Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He, Maoqing Yao, Guanghui Ren. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Integrating federated learning (FL) with blockchain technology provides an effective solution for enhancing data security and privacy in decentralized IoT ecosystems. However, challenges arise in efficiently achieving consensus and balancing the load across multiple shards, primarily due to the resource constraints and heterogeneity of IoT devices. This paper introduces SynergyMining, a novel collaborative sharding consensus mechanism designed specifically for blockchain-based FL in IoT. SynergyMining leverages reinforcement learning to dynamically optimize consensus group selection, ensuring balanced workloads across shards and efficient resource utilization. Additionally, we propose a freshness and quality-aware FL framework with asynchronous model aggregation called FedFQ that dynamically adjusts aggregation weights based on the recency and quality of local models. This approach mitigates client instability and improves the efficiency of the global model aggregation process. Experimental results demonstrate that SynergyMining outperforms leading algorithms, including Monoxide, HMM, Elastic and ORSP across key performance metrics. Specifically, compared to these algorithms, SynergyMining improves system throughput by 9.97% to 72.16%, final model accuracy by 1.18% to 5.53%, and reduces load imbalance by 6.65% to 16.29%. These advancements, combined with the freshness-aware aggregation, make SynergyMining a robust and scalable solution for IoT-based FL applications, offering significant improvements in efficiency, scalability, and security.

The field of computer vision is currently transitioning from closed-set to open-set tasks. Vision foundation models have already demonstrated success in open-set scenarios. Building on these models, the utilization of a feature supervision framework can further enhance results. Our paper introduces a new method called SAMS (Segment Anything Model using Similar Images), which is a type of feature supervision framework. It is designed to segment specific masks from visual supervision features. Our framework comprises a pre-trained segmentation model and an efficient, novel prompt generation model capable of generating new prompts based on pre-extracted image features. This innovation eliminates the need for manually crafted prompts in the mask generation phase by integrating the principles of one-shot or few-shot learning with visual instructions from similar images. The effectiveness of the SAMS method is evident in its performance across various tasks, particularly in open-set tasks where traditional models tend to struggle. The pretrained model not only achieves impressive mean Intersection over Union (mIOU) scores without incurring additional time loss, but also demonstrates potential for further improvement through targeted module training.

In developing the sixth-generation (6G) system, integrated sensing and communication technology is becoming increasingly essential, especially for applications like autonomous driving. This paper develops an architecture for integrated sensing, communication, and computation (ISCC) in the vehicular network, where vehicles perform environment sensing, sensing data computation, and transmission. To support low-latency cooperation between vehicles and extend vehicles’ sensing range, over-air-computation federated learning is employed. The optimization problem of joint beamforming design and power resource allocation in the ISCC scenario is formulated to maximize the achievable data rate while ensuring sensing and computing performance. However, solving this joint optimization problem is a great challenge due to the high coupling resource and time-varying channel environment. Therefore, a hybrid reinforcement learning scheme is proposed in this work. First, the semidefinite relaxation and Gaussian randomization techniques are leveraged to obtain the approximate solution of the aggregation beamformer. Then, the deep deterministic policy gradient algorithm is proposed to tackle the transmit beamforming design and resource allocation problem in continuous action space. Extensive simulation results validated the admirable performance of the proposed scheme in convergence and achievable sum rate compared with the benchmark schemes. In addition, the impact of variables on the optimization performance is demonstrated via numerical results.

The rapid development of connected autonomous vehicles (CAVs) makes it foreseeable that CAVs will dominate future road traffic. To manage CAV traffic, researchers developed a revolutionary paradigm, which uses intelligent intersection managers (IMs) for a finer-grained control of CAVs' cruising at intersections than traditional traffic lights. However, existing IM-based methods mostly focus on optimizing the single-intersection CAV traffic efficiency, without solving the fundamental problem of maximizing the global efficiency of a multi-intersection road network. Therefore, we address such problem by proposing a system architecture that decomposes each IM into an oracle and a valve, where the oracle ensures safe and efficient crossing at individual intersections, and the valve selects some of the approaching CAVs for the oracle to control and postpones the crossing of the unselected ones. We further focus on distributed decision making for the valves, and propose a multi-agent reinforcement learning framework, spatial-aware multi-agent actor-credit (SMAC). Specifically, SMAC integrates a novel credit assignment method that captures agents' spatially decaying influences to stimulate agent cooperation, and a novel graph convolutional mixing network to capture the graph-structured inter-agent relationships in a road network. We conduct extensive experiments on three traffic flow datasets, and show that SMAC outperforms state-of-the-art baselines.

