Edge intelligence is anticipated to underlay the pathway to connected intelligence for 6G networks, but the organic confluence of edge computing and artificial intelligence still needs to be carefully treated. To this end, this article discusses the concepts of edge intelligence from the semantic cognitive perspective. Two instructive theoretical models for edge semantic cognitive intelligence (ESCI) are first established. Afterwards, the ESCI framework orchestrating deep learning with semantic communication is discussed. Two representative applications are present to shed light on the prospect of ESCI in 6G networks. Some open problems are finally listed to elicit the future research directions of ESCI.
Deep learning (DL) has been applied to the physical layer of wireless communication systems, which directly extracts environment knowledge from data and outperforms conventional methods either in accuracy or computation complexity. However, most related research works employ centralized training that inevitably involves collecting training data from edge devices. The data uploading process usually results in excessive communication overhead and privacy disclosure. Alternatively, a distributed learning approach named federated edge learning (FEEL) is introduced to physical layer designs. In FEEL, all devices collaborate to train a global model only by exchanging parameters with a nearby access point. Because all datasets are kept local, data privacy is better protected and data transmission overhead can be reduced. This paper reviews the studies on applying FEEL to the wireless physical layer including channel state information acquisition, transmitter, and receiver design, which represent a paradigm shift of the DL-based physical layer design. In the meantime they also reveal several limitations inherent in FEEL, particularly when applied to the wireless physical layer, thus motivating further research efforts in the field.
Satellite communication has been seen as a vital part of the sixth generation communication, which greatly extends network coverage.In satellite communication, resource management is a key problem attracting many research interests. However, previous study mainly focuses on throughput improvement via power allocation and spectrum assignment and the proposed approaches are mostly model-based and dedicated to specific problem structures. Fortunately, with the trend of edge intelligence, complex resource management problems can be efficiently resolved in a model-free manner. In this paper, a joint beam activation, user-beam association and time resource allocation approach is proposed. The core idea is using stochastic learning at the ground station to identify active user-link beams to meet user rate demand. In addition, the convergence, optimality and complexity of our proposal are rigorously discussed. By simulation, it is shown that the rate goal of most of the users can be met and meanwhile satellite energy is saved owing to much less active beams.
As a promising edge learning framework in future 6G networks, federated learning (FL) faces a number of technical challenges due to the heterogeneous network environment and diversified user behaviors. Data imbalance is one of these challenges that can significantly degrade the learning efficiency. To deal with data imbalance issue, this work proposes a new learning framework, called clustered federated learning with weighted model aggregation (weighted CFL). Compared with traditional FL, our weighted CFL adaptively clusters the participating edge devices based on the cosine similarity of their local gradients at each training iteration, and then performs weighted per-cluster model aggregation. Therein, the similarity threshold for clustering is adaptive over iterations in response to the time-varying divergence of local gradients. Moreover, the weights for per-cluster model aggregation are adjusted according to the data balance feature so as to speed up the convergence rate. Experimental results show that the proposed weighted CFL achieves a faster model convergence rate and greater learning accuracy than benchmark methods under the imbalanced data scenario.
To relieve the backhaul link stress and reduce the content acquisition delay, mobile edge caching has become one of the promising approaches. In this paper, a novel federated reinforcement learning (FRL) method with adaptive training times is proposed for edge caching. Through a new federated learning process with the asynchronous model training process and synchronous global aggregation process, the proposed FRL-based edge caching algorithm mitigates the performance degradation brought by the non-identically and independently distributed (non-i.i.d.) characteristics of content popularity among edge nodes. The theoretical bound of the loss function difference is analyzed in the paper, based on which the training times adaption mechanism is proposed to deal with the tradeoff between local training and global aggregation for each edge node in the federation. Numerical simulations have verified that the proposed FRL-based edge caching method outperforms other baseline methods in terms of the caching benefit, the cache hit ratio and the convergence speed.
