In Industrial Internet of Things (IIoT), reliability and latency are two important performance indicators. However, these two performance indicators are contradictory with each other, which are difficult to be enhanced simultaneously. In reality, many IIoT applications are in video or image format with critical requirements of both reliability and latency. In this article, we propose a scalable task offloading scheme for IIoT visual applications considering the unique scalable feature compared with general content. The proposed scheme demonstrates that partial content can be adaptively offloaded to a specific computing node to meet the reliability and latency requirements, meanwhile obtaining an excellent tradeoff between them. For optimization, a utility function is defined to characterize the tradeoff between reliability and latency. Then, a greedy algorithm is introduced to solve the problem of maximizing the utility function, where a near-optimal scheduling policy is adopted to achieve offloading association and properly offload data volume. Simulation results reveal that the proposed scalable task offloading scheme performs better than other benchmark schemes in balancing reliability and latency in IIoT visual applications, especially when the network traffic is moderate and channel conditions are undesirable.

Existing routing protocols may not be applicable in UAV networks because of their dynamic network topology and lack of accurate position information. In this paper, an enhanced flooding-based routing protocol is designed based on random network coding (RNC) and clustering for swarm UAV networks, enabling the efficient routing process without any routing path discovery or network topology information. RNC can naturally accelerate the routing process, with which in some hops fewer generations need to be transmitted. To address the issue of numerous hops and further expedite routing process, a clustering method is leveraged, where UAV networks are partitioned into multiple clusters and generations are only flooded from representatives of each cluster rather than flooded from each UAV. By this way, the amount of hops can be significantly reduced. The technical details of the introduced routing protocol are designed. Moreover, to capture the dynamic network topology, the Poisson cluster process is employed to model UAV networks. Afterwards, stochastic geometry tools are utilized to derive the distance distribution between two random selected UAVs and analytically evaluate performance. Extensive simulation studies are conducted to prove the validation of performance analysis, demonstrate the effectiveness of our designed routing protocol, and reveal its design insight.

Internet of Things (IoT) has attracted considerable attention in recent years due to its potential of interconnecting a large number of heterogeneous wireless devices. However, it is usually challenging to provide reliable and efficient random access control when massive IoT devices are trying to access the network simultaneously. In this article, we investigate methods to introduce intelligent random access management for a massive cellular IoT network to reduce access latency and access failures. Toward this end, we introduce two novel frameworks, namely, local device selection (LDS) and intelligent preamble selection (IPS). LDS enables local communication between neighboring devices to provide cluster-wide cooperative congestion control, which leads to a better distribution of the access intensity under bursty traffics. Taking advantage of the capability of reinforcement learning in developing cooperative multiagent policies, IPS is introduced to enable the optimization of the preamble selection policy in each IoT clusters. To handle the exponentially growing action space in IPS, we design a novel reinforcement learning structure, named branching actor–critic, to ensure that the output size of the underlying neural networks only grows linearly with the number of action dimensions. Simulation results indicate that the introduced mechanism achieves much lower access delays with fewer access failures in various realistic scenarios of interests.

Freshness and quality are two important metrics in real-time video applications in surveillance networks. However, these two metrics conflict with each other in many cases. To enhance the performance of real-time video services, it is very important, but also challenging, to find a good tradeoff between freshness and quality. In this article, we focus on studying the tradeoff between freshness and quality, where video packets are encoded with scalable video coding (SVC) and adaptive random network coding (ARNC). Moreover, the Age of Information (AoI) is applied to model video freshness, while the video quality is modeled by the number of layers received by users. A utility function is defined to capture the tradeoff between video freshness and video quality. By maximizing the defined utilities, an excellent tradeoff between freshness and quality could be obtained. To solve the formulated optimization problem, the maximization of the utility function is characterized as a Markov decision process (MDP) problem, which is effectively solved by a heuristic algorithm and a deep$Q$network (DQN)-based algorithm. Simulation results indicate that the applied ARNC technique can achieve higher utility performance than other benchmark transmission techniques, and the DQN-based algorithm outperforms the heuristic algorithm in most cases.