For-hire vehicle-enabled crowd sensing (FVCS) has become a promising paradigm to conduct urban sensing tasks in recent years. FVCS platforms aim to jointly optimize both the order-serving revenue as well as sensing coverage and quality. However, such two objectives are often conflicting and need to be balanced according to the platforms’ preferences on both objectives. To address this problem, we propose a novel cooperative multi-objective multi-agent reinforcement learning framework, referred to as MOVDN, to serve as the first preference-configurable order dispatch mechanism for FVCS platforms. Specifically, MOVDN adopts a decomposed network structure, which enables agents to make distributed order selection decisions, and meanwhile aligns each agent’s local decision with the global objectives of the FVCS platform. Then, we propose a novel algorithm to train a single universal MOVDN that is optimized over the space of all preferences. This allows our trained model to produce the optimal policy for any preference. Furthermore, we provide the theoretical convergence guarantee and sample efficiency analysis of our algorithm. Extensive experiments on three real-world ride-hailing order datasets demonstrate that MOVDN outperforms strong baselines and can support the platform in decision-making effectively.

Multi-access edge computing (MEC) enables the computation-intensive and latency-critical application to be processed at the network edge, which reduces the transmission latency and energy consumption. The quality of the wireless channel seriously affects the performance of the edge network. Consequently, the performance of the edge network can be significantly improved from the perspective of communication. The recently advocated intelligent reflecting surface (IRS) intelligently controls the radio propagation environment to improve the quality of wireless communication links. This paper proposes an edge heterogeneous network with the assistance of intelligent reflecting surface. Specifically, the macro base station and small base stations are equipped with MEC servers, and IRS is adopted to provide an additional computation offloading link. The user association, computation offloading and resource allocation, as well as IRS phase shift design are optimized with the aim of minimizing the long-term energy consumption subject to the constraints imposed on quality of service (QoS) and available resources. The challenge of the optimization problem is rooted from the fact that update timescale of user association is different from others. Hence, a two-timescale mechanism is invoked by marrying tools from matching theory and deep reinforcement learning. More specifically, the user association decision takes place in the long timescale. In the short timescale, the computation offloading, resource allocation and IRS phase shift design strategy is performed. The effectiveness of the proposed two-timescale mechanism is verified by the simulation results.

Abstract Anomaly detection is one of the most important applications in video surveillance that involves the temporal localisation of anomaly events in unannotated video sequences. By learning the normal patterns to generate frames and calculating their reconstruction error relative to the ground truth, a frame can be recognised as being abnormal if the reconstruction error exceeds a threshold. Most existing works use a fixed threshold that computes over all the testing data to determine the anomalies. However, fixed threshold strategy cannot address the challenges brought by the dynamic environment, e.g. changes in illumination conditions. In this paper, a dynamic thresholding algorithm (DTA) is proposed, which is fully data‐driven and capable of automatically determining thresholds such that the developed anomaly detection system can flexibly adapt to different scenarios. The proposed DTA is independent of the backbone network and can be easily incorporated into most existing video anomaly detection models to help identify the appropriate thresholds. On both synthetic and real‐world datasets, the experimental results show that with the proposed DTA, the video anomaly detection methods achieve a better performance considering the changes in dynamic environment.

The growing number of Internet of Things (IoT) devices brings enormous time-sensitive applications, which require real-time transmission to effectuate communication services. The ultrareliable and low-latency communication (URLLC) scenario in the fifth generation (5G) has played a critical role in supporting services with delay-sensitive properties. Time-sensitive networking (TSN) has been widely considered as a promising paradigm for enabling the deterministic transmission guarantees for 5G. However, TSN is a hybrid traffic system with time-sensitive traffic and best effort traffic, which require effective routing and scheduling to provide a deterministic and bounded delay. While joint optimization of time-sensitive and non-time-sensitive traffic greatly increases the solution space and brings a significant challenge to obtain solutions. Therefore, this article proposes a graph convolutional network-based deep reinforcement learning (GCN-based DRL) solution for the joint optimization problem in practical communication scenarios. The GCN is integrated into deep reinforcement learning (DRL) to obtain the network’s spatial dependence and elevate the generalization performance of the proposed method. Specifically, the GCN adopts the first-order Chebyshev polynomial to approximate the graph convolution kernel, which reduces the complexity of the algorithm and improves the feasibility for the joint optimization task. Furthermore, priority experience replay is employed to accelerate the convergence speed of the model training process. Numerical simulations demonstrate that the proposed GCN-based DRL algorithm has good convergence and outperforms the benchmark methods in terms of the average end-to-end delay.

