LEO cloud storage constellation (LCSC) has gained significant popularity thanks to its on-board data storage capability and extensive inter-satellite connectivity. Unfortunately, the satellite disks will fail occasionally due to cosmic radiation and energy depletion, which leads to data loss and network unavailable. However, multi-node repair in the LCSC leads to the larger repair delay and the higher energy cost. To address this, we introduced the aggregation and multicast coded repair (AMCR) to fast recover the stored data using Reed-Solomon (RS) codes. We first propose the multi-weight multinode repair tree (MWNRT) model, i.e., a staged tree graph containing edge weights, to measure the multiple factors affecting repair performance. Next, we analyze the repair delay and the energy cost associated with multi-node repair leveraging AMCR. Then, to minimize repair delay while reducing energy cost, the aggregation-based multiple single-node repair trees construction (A-MSRT) algorithm is designed to construct multiple single-node repair trees based on the shortest-path principles. While the multicast-based aggregation of multiple repair trees (M-AMRT) algorithm is designed to select the repair tree with the longest delay from the output of A-MSRT as the initial repair tree, then adds the remaining replacement nodes. And the complexity of the two algorithms is elaborated and proven to be reasonable. Simulations show that AMCR scheme outperforms other schemes under different network conditions in LCSC.

In this paper, we focus on the application of coded distributed computing (CDC) in a multi-server clustered network (MSCN), which is designed to accelerate the gradient update process in federated learning (FL) by considering both communication and computational heterogeneity. As the number of participating devices increases and resource heterogeneity becomes more pronounced, reducing total execution latency (TEL) has become a critical challenge. To address this issue, we focus on optimizing the matching between heterogeneous devices and server task loads to improve resource utilization while enhancing the robustness and fault tolerance of the FL system. To minimize TEL, we propose a greedy algorithm and an iter-genetic algorithm for device assignment, named GADA and IGADA, based on the task allocation for the single server (TASS) algorithm, respectively. Based on simulation results and theoretical analysis, we confirm that our proposed algorithms substantially reduce the TEL in various scenarios compared to existing CDC methods, with complexity markedly lower than that of the exhaustive scheme.

Satellite Federated Learning (SFL) has emerged as a transformative paradigm for distributed machine learning in Low Earth Orbit (LEO) mega-constellations, enabling real-time processing of space-acquired data and enhancing remote sensing missions. The integration of Inter-Satellite Links (ISLs) into SFL alleviates synchronization delays due to intermittent connectivity between LEO satellites and ground-based parameter server (PS). However, the traffic generated from satellites creates communication bandwidth bottlenecks at the PS in the global model aggregation procedure. To address this issue, this paper proposes a novel SFL framework that leverages in-network model aggregation through ISLs to improve communication efficiency. Furthermore, two aggregation strategies, i.e., Chain Aggregation (CA) and Ring Aggregation (RA), are discussed in detail. Through system latency analysis and comprehensive simulations across constellation scales and data distributions, we demonstrate that: (1) in-network model aggregation fundamentally transforms communication load growth from ${\mathcal{O}}\left({{N^2}}\right)$ to ${\mathcal{O}}\left(N\right)$, and (2) the convergence time improves with increasing number of satellites, but degrades beyond a threshold.

Reliable image transmission is pivotal for lunar IoT networks, providing visual information for scientific exploration and real-time navigation. However, the moon’s harsh environment, i.e., lack of atmosphere, low surface conductivity, and rugged terrain, induces abnormal signal attenuation and packet losses, significantly degrading image transmission quality. This paper presents the Lunar Adaptive Image Transmission System (LAITS), which integrates the Terrain-Aware Field Strength Prediction (TAFSP) framework with the Hierarchical RaptorQ Redundancy Optimization (HRRO) coding algorithm. The TAFSP framework provides field strength predictions for channel packet loss rate estimation, by leveraging high-resolution lunar elevation data to formulate a radio propagation loss model. The HRRO algorithm optimizes coding efficiency and enables low-overhead transmission, by dynamically adjusting RaptorQ’s data segmentation based on the predictions of channel packet loss rate and priorities of image data. Simulations demonstrate that while maintaining image transmission quality above the 25 dB PSNR threshold, LAITS achieves a coverage rate of 85% in flat terrain with a 4 km radius at 440 MHz, 915 MHz, and 2400 MHz, and achieves coverage rates of 85% at 440 MHz, 70% at 915 MHz, and 56% at 2400 MHz in rugged terrain with the same radius.

