Information-centric networking (ICN) offers new perspectives on mobile ad-hoc communication because routing is based on names but not on endpoint identifiers. Since every content object has a unique ...name and is signed, authentic content can be stored and cached by any node. If connectivity to a content source breaks, it is not necessarily required to build a new path to the same source but content can also be retrieved from a closer node that provides the same content copy. For example, in case of collisions, retransmissions do not need to be performed over the entire path but due to caching only over the link where the collision occurred. Furthermore, multiple requests can be aggregated to improve scalability of wireless multi-hop communication. In this work, we base our investigations on Content-Centric Networking (CCN), which is a popular ICN architecture. While related works in wireless CCN communication are based on broadcast communication exclusively, we show that this is not needed for efficient mobile ad-hoc communication. With Dynamic Unicast requesters can build unicast paths to content sources after they have been identified via broadcast. We have implemented Dynamic Unicast in CCNx, which provides a reference implementation of the CCN concepts, and performed extensive evaluations in diverse mobile scenarios using NS3-DCE, the direct code execution framework for the NS3 network simulator. Our evaluations show that Dynamic Unicast can result in more efficient communication than broadcast communication, but still supports all CCN advantages such as caching, scalability and implicit content discovery.
The millimeter-wave (mmWave) spectrum has become a core of wireless communication, which has the advantages of richer spectrum resources, larger communication bandwidth, and smaller spectrum ...interference. Human activity recognition (HAR) by mmWave radar based on point cloud attracts significant attention due to its nature of privacy-preserving, which is an important task of realizing integrated sensing and communication (ISAC). This article proposes a framework of spatial-temporal point cloud transformer (ST-PCT) to realize high precision of HAR, based on sequential point cloud after preprocessing from mmWave radar without voxelization. In ST-PCT, it consists of four enhanced components: 1) a framewise spatial neighbor embedding module to extract the local feature; 2) a temporal and spatial attention mechanism module to find connections within and across frames; 3) an optimized attention mechanism to improve the efficiency of feature extraction; and 4) a sensor fusion module with more motion information to improve the difference between activities. We experimentally evaluate the efficiency of our framework compared with several approaches based on the voxelization or point cloud directly. The experimental results have demonstrated that the proposed ST-PCT network greatly outperforms the other approaches in terms of overall accuracy (oAcc), achieving 99.06% and 99.44%, respectively, on two data sets.
With the fast development of location-based services, an ubiquitous indoor positioning approach with high accuracy and low calibration has become increasingly important. In this work, we target on a ...crowdsourcing approach with zero calibration effort based on visible light, magnetic field, and WiFi to achieve submeter accuracy. We propose a CrowdFusion simultaneous localization and mapping (SLAM) composed of coarse-grained and fine-grained trace merging, respectively, based on the iterative closest point (ICP) SLAM and GraphSLAM. ICP SLAM is proposed to correct the relative locations and directions of crowdsourcing traces and GraphSLAM is further adopted for fine-grained pose optimization. In CrowdFusion SLAM, visible light is used to accurately detect loop closures and magnetic field to extend the coverage. According to the merged traces, we construct a radio map with visible light and WiFi fingerprints. An enhanced particle filter fusing inertial sensors, visible light, WiFi, and floor plan is designed, in which visible light fingerprinting is used to improve the accuracy and increase the resampling/rebooting efficiency. We evaluate CrowdFusion based on comprehensive experiments. The evaluation results show a mean accuracy of 0.67 m for the merged traces and 0.77 m for positioning, merely replying on crowdsourcing traces without professional calibration.
Contemporary applications leverage machine learning models to optimize performance, often necessitating data transmission to a remote server for training. However, this approach entails significant ...resource consumption. A privacy concern arises, which Federated Learning addresses through a cyclical process involving in-device training (local model update) and subsequent reporting to the server for aggregation (global model update). In each iteration of this cycle, termed a communication round, a client selection component determines participant devices contributing to global model enhancement. However, existing literature inadequately addresses scenarios where optimized energy consumption is imperative. This paper introduces an Energy Saving Client Selection (ESCS) mechanism, considering decision criteria such as battery level, training time capacity, and network quality. As a pertinent use case, classification scenarios are utilized to compare the performance of ESCS against other state-of-the-art approaches. The findings reveal that ESCS effectively conserves energy while maintaining optimal performance. This research contributes to the ongoing discourse on energy-efficient client selection strategies within the domain of Federated Learning.
Mobile Edge Computing enables the deployment of services, applications, content storage and processing in close proximity to mobile end users. This highly distributed computing environment can be ...used to provide ultra-low latency, precise positional awareness and agile applications, which could significantly improve user experience. In order to achieve this, it is necessary to consider next-generation paradigms such as Information-Centric Networking and Cloud Computing, integrated with the upcoming 5th Generation networking access. A cohesive end-to-end architecture is proposed, fully exploiting Information-Centric Networking together with the Mobile Follow-Me Cloud approach, for enhancing the migration of content-caches located at the edge of cloudified mobile networks. The chosen content-relocation algorithm attains content-availability improvements of up to 500% when a mobile user performs a request and compared against other existing solutions. The performed evaluation considers a realistic core-network, with functional and non-functional measurements, including the deployment of the entire system, computation and allocation/migration of resources. The achieved results reveal that the proposed architecture is beneficial not only from the users’ perspective but also from the providers point-of-view, which may be able to optimize their resources and reach significant bandwidth savings.