To achieve the service-oriented features of the 5G, network slicing aims to create logical virtual networks where multiple services are provided on a common physical infrastructure. The performance of network slicing depends on the intelligent management of multi-dimensional resources, which are exactly what multi-access edge computing (MEC) provides. This paper proposes joint optimization of communication, computing and caching (3C) resources in multi-access edge network slicing. The optimization objective of the two-level resource allocation problem is to maximize the utility obtained by mobile virtual network operators while ensuring the quality of service (QoS). The deep reinforcement learning (DRL) approach is employed which enables the resource allocation scheme to intelligently adapt to the dynamic environment. Specifically, we propose a novel DRL approach named twin-actor deep deterministic policy gradient (twin-actor DDPG). Since the action space is continuous, the DDPG is adopted where the actor generates the deterministic policy while the critic evaluates the policy and guides the actor to obtain the optimal policy. A novel twin-actor structure is put forward to replace the actor of the DDPG, thus the slice-level action and user-level action can be generated respectively. The convergence and effectiveness of the proposed DRL based algorithm is are verified by numerical simulation.

Recently, vehicular crowd sensing (VCS) that leverages sensor-equipped urban vehicles to collect city-scale sensory data has emerged as a promising paradigm for urban sensing. Nowadays, a wide spectrum of VCS tasks are carried out by for-hire vehicles (FHVs) due to various hardware and software constraints that are difficult for private vehicles to satisfy. However, such FHV-enabled VCS systems face a fundamental yet unsolved problem of striking a balance between the order-serving and sensing outcomes. To address this problem, we propose a novel graph convolutional cooperative multi-agent reinforcement learning (GCC-MARL) framework, which helps FHVs make distributed routing decisions that cooperatively optimize the system-wide global objective. Specifically, GCC-MARL meticulously assigns credits to agents in the training process to effectively stimulate cooperation, represents agents' actions by a carefully chosen statistics to cope with the variable agent scales, and integrates graph convolution to capture useful spatial features from complex large-scale urban road networks. We conduct extensive experiments with a real-world dataset collected in Shenzhen, China, containing around 1 million trajectories and 50 thousand orders of 553 taxis per-day from June 1st to 30th, 2017. Our experiment results show that GCC-MARL outperforms state-of-the-art baseline methods in order-serving revenue, as well as sensing coverage and quality.

The rapid development of information and communication technologies has given rise to mobility-on-demand (MoD) systems (e.g., Uber, Didi) that have fundamentally revolutionized urban transportation. One common feature of today's MoD systems is the integration of ridesharing due to its cost-efficient and environment-friendly natures. However, a fundamental unsolved problem for such systems is how to serve people's heterogeneous transportation demands with as few vehicles as possible. Naturally, solving such minimum fleet problem is essential to reduce the vehicles on the road to improve transportation efficiency. Therefore, we investigate the fleet minimization problem in ridesharing-aware MoD systems. We use graph-theoretic methods to construct a novel order graph capturing the complicated inter-order shareability, each order's spatial-temporal features, and various other real-world factors. We then formulate the problem as a tree cover problem over the order graph, which differs from the traditional coverage problems. Theoretically, we prove the problem is NP-hard, and propose a polynomial-time algorithm with a guaranteed approximation ratio. Besides, we address the online fleet minimization problem, where orders arrive in an online manner. Finally, extensive experiments on a city-scale dataset from Shenzhen, containing 21 million orders from June 1st to 30th, 2017, validate the effectiveness of our algorithms.

With the constant development of 5G technology, such as softwareization and virtualization, the novel concept of network slicing has been appeared. Blockchain is a decentralized technology for managing transactions and data which can ensure the security of transaction. Recently, the classical mobile network introduces a new role such as network slice agent to provide slices for one or across multiple operators, providing services for users or vertical industries over a larger time and space range. In this paper, we propose the blockchain network slicing broker (BNSB), an intermediate broker, which receive resources request and response then allocation resources between Network Slice Tenants (NST) and then schedule physical resources from Infrastructure Provider (InP) through smart contracts. The topology information is obtained according to the Complex Network theory and the value of nodes is defined according to their importance. In addition, Deep Reinforcement Learning algorithms is used to explore the optimal policy under the condition of meeting the service Level Agreement (SLA).

