices. However, implementing federated learning in an energy-efficient way still faces some problems in practice: i) uploading high-dimensional parameters of edge devices is energy-costly and causes communication congestion; ii) The heterogeneity of edge devices, i.e. non-i.i.d. data, different software/hardware configurations, and time-varying channel conditions, affects training accuracy and convergence rate of federated learning. To address these issues, in this paper, we aim at minimizing energy use of the heterogeneous edge devices while maintaining the learning performance. Note that the effects of sparsification and the number of participating devices are highly coupled, and they have opposite effects on both learning performance and energy consumption. Therefore, the gradient sparsification and device scheduling should be jointly optimized for federated learning. We consider the case where a fraction of heterogeneous devices are scheduled to upload their sparsified local gradients for global aggregation at the server. First, a tradeoff between the sparsification and the number of participating devices is revealed through the convergence rate analysis. Then, a joint optimization problem is formulated to minimize energy consumption under the convergence guarantee. An efficient algorithm is proposed to find the globally optimal solution of the considered non-convex problem. Simulations verify the efficiency of the proposed scheme.

Semantic-Driven Efficient Service Network Towards Smart Healthcare System in Intelligent Fabric

The advantages of intelligent fabrics enable health service systems more efficient and safe to perceive and transmit, where massive sensitive data related to health and behavior are collected through the multi-source flexible sensor network. However, due to its complex network structure, health service systems face the challenge of low-power data transmission and processing in intelligent fabric space. Recently, Deep learning-powered semantic communication (Deep-SC) has emerged as a promising communication paradigm. To tackle the above problem, we introduce the concept of semantic cognition into the cyber-physical system of health service and present the Deep-SC based network service framework for the healthcare system, where physical layer blocks are merged into the traditional communication system to jointly optimize the transceiver in communication. Since semantic encoding and decoding require additional knowledge, consider the introduction of the semantic knowledge base in the system to formulate the joint optimization problem of service offloading and bandwidth allocation in the proposed network service framework, with the goals of reliable semantic communication and efficient network transmission. Furthermore, an online algorithm that optimally adapts service offloading and subcarrier allocation decisions to the time-varying channel conditions is required. Finally, we use a reinforcement learning-based decision algorithm to solve combinatorial optimization problems, which further reduces the computing complexity. Experimental results show that the proposed framework achieves significant performance improvements in system energy consumption and reliable transmission, compared with traditional communication strategies.

Learning-Based IRS-Assisted Secure Transmission for Mine IoTs.

Mine Internet of Things (MIoT) devices in intelligent mines often face substantial signal attenuation due to challenging operating conditions. The openness of wireless communication also makes it susceptible to smart attackers, such as active eavesdroppers. The attackers can disrupt equipment operations, compromise production safety, and exfiltrate sensitive environmental data. To address these challenges, we propose an intelligent reflecting surface (IRS)-assisted secure transmission system for an MIoT device which enhances the security and reliability of wireless communication in challenging mining environments. We develop a joint optimization problem for the IRS phase shifts and transmit power, with the goal of enhancing legitimate transmission while suppressing eavesdropping. To accommodate time-varying channel conditions, we propose a reinforcement learning (RL)-based IRS-assisted secure transmission scheme that enables MIoT device to optimize both the IRS reflecting coefficients and transmit power for optimal transmission policy in dynamic environments. We adopt the deep deterministic policy gradient (DDPG) algorithm to explore the optimal transmission policy in continuous space. This can reduce the discretization error caused by traditional RL methods. The simulation results indicate that our proposed scheme achieves superior system utility compared with both the IRS-free (IF) scheme and the IRS randomly configured (IRC) scheme. These results demonstrate the effectiveness and practical relevance of our contributions, proving that implementing IRS in MIoT wireless communication can enhance safety, security, and efficiency in the mining industry.