Coded caching is an effective technique to reduce the downlink traffic on the network. While coded caching has been extended to many scenarios, coded caching in satellite networks has not been well investigated in the literature. In this paper, we first introduce a novel model of coded caching in satellite networks, which consists of P satellites periodically moving in a given orbit and K users on Earth. In this model, at each timeslot, every satellite (regarded as a server) serves Q consecutive users in a regime, while each user could access one or more satellites at the same time. Due to the cyclic mobility of satellites, the connections between satellites and users could be predictable but also dynamically change in a cyclic wrap-around fashion. Thus, the connections between different satellites and different users at different timeslots could be highly coupled. Taking advantage of the predictable connections given the satellite constellation, we propose a centralized achievable scheme such that different satellites can serve the users jointly. For the converse bound, we introduce a novel method to select user groups and construct request patterns, such that the connections between users and satellites involved could be decoupled. Moreover, the gap between the achievable rate and the converse bound is shown to be at most a constant. Numerical results show the superior performance of the proposed scheme and converse bound.

On-board distributed computing can provide more powerful computation capabilities for future low-earth-orbit (LEO) satellite constellations, serving intelligent information sensing and spatial large model through multi-satellite cooperation. On-board distributed computing depends on the efficient exchanging data flows between satellites termed coflow. The application of laser inter-satellite links (LISLs) will drastically improve the transmission capacity among the satellite distributed computing network (SDCN). However, due to the temporary interruptions of LISLs and the characteristics of optical circuit switching (OCS), the flow interruptions and conflicts significantly affect the coflow completion time (CCT). In this paper, we propose a conflict-aware coflow scheduling scheme to reduce the CCT in the OCS-based SDCN. Firstly, the time-varying LISLs and OCS-based coflow transmission are modeled and the problem of minimizing CCT is formulated. After that, we characterize the routing paths of coflow as the conflict graph and transform the coflow concurrent matching problem into the maximum independent set (MIS) problem in conflict graph. Based on this, we design the coflow polling greedy scheduling (CPGS) algorithm, which not only considers the sequence of coflow scheduling, but more importantly maximizes concurrent flows by MIS search. We deploy three different simulation scenarios to evaluate the algorithm performance. Simulation results show that our algorithm can significantly reduce the CCT by about 28.9% to 42.1% compared with existing works.

Low earth orbit (LEO) constellation network is a crucial component and paradigm for big data applications in the future satellite Internet. However, the characteristic of multi-hop transmission significantly increases the data retrieval delay and energy consumption depending on the inter-satellite communications. To mitigate this issue, this paper explores encoding redundancy by reed-solomon (RS) codes to generate the data and parity blocks, and store them in the satellite nodes of LEO constellation. We propose a fast data retrieval strategy, involving three stages: data collection, parity block placement, and data retrieval. Through the derivations of delay and energy consumption, we find that both are intensively related to the placement of parity blocks. To reduce energy consumption during the data retrieval process, we formulate a minimum problem under the delay constraint, which is an integer nonlinear programming problem. Then, we design an energy-efficient parity block placement based on genetic algorithm (PBP-GA), which is heuristic with fast convergence property. Simulation results show that, PBP-GA achieves a comprehensive performance improvement in average data retrieval delay and total energy consumption, compared to other placement schemes, i.e., random placement, retrieval cluster priority placement, nearby placement and non-coding. Specifically, PBP-GA can find the optimal number of parity blocks in a practical scenario of data retrieval in LEO constellation.