Network slicing and Multi-access Edge Computing (MEC) have been envisioned as promising technique in the fifth generation mobile communication (5G). In this work, we study joint optimization of radio and computation resource in network slicing with MEC to maximize utility of Mobile Virtual Network Operator (MVNO), while meeting slice Quality of Service (QoS) requirements. On account of the dynamic change of slice demands and environment information, it is hard to solve resource allocation problems with conventional methods. Inspired by the superiority of deep reinforcement learning (DRL) in decision-making problems with the high state space and continuous action space. We formulate the utility maximization problem as a markov decision process (MDP). With an MVNO controller, the problem can be solved utilizing deep deterministic policy gradient (DDPG) algorithm to execute the dynamic resource allocation scheme. Simulation results show that utility performance of the proposed algorithm outperforms than the benchmark algorithms and enables dynamic resource allocation scheme.

In order to satisfy the boosting mobile traffic demand, the deployment of small cells has been regarded as a feasible solution. But the growth of network infrastructure leads to a tremendous increase of energy consumption. Using renewable energy harvested from the environment to power the small cell base station, forming green heterogeneous networks (HetNets), can help reduce the conventional energy consumption. However, the stochastic user demand and random renewable energy harvesting amount have brought new challenges for the network operation. Based on reinforcement learning, this paper proposes a decentralized and a centralized base station operation scheme. Assuming each base station operates individually, the energy efficiency maximization problem is modeled as a general-sum game. After defining the state, action and reward of each base station, the problem can be solved by multi-agent reinforcement learning. Assuming there is a centralized controller, then the whole network can be seen as a huge agent, thus, the problem can be solved using deep reinforcement learning since the state space is too complicated. Simulation results show the centralized scheme shows higher performance but need more signaling overheads. The energy efficiency is lower for the decentralized scheme but it can be realized easier in real life. Both our proposed scheme can achieve significant energy efficiency improvement compared to the greedy scheme.

With the proliferation of users in wireless communication networks and the increase in traffic, heterogeneous networks have emerged. Minimizing the total energy consumption of base stations is an important issue for environmental reasons. Therefore, the concept of a green heterogeneous network was proposed. However, the deployment of a large number of small base stations also poses problems for user management. In order to better improve the decision-making and self-organizing ability of the network, the paper also proposes an user energy consumption prediction model based on Recurrent Neural Network. After that, the article also proposes a power control scheme through a Deep Reinforcement Learning algorithm with Long Short-Term Memory to improve the quality of user service. Finally, a joint optimization scheme of network power control and user management is realized. The experimental results show that the joint optimization effect using this method can converge to better solution and reduce energy consumption compared with traditional deep reinforcement learning.

The cloud-based Internet of Things (IoT) develops rapidly but suffer from large latency and backhaul bandwidth requirement, the technology of fog computing and caching has emerged as a promising paradigm for IoT to provide proximity services, and thus reduce service latency and save backhaul bandwidth. However, the performance of the fog-enabled IoT depends on the intelligent and efficient management of various network resources, and consequently the synergy of caching, computing, and communications becomes the big challenge. This paper simultaneously tackles the issues of content caching strategy, computation offloading policy, and radio resource allocation, and propose a joint optimization solution for the fog-enabled IoT. Since wireless signals and service requests have stochastic properties, we use the actor-critic reinforcement learning framework to solve the joint decision-making problem with the objective of minimizing the average end-to-end delay. The deep neural network (DNN) is employed as the function approximator to estimate the value functions in the critic part due to the extremely large state and action space in our problem. The actor part uses another DNN to represent a parameterized stochastic policy and improves the policy with the help of the critic. Furthermore, the Natural policy gradient method is used to avoid converging to the local maximum. Using the numerical simulations, we demonstrate the learning capacity of the proposed algorithm and analyze the end-to-end service latency.

