To provide real-time map information, roadside units (RSUs) near vehicles cache 3D map tiles to reduce transmission delays and alleviate backhaul congestion. Unfortunately, traditional cache problems primarily focus on maximizing the cache hit rate (i.e., popularity) while often neglecting other criteria, thus suppressing caching efficiency. For instance, the priority of each map tile may vary for different vehicles based on their route plans and current positions. Additionally, caching a greater number of small-scale map tiles with broader coverage helps serve more vehicles’ requests and reduce cache misses. However, these tiles may only be sufficient for vehicles that can tolerate lower detail levels, as they provide less information than large-scale tiles. Furthermore, ensuring the freshness of cached map tiles is essential for maintaining driving safety. To address the interplay among popularity, priority, map scale, and information freshness in online map caching, this paper formulates an online optimization problem and proposes a novel online algorithm called ADAM, which integrates mixed-integer linear programming (MILP) with deep reinforcement learning. The ADAM predicts future total costs to support caching decisions by leveraging an ingeniously designed MILP that emulates the behavior of a neural network. Finally, simulation results manifest that the proposed ADAM outperforms existing methods by an average of 50%.

Telecom carriers have announced new content services by making a partnership with content providers and offered popular video streaming to customers. Via the integration with edge networks, telecom carriers can procure various contents from content providers and place them on edge servers proximate to end users to serve real-time requests with high bandwidth and ultra-low latency. Nevertheless, it is challenging to consider the content procurement, placement, and services jointly due to the user preference, user distribution, storage capacity of edge server, economic costs, etc. Telecom carriers would like to balance the procuring, placing, and transfer costs. To address this problem, the paper formulates an optimization problem and then proposes an approximation algorithm. Finally, the simulation results manifest that our algorithm outperforms other baselines.

Dockless electric bike (E-bike) sharing has become a new urban modality of green transportation to offer convenient services. Typically, the service provider arranges a truck starting from the depot to visit multiple parking locations to replace low-energy batteries. However, visiting many parking locations may cause a considerable tour cost. One efficient way is to aggregate low-energy E-bikes together. Some incentive mechanisms are thus adopted to encourage E-bike users to move their bikes to suitable parking locations, but leading to an incentive cost. The service provider would like to balance the tour cost of the truck and the incentive cost of E-bike users. To address this problem, the paper formulates an optimization problem and then proposes an approximation algorithm. The simulation results with the real dataset show that our algorithm outperforms the other baselines.

Cooperative intelligent transport systems (C-ITS) enable fast communication among vehicles, infrastructure, and other road users. Via C-ITS, vehicles can acquire the real-time traffic information from various C-ITS stations, especially the information of the highly dynamic data in the local dynamic map (LDM). In the paper, we consider the message broadcast from the trustworthy roadside unit (RSU) to vehicles, where the messages have different popularity levels (i.e., how many vehicles request for this message), generation time of last-received corresponding messages, and priority towards each vehicle. Besides, the freshness of information of messages needs to be as fresh as possible. To explore the non-trivial order of transmission in time under the limited bandwidth, we formulate an optimization problem named ROAD to find an efficient transmission schedule and propose an approximation algorithm termed ABS. Experiment results manifest that ABS outperforms traditional approaches by 40%.

Online Decentralized Learning (ODL) is suitable for Internet-of-Things (IoT) devices since only parameter updates are exchanged with neighbors to avoid uploading private data to a central server and the training data is allowed to arrive at the devices sequentially. However, the current ODL frameworks cannot support the emerging Social IoT (SIoT) paradigm favorably since the SIoT devices exchange parameter updates with only trust-worthy neighbors based on specific social relations (e.g., parental object relation and ownership object relation). Conversely, sharing parameter updates with untrustworthy neighbors could speed up the training process but may violate social relations. Differential privacy (DP) is thus used to ensure data security while excessive devices engaging DP may downgrade the training performance. However, most research neglects the effect of neighbor selection for each device based on social networks, physical networks, and DP. Thus, in this paper, we innovate an ODL framework ODLF-PDP to allow only a part of devices to engage DP (i.e., partially DP) to improve training performance. Then, an algorithm BeTTa is proposed to build an adequate communication topology based on the interplay among the social networks, physical networks, and DP. Last, the experiment results manifest that ODLF-PDP saves more than 20% physical training time compared to the current frameworks via the benchmark of MNIST.

Decentralized learning (DL) allows IoT devices to exchange local model updates with only their neighboring devices instead of sending their model updates to a central server for aggregation. However, current DL frameworks cannot support the emerging Social IoT(SIoT) paradigm since SIoT devices exchange model updates with only social neighbors based on specific social relations (e.g., ownership and parental relationships). Conversely, sharing model updates with non-social neighbors can improve training performance but may violate social relations. Differential privacy (DP) is thus engaged with DL to ensure data security, while excessive devices engaging DP may downgrade the training performance. However, most research neglects the effect of neighbor selection for each device based on social networks, physical networks, and DP. Therefore, in this paper, we explore the non-trivial relation among the above factors to present a DL framework, DeepPrivacy, and prove its convergence rate and DP. Then, we formulate a novel optimization problem, CoTOPO, to find an efficient communication topology1for model updates exchange among devices in DL, and propose an algorithm, AutoTag, for CoTOPO. Last, experiment results manifest that DeepPrivacy and AutoTag combined outperform the state of the art in terms of convergence rate and physical training time significantly on CIFAR10 and FMNIST.