Federated learning is a newly emerged distributed machine paradigm, where the clients are allowed to individually train local deep neural network (DNN) models with data and then jointly aggregate global DNN model at central server. Vehicular edge computing (VEC) aims exploiting computation communication resources of vehicular networks. in VEC promising meet ever-increasing demands artificial intelligence (AI) applications intelligent connected vehicles (ICV). Considering image classification...

Recently intensive efforts have been made on the transformation of world's largest physical system, power grid, into a “smart grid” by incorporating extensive information and communication infrastructures. Key features in such include high penetration renewable distributed energy sources, large-scale storage, market-based online electricity pricing, widespread demand response programs. From perspective residential customers, we can investigate how to minimize expected cost with real-time...

The emerging paradigm - Software-Defined Networking (SDN) and Network Function Virtualization (NFV) makes it feasible scalable to run Virtual Functions (VNFs) in commercial-off-the-shelf devices, which provides a variety of network services with reduced cost. Benefitting from centralized management, lots information about traffic resources can be collected SDN/NFV-enabled networks. Using powerful machine learning tools, algorithms designed customized way according the efficiently optimize...

The current cloud-based Internet-of-Things (IoT) model has revealed great potential in offering storage and computing services to the IoT users. Fog computing, as an emerging paradigm complement cloud platform, been proposed extend role edge of network. With fog service providers can exchange control signals with users for specific task requirements, offload users' delay-sensitive tasks directly widely distributed nodes at network edge, thus improving user experience. So far, most existing...

Unmanned aerial vehicles (UAVs) can be deployed efficiently to provide high quality of service for Internet Things (IoT). By using cooperative communication and relay technologies, a large swarm UAVs enlarge the effective coverage area IoT services via multiple nodes. However, low latency requirement dynamic topology UAV network bring in new challenges routing optimization among UAVs. In this paper, layered architecture is proposed an optimal number analyzed. Furthermore, algorithm (LLRA)...

Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive edge devices, which opens new horizons for numerous intelligent applications. Despite the potential benefits, FL imposes huge communication computation burdens on participating devices due to periodical global synchronization continuous local training, raising great challenges battery constrained devices. In this work, we target at improving...

In this paper, we investigate the minimization of total energy cost multiple residential households in a smart grid neighborhood sharing load serving entity. Specifically, each household may have renewable generation, storage as well inelastic and elastic loads, entity attempts to coordinate consumption these order minimize within neighborhood. The demand arrival, function are all stochastic processes evolve according some, possibly unknown, probabilistic laws. We develop an online control...

Secure communication is a promising technology for wireless networks because it ensures secure transmission of information. In this paper, we investigate the joint subcarrier (SC) assignment and power allocation problem non-orthogonal multiple access amplify-and-forward two-way relay networks, in presence eavesdroppers. By exploiting cooperative jamming (CJ) to enhance security link, aim maximize achievable secrecy energy efficiency by jointly designing SC assignment, user pair scheduling...

Privacy protection is of critical concern to Location-Based Service (LBS) users in mobile networks. Long-term pseudonyms, although appear be anonymous, fact empower third-party service providers continuously track users' movements. Researchers have proposed the mix zone model allow pseudonym changes protected areas. In this paper, we investigate a new form privacy attack LBS system that an adversary reveals user's true identity and complete moving trajectory with aid side information. We...

The prevalence of high performance mobile devices such as smartphones and tablets has brought fundamental changes to existing wireless networks. growth multimedia location-based services exponentially increased network congestion the demands for more access. This led development advanced techniques address resulting challenges based on concept cooperation in various heterogeneous scenarios. Thus, innovative incentive mechanisms networks are needed ensure participation third party nodes,...

Federated learning is a promising tool in the Internet-of-Things (IoT) domain for training machine model decentralized manner. Specifically, data owners (e.g., IoT device consumers) keep their raw and only share local computation results to train global of owner an service provider). When executing federated task, contribute communication resources. In this situation, have face privacy issues where attackers may infer property or recover based on shared information. Considering these...

In device-to-device (D2D) communication, mobile users communicate directly without going through the base station. D2D commutation has advantage of improving spectrum efficiency. But interference introduced by resource sharing become a significant challenge. this paper, we try to optimize system throughput while simultaneously meeting quality service (QoS) requirements for both and cellular (CUs). We implement matching theory solve allocation problem. utilize two efficient stable algorithms...

In recent years, ambient backscatter communications have gained a lot of interests as promising enabling technology for the Internet-of-Things and green communications. communication systems, ultra-low power devices are able to transmit information by backscattering radio-frequency signals generated legacy systems such Wi-Fi cellular networks. This paper is concerned with over orthogonal frequency division multiplexing (OFDM) signals. We propose modulation scheme that allows take advantage...