Low earth orbit (LEO) computing-aware networks (LCANs) are proposed as an intelligent information infrastructure providing a solution for delay-sensitive computing tasks worldwide. The utilization of distributed computing architecture in an LCAN is emerging as a prospective resolution to cope with the limited computational resources of single satellite. Distributed computing depends on the exchange of information between worker nodes, as a type of concurrent and interrelated data flows called coflow. However, huge delay of coflow transmission is caused by the time-varying network topology and dynamic ISL conditions in an LCAN. To solve this problem, we establish an LCAN topology model, elaborating the orbit movement and ISL connectivity. Then we propose a novel time-varying graph to depict coflow transmission, which can improve the adaptability of coflow routing. Based on the proposed time-varying graph, we formulate coflow routing problem as a path combinatorial optimization and present an iterative heuristic algorithm named dynamic priority coflow routing (DPCoR). The DPCoR can dynamically adjust the priorities of coflow according to their increments to CCT, and thereby ensure that flows with high priorities for better routing paths. Furthermore, we compare DP-CoR with traditional flow routing schemes, i.e., equal-cost multi-path routing (ECMP) and software defined routing algorithm (SDRA) in various LCAN scenarios with different numbers of worker nodes, workloads and link conditions. The simulation results demonstrated that DPCoR algorithm can reduce the coflow completion time (CCT) effectively.

The LEO storage constellation (LSC) has gained significant popularity thanks to its inter-satellite massive con-nectivity and space-terrestrial integrated data storage capability. However, the satellite disks will fail occasionally due to exhausting energy or space debris, which leads to data loss and network unavailable. In terrestrial data centers, aggregation coded repair (ACR) is an emerging data repair technique, which can reduce repair traffic by aggregating source data flows on intermediate nodes. However, existing ACR research does not focus on the problems of large propagation distance and energy consumption constraints in LSC. In this paper, we propose the coding path tree (CPT) model, which is a staged tree graph containing aggregation vectors and distance-related edge weights. For reducing repair delay and energy cost, we further propose the Delay-Sensitive Energy-Efficient ACR (DE-ACR) scheme, which is based on a CPT construction algorithm that combines the ideas of the shortest path and minimum Steiner tree. System-level experiment demonstrates that DE-ACR obtains a 7% reduction in repair delay compared to the single repair pattern tree (SRPT), and achieves a 55 % decrease in energy consumption compared to the shortest path ACR (SP-ACR) in LSC.

Coding techniques, known as coded distributed computing (CDC), have been investigated to alleviate the impact of heterogeneous straggler effects and reduce computation latency in distributed computing systems. However, in the multi-hop complicated network topology, the execution latency of the master's task includes both the computation latency and the communication latency, in which the imbalance computation loads and inadequate path selection will lead to the greater straggler effects extremely. In this paper, we focus on the issues of CDC application in a Two-Hop Heterogeneous Computation Network (THHCN). To make full use of the completed computing results of workers, we deploy Luby transform (LT) code to derive a total execution latency expression. Then, we formulate an optimization problem to minimize the total execution latency by selecting the relays and allocating the computation loads for different workers. Furthermore, a greedy minimum penalty relay selection and load allocation (GMPRS-LA) algorithm is proposed with lower complexity compared to the exhaustive searching to solve the integer nonlinear programming problem. Simulation results demonstrate GMPRS-LA achieves a significant reduction in the total execution latency and leads to a better performance than traditional CDC load allocation algorithms.