•A new model is introduced for optimized content migration in mobile networks.•The architecture fully exploits new concepts such as Future Internet and NFV.•Mobility prediction in LTE virtualized networks further improves the system.•It achieves fivefold improvements in performance experienced by end users.•Mobile network providers optimize resources and have significant savings.
The operation of inventory systems plays an important role in the success of manufacturing companies, making it a highly relevant domain for optimization. In particular, the domain lends itself to ...being approached via Deep Reinforcement Learning (DRL) models due to it requiring sequential reorder decisions based on uncertainty to minimize cost. In this paper, we evaluate state-of-the-art optimization approaches to determine whether Deep Reinforcement Learning can be applied to the multi-echelon inventory optimization (MEIO) framework in a practically feasible manner to generate fully dynamic reorder policies. We investigate how it performs in comparison to an optimized static reorder policy, how robust it is when it comes to structural changes in the environment, and whether the use of DRL is safe in terms of risk in real-world applications. Our results show promising performance for DRL with potential for improvement in terms of minimizing risky behavior.
Future mobile communication networks need Unmanned Aerial Vehicles as Base Stations (UAVasBSs) with the fast-moving and long-term hovering capabilities to guarantee consistent network performance. ...UAVasBSs help 5G/B5G mobile communication systems to rapidly recover from emergency situations and handle the instant traffic of the flash crowd. In this context, multiple UAVs might form a flying ad-hoc network to establish a flying access network to enhance the network connectivity and service quality. Therefore, it is important to determine the optimal number and locations of UAVasBSs in a fast and efficient way to cover the target area to provide temporary yet reliable cellular connectivity. The use of Artificial Intelligence (AI) and network data analysis are key tools to fulfill the above issues. In this article, we propose a smart UAVasBS placement (SUAP) mechanism to improve the mobile network operations in flash crowd and emergency situations. We have modeled such an UAVasBS placement task as an optimization problem to obtain required network connectivity and system performance, and resolved it with a genetic algorithm using the network context information. Simulation results show that our proposal could cover 90% of mobile users, and it provides nearly 90% packet delivery ratio for users with a fast convergence rate.
Cloud Computing has evolved to become an enabler for delivering access to large scale distributed applications running on managed network-connected computing systems. This makes possible hosting ...Distributed Enterprise Information Systems (dEISs) in cloud environments, while enforcing strict performance and quality of service requirements, defined using Service Level Agreements (SLAs). SLAs define the performance boundaries of distributed applications, and are enforced by a cloud management system (CMS) dynamically allocating the available computing resources to the cloud services. We present two novel VM-scaling algorithms focused on dEIS systems, which optimally detect most appropriate scaling conditions using performance-models of distributed applications derived from constant-workload benchmarks, together with SLA-specified performance constraints. We simulate the VM-scaling algorithms in a cloud simulator and compare against trace-based performance models of dEISs. We compare a total of three SLA-based VM-scaling algorithms (one using prediction mechanisms) based on a real-world application scenario involving a large variable number of users. Our results show that it is beneficial to use autoregressive predictive SLA-driven scaling algorithms in cloud management systems for guaranteeing performance invariants of distributed cloud applications, as opposed to using only reactive SLA-based VM-scaling algorithms.
Vehicular Networks (VN) enable the collaboration among vehicles and infrastructure to deliver network services, where usually value-added services are provided by cloud computing. In this context, ...fog computing can be deployed closer to the users to meet their needs with minimum help from the Internet infrastructure. Software Defined Networking (SDN) might support the use of large-scale fog-enabled VN services. However, the current management of each wireless network that composes the VN has restricted the exploration of fog-enabled VN services. Therefore, the design principles for a VN architecture is still an open issue, mainly because it is necessary to address the diversity of VN fog applications. In this article, we investigate the design principles for fog-enabled Vehicular Software Defined Networking (VSDN) focusing on the perspectives of the systems, networking, and services. We evaluated these design principles in a use case of a traffic management system for a fast traffic accident rescue, using real traffic accident data. Finally, potential research challenges and opportunities for integrated use fog-enabled VSDN are discussed.
Seamless outdoor-indoor positioning plays a critical role in many emerging applications, e.g., large-coverage user navigation in cities, smart buildings, and analytics of user spatial location big ...data. It is still challenging to construct a large-scale seamless outdoor-indoor positioning system due to the limited coverage of indoor positioning. In this paper, we propose a seamless outdoor-indoor crowdsensing positioning (SoiCP) system in which a radio map is automatically constructed based on crowdsourcing pedestrian dead reckoning (PDR) traces without professional site surveying. The constructed radio map is robust to inaccurate PDR traces and does not rely on prior knowledge of floor plans. In SoiCP, the crowdsensed radio map is obtained by a proposed three-step trace matching algorithm. This algorithm leverages building gates and WiFi fingerprints as landmarks to merge the noisy crowdsourcing traces and accurately construct the user walking paths. Moreover, following the crowdsensed radio map, SoiCP uses an enhanced particle filter to fuse PDR, GPS, and WiFi fingerprinting for seamless outdoor-indoor positioning with high accuracy. The comprehensive real-world experiments in two large-scale shopping malls demonstrate that SoiCP can effectively crowdsense the walking paths and track moving users with high accuracy.