The satellite-terrestrial cooperative network is considered an emerging network architecture, which can adapt to various services and applications in the future communication network. In recent years, the combination of satellite communication and Mobile Edge Computing (MEC) has become an emerging research hotspot. Satellite edge computing can provide users with full coverage on-orbit computing services by deploying MEC servers on satellites. This paper studies the task offloading of multi-user and multi-edge computing satellites and proposes a novel algorithm that joint task offloading and communication computing resource optimization (JTO-CCRO). The JTO-CCRO is decoupled into task offloading and resource allocation sub-problems. After the mutual iteration of the two sub-problems, the system utility function can be further reduced. For the task offloading sub-problem, it is first confirmed that the offloading problem is a game problem. The offloading strategy can be obtained from the Nash equilibrium solution. We confirm resource optimization sub-problem is a convex optimization problem that can be solved by the Lagrange multiplier method. Simulation shows that the JTO-CCRO algorithm can converge quickly and effectively reduce the system utility function.
Mobile edge computing (MEC) emerges as a paradigm to free mobile devices (MDs) from increasingly dense computing workloads in 6G networks. The quality of computing experience can be greatly improved by offloading computing tasks from MDs to MEC servers. Renewable energy harvested by energy harvesting equipments (EHQs) is considered as a promising power supply for users to process and offload tasks. In this paper, we apply the uniform mobility model of MDs to derive a more realistic wireless channel model in a multi-user MEC system with batteries as EHQs to harvest and storage energy. We investigate an optimization problem of the weighted sum of delay cost and energy cost of MDs in the MEC system. We propose an effective joint partial computation offloading and resource allocation (CORA) algorithm which is based on deep reinforcement learning (DRL) to obtain the optimal scheduling without prior knowledge of task arrival, renewable energy arrival as well as channel condition. The simulation results verify the efficiency of the proposed algorithm, which undoubtedly minimizes the cost of MDs compared with other benchmarks.
In the 5 $^{th}$ generation mobile communication (5G) system, better bitrate, better power consumption, and better Bit Error Rate are needed. To meet all these requirements in 5G, the waveform is important. Although the Orthogonal Frequency Division Multiplexing (OFDM) modulation scheme has been commonly used in 4G, it is difficult to meet the requirements of 5G. A lot of candidate waveforms are discussed in the 5G system included Filter Bank Multicarrier (FBMC), Universal Filtered Multicarrier (UFMC), Filtered OFDM (F-OFDM), and Generalized Frequency Division Multiplexing (GFDM), etc. However, since GFDM is no longer widely used, in this paper, FBMC, UFMC, and F-OFDM modulation schemes are discussed and compared with OFDM. Power Spectral Density (PSD), Bit Error Rate (BER), Transmitted Signal Power, Peak Average Power Ratio (PAPR) and Bit Rate parameters of the modulation schemes are studied and compared with OFDM. FBMC demonstrates to be the most promising modulation scheme for 5G systems.
The currently available compilation techniques are for general computing and are not optimized for physical layer computing in 5G micro base stations. In such cases, the foreseeable data sizes and small code size are application specific opportunities for baseband algorithm optimizations. Therefore, the special attention can be paid, for example, the specific register allocation algorithm has not been studied so far. The compilation for kernel sub-routines of baseband in 5G micro base stations is our focusing point. For applications of known and fixed data size, we proposed a compilation scheme of parallel data accessing, while operands can be mainly allocated and stored in registers. Based on a small register group (48×32b), the target of our compilation scheme is the optimization of baseband algorithms based on 4×4 or smaller matrices, maximizing the utilization of register files, and eliminating the extra register data exchanging. Meanwhile, when data is allocated into register files, we used VLIW (Very Long Instruction Word) machine to hide the time of data accessing and minimize the cost of data accessing, thus the total execution time is minimum. Experiments indicate that for algorithms with small data size, the cost of data accessing and extra addressing can be minimized.