Recently, coding techniques have been introduced in distributed computing systems, i.e., coded distributed computing (CDC), to alleviate the heterogeneous straggler effect. However, these techniques bring about additional decoding latency impacting on the task completion time. In this paper, we study the issues of load allocation and latency analysis of systematic CDC in heterogeneous computation and communication straggling networks (HCCSNs). In order to exploit the partial works completed by straggling workers, we use the method of block division to accelerate the sub-tasks' results returning from all workers. Moreover, we attempt to leverage the systematic MDS code, which needs fewer decoding operations, to reduce the decoding latency, but it requires prior determining of the systematic blocks and the parity blocks on the master not on the workers. Therefore, in order to minimize both of the execution (communication and computing) latency and decoding latency, we propose two algorithms, i.e., greedy-based binary search algorithm (GBSA) and proportional systematic block allocation (PSBA), to obtain the optimal numbers of blocks and systematic blocks assigned to each worker, respectively. Simulation results are presented to show that GBSA and PSBA outperforms other conventional block allocation schemes in both execution latency and decoding latency with various straggling parameters.

Coded distributed computing (CDC) has been recently proposed as a promising technique to mitigate the straggler effect in the distributed computing cluster which consists of workers with different computing capabilities, and to reduce the end-to-end task execution latency. However, the heterogeneity of computing and transmission will critically impact the latency performance, especially in the wireless multiple-access network. In this paper, we use CDC over the heterogeneous wireless multipleaccess network (HWMAN) including both computation stragglers and transmission stragglers with various capabilities. In order to reduce the computing task completion latency (computing latency and transmission latency), the optimal stop computing time of workers and the sorting order of result transmission back are obtained via two designed algorithms, namely straggler detection and ordered transmission (SDOT) and worker sorting and ordered transmission (WSOT), respectively, which not only fully utilize the computing results of stragglers, but also improve the total latency performance compared with other existing state-of-theart algorithms.

Coded caching is an effective technique to reduce the downlink traffic on the network. While coded caching has been extended to many scenarios, coded caching in satellite networks has not been well investigated in the literature. In this paper, we introduce a novel model of coded caching in satellite networks, which consists of P satellites periodically moving in a given orbit and K users on the earth. In this model, at each timeslot, every satellite (regarded as a server) serves Q consecutive users in a regime, while each user can access one satellite. Due to the cyclic mobility of satellites, the connections between satellites and users could be predictable but also dynamically change in a cyclic shift pattern. Thus, the connections between different satellites and different users at different timeslots could be highly coupled. Taking advantage of the predictable connections, we propose a centralized achievable scheme such that different satellites can serve the users jointly. For the converse bound, we introduce a novel method to construct request patterns such that the connections between users and satellites involved could be decoupled. The gap between the achievable rate and the converse bound is shown to be at most a constant. Numerical results for the performance of our scheme are also demonstrated.

The low earth satellite networks are envisioned to be an indispensable part of next-generation network due to the seamless Internet access. Deploying distributed computation into LEO satellite networks can decrease the latency of transmitting satellite-terrestrial computing jobs, which is crucial to expanding the service capability. Distributed computation depends on the exchange of data flows between worker nodes, as a type of concurrent and interrelated flows called coflow. However, the mesh-shaped topologies of LEO satellite networks make coflows prone to bandwidth competition on multi-hop links, which impedes the efficiency of distributed computation. In this paper, we formulated the multi-hop coflow scheduling process in LEO satellite networks as a routing and bandwidth allocation problem. Then, we simplified the problem to a coflow routing problem, and proposed the coflow routing greedy scheduling (CRGS) algorithm on the basis of the characteristics of multi-hop networks. Finally, we simulated in an SDN environment, where CRGS was deployed in an SDN controller. Compared with several existing algorithms, the CRGS algorithm is proved to reduce the coflow completion time (CCT) more effectively.