Joint Scheduling of Participants, Local Iterations, and Radio Resources for Fair Federated Learning over Mobile Edge Networks

During the training process of Federated learning (FL), proper devices are selected to participate in the training process to avoid model unfairness. In a mobile edge network, participant selection must be considered together with three factors: non-iid datasets possessed by devices, tunable local iterations on devices, and radio resource allocation to counter the impact of time-varying channel conditions on parameter transmissions. Since datasets of devices are given, to ensure model fairness and achieve fast convergence in the FL training process, participants, local iterations, and radio resources must be scheduled jointly in each iteration of FL training. In this paper, the joint scheduling problem is analyzed and formulated. Since it is NP-hard, a heuristic scheduling method called PALORA is designed to conduct joint scheduling of participants, local iterations, and radio resources. PALORA consists of three sequentially interactive function blocks: 1) a pointer network embedded deep reinforcement learning method to select participants, 2) an estimation algorithm to determine the numbers of local iterations, and 3) a breadth-first search method to allocate radio resources to the selected participants. PALORA is evaluated via extensive simulations based on real-world datasets. Results show that it significantly outperforms benchmark approaches.

Swarm Intelligence Based MMSE Frequency Domain Equalization for MIMO Systems

The automatic upgradation of equalizer weights in channel equalization demands a low-complexity, highly accurate estimation of recovery at the minimum possible time. The low-complexity frequency domain equalization improves the minimum mean square error (MMSE) of the equalization process. Adding the superiority of particle swarm optimization (PSO) to the equalizer coefficient selection process enhances the MMSE. This work proposes frequency-domain channel equalization along with a modified PSO (MPSO) as an adaptive algorithm for equalizer weight selection in MIMO systems. The simulation results validate the performance with the time domain linear and decision feedback equalizer structures for BPSK and QAM systems. The parameters are carefully selected by analyzing MMSE thoroughly under timevarying channel conditions.

Task scheduling of computation-intensive graph jobs in UAV-assisted hybrid vehicular networks

As a promising new form in mobile edge computing network, Vehicular Edge Computing (VEC) can further improve the Quality of Service (QoS) of users. However, when edge servers are damaged or overloaded, the requirements of users are difficult met by VEC servers owing to incomplete connectivity and time-varying channel conditions in dynamic and resource-limited vehicular networks. In this paper, we introduce Unmanned Aerial Vehicle (UAV) to enhance the connectivity and total resources in the vehicular networks. Added to that, we focus on the problem of computation-intensive graph jobs scheduling, where the information interactions among the traditional vehicles, autonomous vehicles and UAV are integrated. And the above scheduling problem is modeled as a binary nonlinear programming problem aiming at minimizing average completion delay of jobs. Then, we develop an effective multiple jobs scheduling scheme by considering the scheduling order of multiple jobs, the remaining processing delay of servers, and the available resources of vehicular networks, which consists of two stages: (1) the multiple jobs priority scheduling algorithm for optimizing the jobs scheduling order; (2) the task offloading decision algorithm for optimizing average completion delay of jobs. Finally, the effectiveness of proposed scheme is proved by extensive simulation experiments. Compared with the other schemes, the proposed scheme can effectively reduce average completion delay of jobs.

A time-varying acoustic channel-aware topology control mechanism for cooperative underwater sonar detection network

Topology control plays a vital role in cooperative underwater sonar detection networks (USDNs) to ensure detection applications. By incorporating spatio-temporal uncertainties in acoustic channel and limited resources in underwater networks, a large number of node deployment schemes have been proposed to overcome these difficulties through topology control. However, the channel uncertainty has not been solved fundamentally. In order to effectively deal with the time-space-frequency uncertainty of the acoustic channel, this paper proposes a time-varying acoustic channel-aware (TVAC) topology control mechanism to deploy sonar nodes in USDNs. Initially, a time-varying acoustic channel state information (CSI) estimation algorithm and a prediction algorithm are proposed by applying three sub-modules: a feature stitching deep neural network-based temperature prediction model that we designed, a deep neural network-based sound velocity estimation model, and a BELLHOP-based propagation loss calculation model. After that, a TVAC topology control mechanism is adopted to adaptively deploy nodes based on the CSI estimation and prediction results. Using the improved weighted set covering algorithm, the current CSI is adopted to determine the working modes of sonar nodes, and the predicted CSI is adopted to obtain the cycle of topology update. What is more, we develop an offline–online CSI prediction model to improve the accuracy and stability of node working modes management. Simulation results show that compared with other topology control schemes, TVAC can obtain superior coverage performance, full connectivity, and prolong the network lifetime with guaranteed coverage and connectivity.