In quantum noise stream cipher (QNSC) systems, it is difficult to compensate fiber nonlinearity by digital signal processing (DSP) due to interactions between chromatic dispersion (CD), amplified spontaneous emission (ASE) noise from erbium-doped fiber amplifier (EDFA) and Kerr nonlinearity. Nonlinearity equalizer (NLE) based on machine learning (ML) algorithms have been extensively studied. However, most NLE based on supervised ML algorithms have high training overhead and computation complexity. In addition, the performance of these algorithms have a lot of randomness. This paper proposes two clustering algorithms based on Fuzzy-logic C-Means Clustering (FLC) to compensate the fiber nonlinearity in quadrature amplitude modulation (QAM)-based QNSC system, including FLC based on subtractive clustering (SC) and annealing evolution (AE) algorithm. The performance of FLC-SC and FLC-AE are evaluated through simulation and experiment. The proposed algorithms can promptly obtain suitable initial centroids and choose optimal initial centroids of the clusters to achieve the global optimal initial centroids especially for high order modulation scheme. In the simulation, different parameter configurations are considered, including fiber length, optical signal-to-noise ratio (OSNR), clipping ratio and resolution of digital to analog converter (DAC). Furthermore, we measure the Q-factor of transmission signal with different launched powers, DAC resolution and laser linewidth in the optical back-to-back (BTB) experiment with 80-km single mode fiber. Both simulation and experimental results show that the proposed techniques can greatly mitigate the signal impairments.
To realize high-accuracy physical-cyber digital twin (DT) mapping in a manufacturing system, a huge amount of data need to be collected and analyzed in real-time. Traditional DTs systems are deployed in cloud or edge servers independently, whilst it is hard to apply in real production systems due to the high interaction or execution delay. This results in a low consistency in the temporal dimension of the physical-cyber model. In this work, we propose a novel efficient edge-cloud DT manufacturing system, which is inspired by resource scheduling technology. Specifically, an edge-cloud collaborative DTs system deployment architecture is first constructed. Then, deterministic and uncertainty optimization adaptive strategies are presented to choose a more powerful server for running DT-based applications. We model the adaptive optimization problems as dynamic programming problems and propose a novel collaborative clustering parallel Q-learning (CCPQL) algorithm and prediction-based CCPQL to solve the problems. The proposed approach reduces the total delay with a higher convergence rate. Numerical simulation results are provided to validate the approach, which would have great potential in dynamic and complex industrial internet environments.
With increasing the demand for transmitting secure information in wireless networks, device-to-device (D2D) communication has great potential to improve system performance. As a well-known security risk is eavesdropping in D2D communication, ensuring information security is quite challenging. In this paper, we first obtain the closed-forms of the secrecy outage probability (SOP) and the secrecy ergodic capacity (SEC) for direct and decode-and-forward (DF) relay modes. Numerical results are presented to verify the theoretical results, and these results show the cases that the DF relay mode improves security performance compared to the direct mode at long distances between the transmitter and receiver nodes. Further, we look into the optimization problems of secure resource allocation in D2D communication to maximize the SEC and to minimize the SOP by considering the strictly positive secrecy capacity constraint as a mixed-integer non-linear programming (MINLP) problem. In the continue, we convert the MINLP to convex optimization. Finally, we solve this program with a dual method and obtain an optimal solution in the direct and DF relay modes.
Nowadays, the fifth-generation (5G) mobile communication system has obtained prosperous development and deployment, reshaping our daily lives. However, anomalies of cell outages and congestion in 5G critically influence the quality of experience and significantly increase operational expenditures. Although several big data and artificial intelligence-based anomaly detection methods have been proposed for wireless cellular systems, they change distributions of the data and ignore the relevance among user activities, causing anomaly detection ineffective for some cells. In this paper, we propose a highly effective and accurate anomaly detection framework by utilizing generative adversarial networks (GAN) and long short-term memory (LSTM) neural networks. The framework expands the original dataset while simultaneously keeping the distribution of data unchanged, and explores the relevance among user activities to further improve the system performance. The results demonstrate that our framework can achieve 97.16% accuracy and 2.30% false positive rate by utilizing the correlation of user activities and data expansion.
Based on the wide application of cloud computing and wireless sensor networks in various fields, the Sensor-Cloud System (SCS) plays an indispensable role between the physical world and the network world. However, due to the close connection and interdependence between the physical resource network and computing resource network, there are security problems such as cascading failures between systems in the SCS. In this paper, we propose a model with two interdependent networks to represent a sensor-cloud system. Besides, based on the percolation theory, we have carried out a formulaic theoretical analysis of the whole process of cascading failure. When the system's subnetwork presents a steady state where there is no further collapse, we can obtain the largest remaining connected subgroup components and the penetration threshold. Theoretically, this result is the critical maximum that the coupled SCS can withstand. To verify the correctness of the theoretical results, we further carried out actual simulation experiments. The results show that a scale-free network priority attack's percolation threshold is always less than that of ER network which is priority attacked. Similarly, when the scale-free network is attacked first, adding the power law exponent $\lambda$ can be more intuitive and more effective to improve the network's reliability.
