TY - JOUR
T1 - QoS provision for vehicle big data by parallel transmission based on heterogeneous network characteristics prediction
AU - Qiao, Wenxuan
AU - Dong, Ping
AU - Du, Xiaojiang
AU - Zhang, Yuyang
AU - Zhang, Hongke
AU - Guizani, Mohsen
N1 - Publisher Copyright:
© 2022 Elsevier Inc.
PY - 2022/5
Y1 - 2022/5
N2 - Multipath parallel transmission has become an important research direction to improve big data transmission efficiency of connected vehicles. However, due to the heterogeneity and time-varying characteristics of parallel transmission paths, packets transmitted in parallel are usually out-of-order delivered to the destination, which greatly limits the throughput. To Lift the restriction of out-of-order delivery on the efficiency of big data transmission, this paper proposes a packet-granular real-time shortest delay scheduling scheme for multipath transmission based on path characteristics prediction. The scheme first clusters and models the heterogeneous network, which greatly reduces the complexity of the network. Subsequently, a prediction algorithm that can quickly converge to real-time delay is proposed. Then the details of the scheduling scheme are introduced by modules, and the bandwidth aggregation efficiency close to the theoretical upper limit is proved through simulation. Finally, we summarize the applicable scenarios and future work of the scheme.
AB - Multipath parallel transmission has become an important research direction to improve big data transmission efficiency of connected vehicles. However, due to the heterogeneity and time-varying characteristics of parallel transmission paths, packets transmitted in parallel are usually out-of-order delivered to the destination, which greatly limits the throughput. To Lift the restriction of out-of-order delivery on the efficiency of big data transmission, this paper proposes a packet-granular real-time shortest delay scheduling scheme for multipath transmission based on path characteristics prediction. The scheme first clusters and models the heterogeneous network, which greatly reduces the complexity of the network. Subsequently, a prediction algorithm that can quickly converge to real-time delay is proposed. Then the details of the scheduling scheme are introduced by modules, and the bandwidth aggregation efficiency close to the theoretical upper limit is proved through simulation. Finally, we summarize the applicable scenarios and future work of the scheme.
KW - Big data
KW - Multipath parallel transmission
KW - Network bottleneck prediction
KW - Quality of service
KW - Vehicular networks
UR - http://www.scopus.com/inward/record.url?scp=85124297577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124297577&partnerID=8YFLogxK
U2 - 10.1016/j.jpdc.2022.01.018
DO - 10.1016/j.jpdc.2022.01.018
M3 - Article
AN - SCOPUS:85124297577
SN - 0743-7315
VL - 163
SP - 83
EP - 96
JO - Journal of Parallel and Distributed Computing
JF - Journal of Parallel and Distributed Computing
ER -