DRL-Based Offloading for Computation Delay Minimization in Wireless-Powered Multi-Access Edge Computing

Wireless power transfer (WPT) and edge computing have been validated as effective ways to solve the energy-limited problem and computation-capacity-limited problem of wireless devices (WDs), respectively. This paper studies the wireless-powered multi-access edge computing (WP-MEC) network, where WDs conduct either local computing or task offloading for their individable computation tasks. We aim to minimize total computation delay (TCD) when each WD has a computation task to execute, referred to as the total computation delay minimization (TCDM) problem, by jointly optimizing the offloading-decision, WPT duration, and transmission durations of offloading WDs. The TCDM problem is a mixed integer programming (MIP) problem that is challenging to efficiently obtain the optimal or near-optimal solution. To tackle this challenge, we decompose the TCDM problem into the sub-problem of optimizing the WPT duration and transmission durations, and the top-problem of optimizing the offloading decision. For the nonconvex sub-problem, we design a worst-WD-adjusting (WDA) algorithm to efficiently obtain its optimal solution. For the top-problem, under the time-varying channel conditions, traditional optimization methods are hard to determine the optimal or near-optimal offloading decision within the channel coherence duration. To fast obtain the near-optimal offloading decision, we propose a deep neural networks (DNN)-based deep reinforcement learning (DRL) model, which takes the sub-problem solving as one component for utility evaluation. Finally, numerical results demonstrate that the proposed online DRL-based offloading algorithm achieves the near-minimal TCD with low computational complexity, and is suitable for the fast-fading WP-MEC network.

Optimal Sampling for Data Freshness: Unreliable Transmissions With Random Two-Way Delay

In this paper, we aim to design an optimal sampler for a system in which fresh samples of a signal (source) are sent through an unreliable channel to a remote estimator, and acknowledgments are sent back over a feedback channel. Both the forward and feedback channels could have random transmission times due to time varying channel conditions. Motivated by distributed sensing, the estimator can estimate the real-time value of the source signal by combining the signal samples received through the channel and the noisy signal observations collected from a local sensor. We prove that the estimation error is a non-decreasing function of the Age of Information (AoI) for the received signal samples and design an optimal sampling strategy that minimizes the long-term average estimation error subject to a sampling rate constraint. The sampling strategy is also optimal for minimizing the long-term average of general non-decreasing functions of the AoI. The optimal sampler design follows a randomized threshold strategy: If the last transmission was successful, the source waits until the expected estimation error upon delivery exceeds a threshold and then sends out a new sample. If the last transmission fails, the source immediately sends out a new sample without waiting. The threshold is the root of a fixed-point equation and can be solved with low complexity (e.g., by bisection search). The optimal sampling strategy holds for general transmission time distributions of the forward and feedback channels. Numerical simulations are provided to compare different sampling policies.

Reinforcement learning-based cost-efficient service function chaining with CoMP zero-forcing beamforming in edge networks

As two promising paradigms in emerging 6G wireless systems, service function chaining (SFC) and mobile edge computing (MEC) have attracted insensitive attentions from both industry and academia, and would bring more close-proximity services to 6G users with communication, computing and caching (3C) resources, yet also faced with challenges arising in time-varying channel conditions and resource dynamics. In this work, boosted by recent advents in artificial intelligence and reinforcement learning, we investigate the on-line SFC deployment in the edge of 6G wireless systems via the actor–critic learning framework. First, one long-run cost-efficient SFC deployment problem is investigated, and the coordinated multiple points (CoMP)-based zero-forcing beamforming is utilized to cancel the interference across SFCs. Then, by exploiting the Markov decision processes (MDP) property of long-run SFC deployment, one natural gradient-based actor–critic framework is proposed to characterize edge network dynamics, and meanwhile facilitates the training of neural networks to the global optimum. Next, to lower the size of action space, we follow the principle that a subproblem is embedded into each state–action pair’s critic to solve the reward function, and then utilize both the ℓp(0<p<1) norm-based successive convex approximation (SCA) and proximal center-based dual decomposition to approach the global optimum and accelerate the convergence. Finally, numerical results are used to validate proposed actor–critic approach, showing that the communication resource management deserves special attentions in the SFC deployment in the edge of 6G wireless systems.