The Internet of Vehicles (IoV) can offer safe and comfortable driving experience, by the enhanced advantages of space–air–ground-integrated networks (SAGINs), i.e., global seamless access, wide-area coverage, and flexible traffic scheduling. However, due to the huge popular traffic volume, limited cache/power resources, and the heterogeneous network infrastructures, the burden of backhaul link will be seriously enlarged, degrading the energy efficiency of IoV in SAGIN. In this article, to implement the popular content severing multiple vehicle users (VUs), we consider a cache-enabled satellite-UAV-vehicle-integrated network (CSUVIN), where the geosynchronous Earth orbit (GEO) satellite is regard as a cloud server, and unmanned aerial vehicles are deployed as edge caching servers. Then, we propose an energy-aware coded caching strategy employed in our system model to provide more multicast opportunities, and to reduce the backhaul transmission volume, considering the effects of file popularity, cache size, request frequency, and mobility in different road sections (RSs). Furthermore, we derive the closed-form expressions of total energy consumption both in single-RS and multi-RSs scenarios with asynchronous and synchronous services schemes, respectively. An optimization problem is formulated to minimize the total energy consumption, and the optimal content placement matrix, power allocation vector, and coverage deployment vector are obtained by well-designed algorithms. We finally show, numerically, our coded caching strategy can greatly improve energy efficient performance in CSUVINs, compared with other benchmarked caching schemes under the heterogeneous network conditions.

Ultra-dense computation services are widely distributed in various application scenarios with the rapid development of artificial intelligence and machine learning. Relying on the existing ground cellular networks, it is challenging to satisfy the 6G vision of full coverage and massive machine connectivity. Satellite-terrestrial integrated network (STIN) has abundant computation resources and seamless coverage ability, which can be served as an effective supplementary for the task allocating in cellular networks. Nevertheless, STIN has the characteristic of architecture complexity, unavoidable stragglers and high economic costs. The rational computation resource allocation among distributed on-orbit satellites becomes an urge problem, synthesizing these drawbacks in STINs. In this paper, to address these issues, we attempt to design a coded computation offloading strategy (CCOS) to migrate ground ultra-dense computing tasks to distributed satellite constellations in space. Considering the effect of unpredictable computation resource occupation on satellites, we investigate two coded computation methods, i.e., maximum distance separable (MDS) code and rateless code, to resist the random stragglers occurring on satellite nodes. Then, we formulate the optimization problem about minimizing the delay-energy tradeoff cost with different CCOSs under the tolerant time constraints, and obtain the optimal task offloading decisions (i.e., executing locations and coding parameters) using a proposed low-cost offloading decision searching algorithm (LODSA). Numerical simulation results show that, our coded computation strategies can significantly eliminate the effect of stragglers, and improve the cost performance obviously compared with the un-coded strategies in typical application cases.

Unmanned aerial vehicles (UAVs) have been widely used in wireless edge networks for task offloading, with the advantages of their agile management and high-flexibility deployment. However, due to limited computation capability and restricted battery life, processing computation-intensive tasks on board may cause the excessive cost of latency and energy. In this paper, we propose a novel framework with coded distributed computing (CDC) for the task offloading from multi-UAV to ground edge servers, which can save transmitting and flying energy consumption in the air, and reduce computation latency in the terrestrial distributed server networks with stragglers. Specifically, we formulate a latency-energy cost minimization problem, to obtain the optimal the UAVs' trajectory schedule and the appropriate CDC's parameters. Moreover, we divide this problem into two sub-optimization problems, which are solved by a cost optimal trajectory schedule (COTS) algorithm and a cost optimal code parameter design (COCPD) algorithm, respectively. Finally, numerical results indicate the feasibility and the effectiveness of our proposed framework, which also validate that CDC can significantly reduce the cost in the UAV edge computing network.