Wireless sensor networks (WSNs) are an important part of the Internet of Things (IoT). In WSNs, the sensors may act as an information collector as well as relay. This trait will cause the sensors that around the Sink easily run out of battery due to heavy traffic-flow, which is called energy hole problem and limits the network lifetime dramatically. To cope with this problem, we derive an optimal hop distance in multi-hop environment and get a conclusion that the optimal receive signal-to-noise is fixed under the large scale fading model. Then, we get a relationship between transmission power and the optimal sensor's coverage. We proposed a new method to improve WSNs' lifetime by using the optimal hop distance and changing the sensor's coverage according to the distance between sensors and the Sink. Simulations show that the proposed method can improve the lifetime and energy efficient of WSNs. Our research can also be used in SDN to help the controllers make decisions.

Densely deployment of various small-cell base stations in cellular networks to increase capacity will lead to heterogeneous networks (HetNets), and meanwhile, embedding the energy harvesting capabilities in base stations as an alternative energy supply is becoming a reality. How to make efficient utilization of radio resource and renewable energy is a brand-new challenge. This paper investigates the optimal policy for user scheduling and resource allocation in HetNets powered by hybrid energy with the purpose of maximizing energy efficiency of the overall network. Since wireless channel conditions and renewable energy arrival rates have stochastic properties and the environment's dynamics are unknown, the model-free reinforcement learning approach is used to learn the optimal policy through interactions with the environment. To solve our problem with continuous-valued state and action variables, a policy-gradient-based actor-critic algorithm is proposed. The actor part uses the Gaussian distribution as the parameterized policy to generate continuous stochastic actions, and the policy parameters are updated with the gradient ascent method. The critic part uses compatible function approximation to estimate the performance of the policy and helps the actor learn the gradient of the policy. The advantage function is used to further reduce the variance of the policy gradient. Using the numerical simulations, we demonstrate the convergence property of the proposed algorithm and analyze network energy efficiency.

Nowadays, with the rapid development of wireless communications, the demand for high capacity and long battery lifetime has drawn much of the people's attention. In order to solve these two problems, we consider using cooperative communication with the help of green relays. In this paper, we desire an auction market which consists of one base station, M green relays with energy harvesting function, N mobile terminals . Terminals pay to get the relay service and the relay sells it to get reward. In addition, there is a markup factor based on the residual energy of terminals, and relays have a markdown factor based on the instantaneous energy harvesting amount. Furthermore, we propose three different auction rules with different targets. Simulation results shows that the different rules perform diversely but all of them can increase system capacity and extend the lifetime of the mobile terminals.

In order to utilize renewable energy and save conventional energy, energy saving traffic offloading in heterogeneous networks (HetNets) has been attracting attentions by many literature in recent years. This paper focuses on the power allocation problem after user scheduling or traffic offloading, with the goal of optimizing the network energy efficiency. Due to the stochastic property of wireless channels and green energy situation, meanwhile the state transition probabilities and expected rewards for all states are unknown in mobile environments, a stochastic optimal power allocation policy for in HetNets should be learned. We formulate and solve the energy-efficiency oriented power allocation problem in HetNets with the policy-gradient-based actor-critic algorithm, which is a model-free reinforcement learning framework and has been successfully used in applications, such as robotics and operations research. We use the parameterized policy to select actions and update the parameters using the gradient ascend method. The numerical simulations are shown to demonstrate the performance of the proposed algorithm.

Topology construction is a vital technique in cognitive radio ad hoc networks. In this paper, considering the nodes residual energy, available channel quality and the interference of primary users, a topology model based on BBV (Barrat, Barthelemy and Vespignani) model and the triad formation mechanism is proposed, which ensure the network topology with both scale-free and small- world features. The evolution process is composed of three parts: (i) adding nodes to the network; (ii) adding edges between new nodes and existing nodes; (iii) deleting edges because of the energy factor and the interference of primary users. Simulation results show that the topology built by this model with small-world and scale-free features has small average shortest path length and the robustness against random nodes failure, which can significantly improve the transmission efficiency and the stability of networks.

Efficiently and economically using renewable energy in cellular networks with renewable energy powered Base Stations (BSs) is realized in this paper. To realize that the renewable energy supply traces the dynamically changing traffic, the traffic aware inventory policy of renewable energy at each BS is proposed. For each BS at each time period, the optimal inventory quantity of renewable energy which has the lowest inventory cost is derived and numerically simulated. Numerical results show that the optimal inventory quantity of renewable energy for each BS, changes along with the traffic quantity, and shortage cost and holding cost of renewable energy, and provides a baseline for energy cooperation between BSs.