Dynamic spectrum access (DSA) has the great potential to alleviate spectrum shortage and promote network capacity. However, two fundamental technical issues have to be addressed, namely, interference coordination between DSA users and interference suppression for primary users (PUs). These two issues are very challenging since generally there is no powerful infrastructures in DSA networks to support centralized control. As a result, DSA users have to perform spectrum management individually, including spectrum access and power allocation, without accurate channel state information and centralized control. In this article, a novel spectrum management framework is proposed, in which Q-learning, a type of reinforcement learning, is utilized to enable DSA users to carry out effective spectrum management individually and intelligently. For more efficient process, neural networks (NNs) are employed to implement Q-learning processes, so-called deep Q-network (DQN). Furthermore, we also investigate the optimal way to construct DQN considering both the performance of wireless communications and the difficulty of NN training. Finally, extensive simulation studies are conducted to demonstrate the effectiveness of the proposed spectrum management framework.

With the proliferation of mobile access services and wireless devices, spectrum resources are increasingly becoming scarce. Industrial wireless sensor networks may have to share frequency bands with other systems and suffer from considerable interference. To address that, industrial cognitive radio networks (ICRNs) were developed for effective spectrum sharing, where signal classification is a fundamental and important technology, especially for industrial wireless devices, which need to identify suspicious transmissions. In this article, a novel framework of signal intelligent classification is proposed based on deep learning networks in ICRNs. In the proposed framework, wireless signals will be preprocessed first by Choi-Williams distribution time-frequency analysis and represented by two-dimensional time-frequency images. Then, features of wireless signals are extracted through stack hybrid autoencoders (SHAEs). To accommodate general cases, we design multiple signal classification methods, including unsupervised, semisupervised, and supervised methods, which are processed by Softmax function, semisupervised linear discriminant function, and Fisher discriminant function, respectively. Finally, simulation studies are conducted and the corresponding simulation results show that the proposed framework is able to learn hierarchical features accurately and achieve excellent signal classification performance. Moreover, it can effectively overcome the negative impact caused by feature parameters uncertainty.

Satellite industrial Internet of Things (IIoT) plays an important role in industrial manufactures without requiring the support of terrestrial infrastructures. However, due to the scarcity of spectrum resources, existing satellite frequency bands cannot satisfy the demand of IIoT, which have to explore other available spectrum resources. Cognitive satellite networks are promising technologies and have the potential to alleviate the shortage of spectrum resources and enhance spectrum efficiency by sharing both spectral and spatial degrees of freedom. For effective signal estimations, multiple features of wireless signals are needed at receivers, the transmissions of which may cause considerable overhead. To mitigate the overhead, part of parameters, such as modulation order, constellation type, and signal to noise ratio (SNR), could be obtained at receivers through signal estimation rather than transmissions from transmitters to receivers. In this article, a grid method is utilized to process the constellation map to obtain its equivalent probability density function. Then, binary feature matrix of the probability density function is employed to construct a cost function to estimate the modulation order and constellation type for multiple quadrature amplitude modulation (MQAM) signal. Finally, an improved M2M∞method is adopted to realize the SNR estimation of MQAM. Simulation results show that the proposed method is able to accurately estimate the modulation order, constellation type, and SNR of MQAM signal, and these features are extremely useful in satellite-based IIoT.

In industrial sensor networks, complex industrial environments may be encountered leading to a mix of signals of different types. Complicated interference caused by mixed signals on industrial equipments may significantly degrade the classification rate of signals, which may result in a long training time in order to extract features. In addition, with limited channel resources, it is difficult to make the global optimal decision in industrial distributed wireless sensor networks. To address this problem, a signal classification method using feature fusion is proposed for industrial Internet of Things in this article. In the proposed method, the received signals of nodes are processed by frequency reduction and sampling pretreatment, based on which intelligent representations of signals are obtained. Using federated learning, the data samples are trained with the feature fusion network. Moreover, the trained deep learning network is used on each sensor node to classify signals, the results of which will be transmitted to aggregation center. In the aggregation center, the improved evidence theory method is used to aggregate the recognition results of each sensor node to achieve the final classification. Simulation shows that the proposed method has excellent classification performances. Notably, it is not required for the proposed method to transmit signals from nodes to the aggregation center, which could effectively protect the privacy of industrial information.