Zero-trust security is a novel concept to cope with intricate access, which can not be handled by the conventional perimeter-based architecture anymore. The device-to-device continuous authentication protocol is one of the most crucial cornerstones, especially in the IoT scenario. In the zero-trust architecture, trust does not rely on any position, person or device. However, to the best of our knowledge, almost all existing device-to-device continuous authentication relies on a trust authority or a node to generate secret keys or secret values. This is betrayed by the principle of zero-trust architecture. In this paper, we employ the blockchain to eliminate the trusted node. One node is chosen to produce the public parameter and secret keys for two entities through the practical Byzantine fault tolerance consensus mechanism. Additionally, the devices are categorized into three folds: trusted device, suspected device and untrusted device. Only the first two can participate in authentication, and they have different lengths of security parameters and intervals to reach a better balance between security and efficiency. Then we prove the security of the initial authentication part in the eCK model and give an informal analysis of the continuous authentication part. Finally, we implement the proposed protocol on simulated devices. The result illustrates that our scheme is highly efficient, and the continuous authentication only costs around 0.1ms.
The next generation of High Throughput Satellite (HTS) will exploit Q/V band for the feeder link and Ka band for the user link. The exploitation of multiple gateways (GWs) is a transmit diversity measure to compensate severe rain attenuation of Q/V band feeder links. This paper introduces a new smart gateway diversity combination scheme that combinates $N$-active ($K=2$) and $N+1$ diversity method in detail from the working principle, gateway switching strategy, evaluation of system availability and implementation complexity. In addition, a feeder link outage event prediction algorithm featuring combination scheme is given detailly based on modified time-adaptive linear regression. Compared with the existing $N+P$ scheme, the proposed scheme can provide higher system availability and more stable user's experience under the condition of properly increasing the complexity of payload design. Compared with $N$-active scheme that has been reported, it is much easier to implement in engineering and more cost-effective. As a result, the combination scheme is a realistic solution based on a trade-off between performance improvement and implementation complexity.
Recently, satellite imagery has been widely applied in many areas. However, due to the limitations of hardware equipment and transmission bandwidth, the images received on the ground have low resolution and weak texture. In addition, since ground terminals have various resolutions and real-time playing requirements, it is essential to achieve arbitrary scale super-resolution (SR) of satellite images. In this paper, we propose an arbitrary scale SR network for satellite image reconstruction. First, we propose an arbitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbitrary scale enlarged SR outputs. Second, we design an edge reinforcement module to enhance the high-frequency details in satellite images through a two-branch network. Finally, extensive upsample experiments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counterparts.
Recently, Reconfigurable Intelligent Surfaces (RISs) have been introduced to provide the necessary flexibility for the design of the Smart Radio Environment (SRE), which can be optimally shaped to facilitate efficient signal transmissions. In line with the concept of smart cities, SRE needs to be carefully designed with respect to the city infrastructure and utilization of resources. In this paper, we provide our vision on RIS integration into future Smart Cities by highlighting the potential technical, environmental, and economic motivations of RIS deployment in harmony with various ecosystems at a city level such as buildings facades. To this end, we are pointing out some scenarios for mitigating the conflict between RIS realization and the existing building façade's ecosystems such as advertising display and solar cells on building walls. Also, in this fashion, the proposed vision supports a win-win relationship between all stakeholders of different ecosystems. This study presents guidelines for not only enabling seamless economically accepted RIS widespread utilization but, also more technically sounding SRE by supporting enhanced RIS features and more advanced applications that cannot be attained by traditional passive RIS. Moreover, based on the current research directions, we offer promising insights for cost-effective mass production through motivating two scenarios of “all on silicon” and “all as metasurface” fabrication technology. With this study, we aim to encourage the metasurface researchers, that for a broad deployment of the technical solution, economic, environmental, and other commercial requirements should be planned together, early on in the design phase.