Energy efficiency is now a significant concern for network infrastructure and next-generation network devices are expected to embed advanced power management capabilities. However, the effective exploitation of advanced power management capabilities in network devices which adaptively meet network load and operational constraints is still a considerable challenge due to the stochastic properties of the actual traffic load. In this paper, a statistical optimal local control policy for dynamic control of power state configurations according to the actual traffic load is proposed to minimize the power consumption while meeting the performance constraints. The packet-level statistical features of network traffic load is modeled as a first-order Markov chain and the dynamic power state selection problem is formulated as a Markov decision process, which can be solved using dynamic programming. In addition, we discuss the possibility of implementing the proposed scheme in real network devices, and design a case study in an NetFPGA frequency scaled router. Simulation results are presented to show the effectiveness of the proposed scheme.

Cooperative communications and network coding are considered as effective technologies to provide robust and efficient communications. Most existing studies focus on lower layer performance, such as bandwidth efficiency, and little attention has been paid to the performance in the upper layers, such as transmission control protocol (TCP) throughput. In this paper, we investigate TCP throughput in wireless networks with cooperative communications and network coding, and take a cross-layer design approach to improve TCP throughput. Wireless channels are modeled as finite sate Markov channels to characterize the structure of the fading process, and the TCP performance improvement problem is formulated as a stochastic decision process, which can be solved using linear programming and primal-dual index heuristic algorithm. Simulation results show that cooperative communications and network coding have significant impact on TCP throughput, and the TCP throughput can be improved substantially by the proposed scheme.

Energy saving becomes one of the most important design considerations in wireless cooperative networks which are composed of nodes typically powered by batteries that can supply only a finite amount of energy. In this paper, we propose a dynamic relaying scheme based on relay selection and physical-layer power control with the objective of minimizing the energy consumption for data transmission. We first develop a mathematical model for the cooperative relaying and analyze the total battery energy consumption to forward a symbol. Based on the analytic results and Markov channel model, we formulate the optimization problem that minimizes total average energy consumption as a Markov decision process, with which we can decide an optimal relay and the transmission power distributely. In the proposed scheme, the relay selection process and cooperation mode starts only when the direct transmission between source and destination node failed, which is energy efficient from a network sense. Numerical simulation show that the proposed scheme achieves significant energy savings.

In this paper, we investigate the transmission control protocol (TCP) throughput in cooperative relaying networks and take an cross-layer design approach when selecting a relay to optimize the TCP throughput. A first-order finite-sate Markov channel (FSMC) is used to model the wireless time varying channels, and the TCP throughput is estimated as a function of physical layer signal-to-noise ratio (SNR) and link-layer frame size and retransmission times. Since relay selection is crucial in improving the TCP performance, we proposed a stochastic decision making approach to select the optimal relay for every TCP packet according to the states of each relay. We formulated the cross-layer TCP throughput optimization problem as a restless bandit system and obtained the statistically optimal relay selection policy, which has an indexability property and can be easily implemented in real system. We compare the proposed scheme through simulations under different parameters of physical layer and link-layer, simulation results show that the TCP throughput can be improved significantly by the optimal relay selection scheme.

This paper proposes a distributed optimal relay selection scheme in wireless multi-hop cooperative networks where the wireless channels are modeled as first-order finite-state Markov channels (FSMCs) and adaptive modulation and coding (AMC) is applied. The FSMC model is used to approximate the time variations of the average received signal-to-noise ratio (SNR). The state of a relay consists of the channel states of both source-to-relay and relay-to-destination links. In this scheme, a stochastic decision making approach is taken to select the optimal relay according to the states of all available relays with the quality of service (QoS) optimization goals of mitigating error propagation and increasing spectral efficiency. Simulation results show that the proposed scheme outperforms the existing scheme.

Relay selection is crucial in improving the performance of wireless cooperative networks. Most of previous works for relay selection use the current observed channel conditions to make the relay selection decision for the subsequent frame. However, this assumption is often not realistic given the time-varying nature of some mobile environments. In this paper, we consider finite state Markov channels in the relay selection problem. Moreover, we also incorporate adaptive modulation and coding, as well as residual relay energy in the relay selection process. The objectives of the proposed scheme are not only to increase spectral efficiency, mitigate error propagation, but also to maximize the network lifetime. Simulation results are presented to show the effectiveness of the proposed scheme.