Abstract In clustered distributed storage systems (CDSSs), one of the main design goals is minimizing the transmission cost during the failed storage nodes repairing. Generalized regenerating codes (GRCs) are proposed to balance the intra‐cluster repair bandwidth and the inter‐cluster repair bandwidth for guaranteeing data availability. The trade‐off performance of GRCs illustrates that, it can reduce storage overhead and inter‐cluster repair bandwidths simultaneously. However, in practical big data storage scenarios, GRCs cannot give an effective solution to handle the heterogeneity of bandwidth costs among different clusters for node failures recovery. This paper proposes an asymmetric bandwidth allocation strategy (ABAS) of GRCs for the inter‐cluster repair in heterogeneous CDSSs. Furthermore, an upper bound of the achievable capacity of ABAS is derived based on the information flow graph (IFG), and the constraints of storage capacity and intra‐cluster repair bandwidth are also elaborated. Then, a metric termed global repair bandwidth cost (GRBC), which can be minimized regarding of the inter‐cluster repair bandwidths by solving a linear programming problem, is defined. The numerical results demonstrate that, maintaining the same data availability and storage overhead, the proposed ABAS of GRCs can effectively reduce the GRBC compared to the traditional symmetric bandwidth allocation schemes.

Industrial Internet of things (IIoT) is expected to improve efficiency and productivity by connecting massive devices, but it will cause potential congestions in backhual link and high energy consumptions. Caching with coded transmission is an effective method to reduce backhual load for content delivery. However, due to the hierarchy and heterogeneity in IIoT, it is very challenging to perform content placement with lower energy consumption. In this article, we propose an energy-efficient content placement strategy in cache-enabled hierarchical IIoT network with coded transmission. We derive a closed-form expression including the energy consumption for content placement and transmission by the macro base station and the small base stations. In addition, we establish an optimization problem to minimize the total energy consumption, whereby we find the optimal content placement matrix and optimal cache size allocation, respectively. Simulation results show that, the proposed content placement strategy can greatly improve energy efficiency in IIoT.

The large amount of deployed smart devices put tremendous traffic pressure on networks. Caching at the edge has been widely studied as a promising technique to solve this problem. To further improve the successful transmission probability (STP) of cache-enabled cellular networks (CEN), we combine the cooperative transmission technique with CEN and propose a novel transmission scheme. Local channel state information (CSI) is introduced at each cooperative base station (BS) to enhance the strength of the signal received by the user. A tight approximation for the STP of this scheme is derived using tools from stochastic geometry. The locally optimal content placement strategy of this scheme is obtained using a numerical method to maximize the STP. Simulation results demonstrate the optimal strategy achieves significant gains in STP over several comparative baselines with the proposed scheme.

We focus on a mobile caching system using erasure codes to cache content in mobile devices, which enter and depart a fixed area according to Poisson process. Due to the high mobility of devices, cached content is lost and to be repaired by device-to-device (D2D) communication. We consider the limited communication range and repair process with multiple contacts among mobile devices. We adopt a coded repair scheme which the repair process runs periodically, and derive analytical expressions of the average repair delay. The derived expressions are then used to evaluate repair delay using different erasure codes and file size. The results show that maximum distance separable codes can yield lower average repair delay compared to regenerating codes for small size of file. We further find that increasing the speed of mobile devices can reduce the average repair delay.

The Internet of Things (IoT) is creating billions of connected devices and generating enormous amounts of data. Data needs to be stored efficiently so that it can be retrieved easily on demand. Cloud storage is an inevitable choice for data management for IoT. Because of application diversity, limited bandwidth of end devices and the demand for real time, it is necessary to decrease the cost of data access in Heterogeneous Distributed Cloud Storage System (HDCSS). According to the point that applications always access the partial data, this paper combining the data access rate, proposes a degraded read scheme based Local Reconstruction Code (LRC) to improve the local max throughput in HDCSS. Simulation results show that our proposed scheme can achieve about a 50% increase in local throughput of hot data blocks without adding additional access load compared with commonly used LRC.