Underlay cognitive radio (CR) holds the promise to address spectrum scarcity and let industrial wireless sensor networks obtain spectrum extension from shared frequency band resources. However, underlay CR devices should be capable of properly adjusting wireless transmission parameters according to the sensing of wireless environments. To realize the goal, in this article, two different signal-to-noise ratio (SNR) estimation methods are proposed for time-frequency overlapped signal estimations in the underlay CR-based industrial Internet of Things (IoT). In the first method, normalized higher order cumulant equations and the theoretical value of normalized higher order cumulants are adopted to estimate the SNR of component signals and the SNR of received signals. In the second one, the power of each component signals and the received signals is estimated based on the second-order time-varying moments. For the performance analysis, the Cramer-Rao lower bound of the SNR estimation for the time-frequency overlapped signals is derived. Simulation results show that the proposed method based on normalized higher order cumulants not only can effectively estimate the SNR of the time-frequency overlapped signals, but also has the strong robustness to the spectrum overlapped rate and the hybrid power ratio. The proposed method with second-order time-varying moments is able to accurately estimate the SNR of the time-frequency overlapped signals effectively, especially in the low-SNR region. These features are extremely useful in the industrial IoT, which usually operate in low-SNR regimes.

Scalable video coding (SVC) and video caching are two promising techniques in the 5th generation networks to improve the users' quality of experience (QoE) in terms of video retrieval. In this paper, we study the video content retrieval in cache-aided device-to-device (D2D) networks, where each video content is coded into multiple layers via SVC. In video caching placement phase, the probabilistic caching placement policy is applied, while in content retrieval phase, the non-orthogonal transmission scheme is utilized. Besides, different D2D transmitter selection algorithms are considered and cache-aided data rate (CADR) is formulated as a metric in this paper, and it is maximized by jointly optimizing the probability caching policy and the power allocation policy in two phases. Analytical results show that probabilistic caching policy incorporated with power domain non-orthogonal transmission scheme can achieve significant benefits compared with other benchmark schemes.

Unmanned aerial vehicles (UAVs) are becoming important communication infrastructures. One major challenge of communications with UAV networks is the routing protocol design. Due to the inherent characteristics (e.g., dynamic network topology and limited UAV device capabilities), it is difficult to directly apply existing routing protocols that utilize network topology information and routing path explorations. In this article, two novel routing protocols are designed based on random network coding (RNC) for a swarm UAV network, where UAVs operate cooperatively as a swarm, enabling efficient routing process. The first routing protocol utilizes the unique feature of RNC: Original packets can be decoded as long as an UAV accumulates sufficient generations. This property can be used to effectively expedite the underlying routing process. The second routing protocol further improves the efficiency where each forwarding UAV only needs to create a new generation rather than decoding original packets. Accordingly, the duration of each hop can be significantly reduced. Extensive simulations have been conducted to evaluate the performance of the designed routing protocols. The simulation results demonstrate that our designed routing protocols can effectively enhance the performance on both average transmission delay and delay violation probabilities compared to benchmark methods.

Power control plays an important role in improving the system throughput in communication system since co-channel interference is a major limitation to the system throughput. The power control problem of maximizing the system throughput in the multiuser and multichannel communication system is a highly complicated nonconvex problem since user are interfered with one another if operating in the same wireless channel. We reformulate the nonconvex objective function of this problem as a difference of two convex functions, which is called DC (difference of convex function) programming. To reduce the computation complexity in the high dimensional space, we introduce an alternative power allocation scheme to search in the low dimensional space, where each user updates its power sequentially. A global optimal power allocation is found by utilizing the branch-and- bound algorithm for each user while taking other users' power allocation as constant value. Furthermore, we incorporate each user's maximum power and minimum data rate constraint into the optimization framework. We found that the minimum data rate constraint of each user can be turned into multiple linear inequalities and then be added to the DC programming optimization framework. The simulation results show that our introduced method achieves the highest sum data rate compared to the state-of-the-art methods, including iterative water filling and geometric programming.