As one of the most promising networks, space–air–ground–aqua integrated network (SAGAIN) has characteristics wide coverage and large information capacity, which can meet various requests from users in different domains. With rapid growth data generated by Internet Things (IoT), SAGAIN received much attention recent years. However, existing architectures are not capable providing personalized services according to task types SAGAIN. Besides, they cannot deal with many problems well, such as...

Federated learning (FL) through its novel applications and services has enhanced presence as a promising tool in the Internet of Things (IoT) domain. Specifically, multiaccess edge computing setup with host IoT devices, FL is most suitable since it leverages distributed client data to train high-performance deep (DL) models while keeping private. However, underlying neural networks (DNNs) are huge, preventing direct deployment onto resource-constrained memory-limited devices. Besides,...

Federated learning (FL) over mobile devices has fostered numerous intriguing applications/services, many of which are delay-sensitive. In this paper, we propose a service delay efficient FL (SDEFL) scheme devices. Unlike traditional communication FL, regards wireless communications as the bottleneck, find that under situations, local computing is comparable to during training process, given development high-speed transmission techniques. Thus, in should be + rounds. To minimize simply...

The essential impediment to apply cognitive radio (CR) technology for spectrum utilization improvement lies in the uncertainty of licensed supply. In this paper, we investigate joint routing and link scheduling problem multi-hop CR networks under uncertain We model vacancy bands with a series random variables, introduce corresponding constraints flow such network. From network planner/operator's point view, characterize pair (α, β) parameters, present mathematical formulation goal minimizing...

Microeconomics-inspired spectrum auctions can dramatically improve the utilization for wireless networks to satisfy ever increasing service demands. However, back-room dealing (i.e., frauds of insincere auctioneer and bid-rigging between greedy bidders auctioneer) poses significant security challenges, fails all existing secure auction designs allocate bands when considering frequency reuse in networks. In this paper, we propose THEMIS, a leveraging Paillier cryptosystem prevent as well...

Throughput maximization is a key challenge for wireless applications in cognitive Vehicular Ad-hoc Networks (C-VANETs). As potential solution, cooperative communications, which may increase link capacity by exploiting spatial diversity, has attracted lot of attention recent years. However, if scheduling considered, this transmission mode perform worse than direct terms end-to-end throughput. In paper, we propose communication aware scheme and investigate the throughput problem C-VANETs....

Numerous applications of wireless sensor networks (WSNs) in harsh terrains are constrained by the sensors' battery-power and face difficulties data collection. In this paper, we propose to exploit power transfer technology replenish energy clusters develop an efficient collection scheme for those rechargeable senor deployed terrains. view terrains, employ unmanned aerial vehicles (UAVs) travel sites clusters, collect data, recharge sensors corresponding clusters. With joint consideration...

Recent developments on DFWS have shown that wireless signals can be utilized not only as a communication medium to transmit data, but also an enabling tool for realizing non-intrusive device-free sensing. has many potential applications, example, human detection and localization, activity gesture recognition, surveillance, elder or patient monitoring, emergency rescue, so on. With the development maturity of DFWS, we believe it will eventually empower traditional networks with augmented...

With the wide adoption of smart mobile devices, there is a rapid development location-based services. One key feature supporting pleasant/excellent service access to adequate and comprehensive data, which can be obtained by crowdsourcing. The main challenge in crowdsourcing how provider (principal) incentivizes large group users participate. In this paper, we investigate problem designing tournament maximize principal's utility provide continuous incentives for rewarding them based on rank...

In this paper, the non-orthogonal multiple access (NOMA) technology is integrated into cognitive orthogonal frequency-division multiplexing (OFDM) systems, called OFDM-NOMA, to boost system capacity. First, a capacity maximization problem considered in half-duplex OFDM-NOMA systems with two accessible users on each subcarrier. Due intractability of problem, we decompose it three subproblems, i.e., optimization of, respectively, sensing duration, user scheduling, and power allocation. By...

Recent advances in device-free wireless sensing (DFS) have shown that it may eventually evolve traditional networks into smart which could sense surrounding target location and activity information without equipping the with any devices. Despite its promising application prospects, one challenging problem to be solved is performance of DFS system degrades significantly complex scenarios, such as through-wall non-line-of-sight (NLOS) scenarios. To alleviate this problem, paper seeks explore...

Device-free gesture recognition (DFGR) is a promising sensing technique, which can recognize by analyzing its influence on surrounding wireless signals. Most of the DFGR systems are designed based machine learning. However, performance will drop dramatically when testing condition different with training one. Inspired transferrable knowledge learning ability humans, this paper develops practical system metalearning to solve aforementioned problem. Specifically, we design deep network could...