Unmanned aerial vehicles (UAVs) have been considered as effective flying base stations (FBSs) to provide on- demand wireless communications. Equipped with computation resource, UAVs are also capable of offering computation offloading opportunities for the mobile users (MUs) in mobile edge computing (MEC) networks. However, due to the small hardware and load capacity, UAVs can only supply limited computation and energy resource. It is thus challenging for UAVs to guarantee the quality of service (QoS) of MUs, while minimizing their total resource consumptions. Toward this end, instead of using all resource for every single task, we propose an intelligent resource allocation algorithm based on reinforcement learning, which enables UAVs to make energy-efficent and computation-efficent allocation decisions intelligently. Then, we take UAVs as learning agents by forming resource allocation decisions as actions and designing a reward function with the aim of minimizing the weighted resource consumptions. Each UAV performs the algorithm only based on its local observations without information exchange among different UAVs. Simulation results show that the proposed reinforcement learning based approach outperforms the benchmark algorithms in terms of weighted consumptions in a whole time period.

The large amount of devices deployed for the Internet of Things (IoT) cause a tremendous traffic burden on the cloud server. Caching content at the edge of IoT networks is a promising technology to alleviate the traffic load. However, how to further improve the successful transmission probability (STP) of cache‐enabled IoT networks is still an open issue. In this study, the authors propose a novel local channel state information based joint transmission (LC‐JT) scheme for cache‐enabled IoT networks and design the optimal content placement probability at the cooperative edge base stations, correspondingly. First, they derive an upper bound and a tight approximation for the STP of LC‐JT scheme using stochastic geometry. Next, an algorithm is proposed to maximise the approximation of STP in LC‐JT by optimising the placement probability vector, which is a non‐convex optimisation problem. By utilising some properties of the STP, they obtain the globally optimal solutions in specific cases. Moreover, the locally optimal solutions in general cases are obtained by using the gradient projection method. Finally, numerical results show the optimised content placement strategy can achieve significant gains in STP over several comparative baselines. It verifies that the strategy with LC‐JT can considerably enhance the STP in cache‐enabled IoT networks.

Unmanned aerial vehicles (UAVs) have been recently considered as a flying platform to provide wide coverage and relaying services for mobile users (MUs). Mobile edge computing (MEC) is developed as a new paradigm to improve quality of experience of MUs in future networks. Motivated by the high flexibility and controllability of UAVs, in this study, the authors study a multi‐UAV‐enabled MEC system, in which UAVs have computation resources to offer computation offloading opportunities for MUs, aiming to reduce MUs' total consumptions in terms of time and energy. Considering the rich computation resource in the remote cloud centre, they propose the MUs‐Edge‐Cloud three‐layer network architecture, where UAVs play the role of flying edge servers. Based on this framework, they formulate the computation offloading issue as a mixed‐integer non‐linear programming problem, which is difficult to obtain an optimal solution in general. To address this, they propose an efficient Q ‐learning based computation offloading algorithm (QCOA) to reduce the complexity of optimisation problem. Numerical results show that the proposed QCOA outperforms benchmark offloading policies (e.g. random offloading, traversal offloading). Furthermore, the proposed three‐layer network architecture achieves a 5% benefits compared with the traditional two‐layer network architecture in terms of MUs' energy and time consumptions.

Network selection is one of the important techniques in cognitive radio networks (CRNs). With the development of network convergence technology and the popularity of heterogeneous networks, multiple primary CRNs interacting with multiple authorized networks are becoming possible, which can provide secondary users with more spectrum resources by network selection. Network selection is the key to spectrum sharing between CRNs and multiple primary networks. However, the spectrum sensing results, highly complex system state, and unsystematic research framework make the research of network selection very challenging. Traditional network selection algorithms are offline selection methods that are based on prior knowledge of primary networks. However, in the complex network environment, it is impossible to get prior knowledge from multiple primary networks, because the offline network selection methods lack efficiency. In order to meet these challenges, this article aims at improving the quality of service of cognitive users, and based on reinforcement learning method and the achievements of dynamic spectrum access of cognitive radio in single primary network environment, proposed a deep reinforcement learning based online network selection method of CRNs with multiple primary networks.