Routing protocol design is one of the major challenges for swarm UAV networks. Due to the characteristics of a dynamic network topology, the low-complexity and the large volume of UAV devices, existing routing protocols based on network topology information, and routing table updates are not applicable in swarm UAV networks. In this paper, a Random Network Coding (RNC) enabled routing protocol is proposed to support an efficient routing process, which does not require network topology information or pre-determined routing tables. With the proposed routing protocol, the routing process could be significantly expedited, since each forwarding UAV may have already overheard some encoded packets in previous hops. As a result, some hops may be required to deliver a few encoded packets, and less hops may need to be completed in the whole routing process. The corresponding simulation study is conducted, demonstrating that our proposed routing protocol is able to facilitate a more efficient routing process.

Dynamic spectrum access (DSA) is regarded as an effective and efficient technology to share radio spectrum among different networks. As a secondary user (SU), a DSA device will face two critical problems: 1) avoiding causing harmful interference to primary users (PUs) and 2) conducting effective interference coordination with other SUs. These two problems become even more challenging for a distributed DSA network where there is no centralized controllers for SUs. In this paper, we investigate communication strategies of a distributive DSA network under the presence of spectrum sensing errors. To be specific, we apply the powerful machine learning tool, deep reinforcement learning (DRL), for SUs to learn “appropriate” spectrum access strategies in a distributed fashion assuming NO knowledge of the underlying system statistics. Furthermore, a special type of recurrent neural network, called the reservoir computing (RC), is utilized to realize DRL by taking advantage of the underlying temporal correlation of the DSA network. Using the introduced machine learning-based strategy, SUs could make spectrum access decisions distributedly relying only on their own current and past spectrum sensing outcomes. Through extensive experiments, our results suggest that the RC-based spectrum access strategy can help the SU to significantly reduce the chances of collision with PUs and other SUs. We also show that our scheme outperforms the myopic method which assumes the knowledge of system statistics, and converges faster than the Q-learning method when the number of channels is large.

Unlicensed spectra access holds the promise of alleviating licensed spectra scarcity and providing super high-rate mobile data services, which has been viewed as one of the key technologies of fifth generation (5G) cellular networks. In this paper, we first design a framework for 5G licensed and unlicensed spectra interoperable networks based on the cloud radio access network technology and the control/data decoupled architecture. Then, we investigate network-level cost-reliability tradeoff from two aspects. First, we study a fundamental tradeoff between the cost and the reliability by minimizing cost for a given reliability level. Second, we define a quality of experience efficiency utility as the complementary measure to characterize the cost and the reliability, offering an inherent tradeoff between them. Moreover, an interference power estimation method is proposed to more accurately estimate channel states to guarantee resource allocation effectiveness. Finally, we conduct extensive simulation study and demonstrate the effectiveness of the interference power estimation method.

Unlicensed spectra fusion technology for LTE holds the promise of alleviating the licensed spectra scarcity and enhancing capacity. It allows LTE to effectively utilize the unlicensed spectra distributed over high frequency bands with significant different propagation characteristics from its licensed spectra. However, the interference caused by other systems over unlicensed spectra, particularly the public unlicensed spectra, is viewed as the most serious challenge. In this paper, aiming to guarantee the feasibility in existing LTE systems, we design a novel unlicensed spectra fusion scheme based on the popular standard TDD-LTE. To mitigate the interference, we develop an interference coordination scheme which is carried out in two stages: screen the available unlicensed channels for every UE, and allocate unlicensed spectra based on Hungarian algorithm. We have conducted extensive simulation study and demonstrate that our proposed scheme can handle interference coordination effectively and enhance throughput significantly.