Search

Localization services play an important role in Internet of Connected Vehicles (IoCV) and vehicle predictive localization information can greatly improve traffic efficiency and reduce accidents. However, a huge amount of computing and communication overhead is required to obtain such information by traditional methods. In this work, we propose a Behavior-based Clustering Method (BCM) to analyze the behavioral correlation between vehicles and classify them into different clusters. Based on BCM results coupled with a deep learning model, we further propose a Clustering-learning-based Long-term Predictive Localization (CLPL) algorithm to predict vehicles’ future location distribution. In the proposed CLPL algorithm, all the traffic roads are divided into consecutive small segments in order to pinpoint vehicles’ precise current locations and to obtain long-term predictions. Extensive simulations, notably involving real dataset, have been carried out to evaluate BCM and CLPL in terms of several performance criteria including matching rates. The analysis of the results validated how the designed methods can predict vehicle location much more accurately than existing algorithms. [ABSTRACT FROM AUTHOR]

The proliferation of the greedy heterogeneous wireless network demands the ability to handle the sharply increasing resource requirements of power and spectrum. Thus, the study of novel and effective methods to allocate power and spectrum resources in order to reduce energy consumption for heterogeneous devices has become an urgent issue. In this context the article proposes a DJRA in which data fusion, combined with NOMA, SIC and beamforming techniques, are utilized to allocate power and spectrum resources to heterogeneous devices with a reduced energy consumption, where different radio access technologies are integrated into a cellular network for communication between devices. The data correlations between the devices are computed to group the devices so as to reduce data transmission. In addition, NOMA, SIC and beamforming are used in combination to reduce network interference between BSs and the heterogeneous devices. The main contribution of this article is the design of a large-scale heterogeneous wireless network paradigm to improve the percentage of resource utilization also reducing the energy consumption. [ABSTRACT FROM AUTHOR]

Rapidly growing wireless networks are facing spectrum shortages, so how to improve spectrum utilization becomes critical. The rise of artificial intelligence (AI) technologies can provide a more intelligent and effective strategy for realizing cognitive wireless communication to improve spectrum utilization. Therefore, this article uses AI technology for data analytics, and combines cognitive technology to perform dynamic spectrum allocation. In terms of data analytics, AI technology is utilized in both feature extraction and data dimensionality, and the data correlation calculation between users. Then the data analytics results are applied to the spectrum allocation. Combined with deep learning, an AI-driven data-analytics-based spectrum allocation (ADASA) algorithm is proposed. ADASA enables the adaptive adjustment of the allocation parameters according to the network environmental status when allocating spectrum to users. Finally, the simulation results prove that the proposed ADASA algorithm can effectively improve the spectrum utilization in heterogeneous wireless networks. [ABSTRACT FROM AUTHOR]

The space-terrestrial integrated network (STIN), one of the hottest trends in technology, is transforming our future through interconnecting heterogeneous devices. It has a revolutionary impact on reshaping the industry and changing the world. The extending of new generation network spectrum resources creates tremendous opportunities for obtaining high-level terrestrial network and brings a good prospect for the development of STIN, but STIN still faces a big change of resource shortage caused by the ever increasing heterogeneous devices. In this article, a new STIN architecture supporting virtualization technology is first designed to manage spectrum resource in STIN to satisfy various quality of service (QoS) requirements from heterogeneous devices. Then a dynamic virtualized QoS-driven spectrum allocation algorithm (VQSA) is proposed to improve the QoS from different devices in STIN. VQSA classifies heterogeneous devices into virtual cells according to their QoS correlation and determines the corresponding base stations and satellites for providing services. Spectrum resources in multiple base stations and satellites are rationally assigned in a virtual cell to serve heterogeneous devices with different QoS requirements. Finally, simulation results are provided to show the efficiency of the architecture and the VQSA algorithm in terms of transmission delay and transmission rate. [ABSTRACT FROM AUTHOR]

The space-terrestrial integrated network (STIN), one of the hottest trends in technology, is transforming our future through interconnecting heterogeneous devices. It has a revolutionary impact on reshaping the industry and changing the world. The extending of new generation network spectrum resources creates tremendous opportunities for obtaining high-level terrestrial network and brings a good prospect for the development of STIN, but STIN still faces a big change of resource shortage caused by the ever increasing heterogeneous devices. In this article, a new STIN architecture supporting virtualization technology is first designed to manage spectrum resource in STIN to satisfy various quality of service (QoS) requirements from heterogeneous devices. Then a dynamic virtualized QoS-driven spectrum allocation algorithm (VQSA) is proposed to improve the QoS from different devices in STIN. VQSA classifies heterogeneous devices into virtual cells according to their QoS correlation and determines the corresponding base stations and satellites for providing services. Spectrum resources in multiple base stations and satellites are rationally assigned in a virtual cell to serve heterogeneous devices with different QoS requirements. Finally, simulation results are provided to show the efficiency of the architecture and the VQSA algorithm in terms of transmission delay and transmission rate. [ABSTRACT FROM AUTHOR]