Cache-enabled unmanned aerial vehicles (UAVs) have been envisioned as a promising technology for many applications in future urban wireless communication. However, to utilize UAVs properly is challenging due to limited endurance and storage capacity as well as the continuous roam of the mobile users. To meet the diversity of urban communication services, it is essential to exploit UAVs’ potential of mobility and storage resource. Toward this end, we consider an urban cache-enabled communication network where the UAVs serve mobile users with energy and cache capacity constraints. We formulate an optimization problem to maximize the sum achievable throughput in this system. To solve this problem, we propose a deep reinforcement learning-based joint content placement and trajectory design algorithm (DRL-JCT), whose progress can be divided into two stages: offline content placement stage and online user tracking stage. First, we present a link-based scheme to maximize the cache hit rate of all users’ file requirements under cache capacity constraint. The NP-hard problem is solved by approximation and convex optimization. Then, we leverage the Double Deep Q-Network (DDQN) to track mobile users online with their instantaneous two-dimensional coordinate under energy constraint. Numerical results show that our algorithm converges well after a small number of iterations. Compared with several benchmark schemes, our algorithm adapts to the dynamic conditions and provides significant performance in terms of sum achievable throughput.

In this paper, an improved random puncturing pattern of polar codes is proposed, where only the frozen bits can be selected to puncture. Compared to the existing random puncturing schemes, our improved random puncturing scheme can achieve 0.2-1dB decoding performance improvement. Then, an optimized rate-compatible hybrid automatic repeat request (HARQ) transmission scheme is proposed based on parallel concatenated punctured (PCP) polar codes. By analyzing the overhead of the previous successful decoded coding block in our rate-compatible HARQ scheme, two methods of determining the optimal initial code-rate of each new PCP polar coding block are proposed over a time-varying channel. Simulation results show that the average number of retransmissions is about 1.5 times in our proposed rate-compatible HARQ schemes with a 2-level PCP polar encoding construct, which reduces half of the average number of retransmissions than the existing rate-compatible polar coding scheme.

In Mars-to-Earth communications, data transmission suffered severe losses due to the huge path-loss, extremely long propagation delay and lack of line-of-sight link in rovers-to-Earth. Based on delay/disruption tolerant networks (DTN), we proposed a systematic Raptor Network Coding (RNC) scheme for the multi-rovers transform data through an orbiter to Earth station communication scenarios. To enhance the reliability of rover-to-Earth file delivery, and considering the limited capacity of the relaying orbiter, a simplified network coding scheme is designed for the orbiter. We analyzed the asymptotic performance of RNC scheme. Moreover, an improved RNC (IRNC) scheme is optimized in a finite code-length and limited coding complexity. Simulation results show that, our RNC and IRNC schemes can achieve better performance in comparison with existing distributed rateless erasure codes.

To improve the reliability of file transfer and shorten file transfer time in space communication, this study aims to provide an improved strategy for deferred negative acknowledgement (NAK) in Consultative Committee for Space Data Systems File Delivery Protocol (CFDP). Based on a theoretical analysis of the recommended deferred NAK, the authors propose a double retransmission deferred NAK strategy instead to guarantee the reliability of file transfer; the file transfer time is reduced significantly using fewer retransmission spurts. They make the performance comparisons of the recommended deferred NAK in CFDP with the authors’ proposed strategy under several typical scenarios. Numerical and simulation results show the effectiveness of the proposed strategy.

This study proposes a novel adaptive network‐coded rateless coding scheme for an erasure multiple‐access relay system with two distributed sources and an asymmetric network topology. To increase transmission efficiency, a two‐dimensional degree distribution, as part of network‐coded relay protocol, is designed based on the AND–OR tree analysis technique. The degree distributions of rateless coding at the sources and network coding at the relay are optimised by the linear programming approach under asymmetric channel conditions. Simulation results demonstrate that the proposed scheme outperforms existing classical relay protocols under time‐varying channel conditions, and achieves a significantly better performance.