Task Distribution Method of Participatory Sensing Based on Urban Rail Transit
-
摘要: 随着当前移动终端设备的发展和5G技术的普及,移动群智感知的需求越来越大。但是目前感知任务的分发方法依然存在着传输效率低下、代价高且不稳定等问题,极大地限制了感知终端任务的完成。为此,该文利用城市轨道交通对于各大城区良好的覆盖性和轨道交通的可预测性,提出了面向激励成本的任务分发模型(ICTDM)和面向用户数量的任务分发模型(UNTDM)。通过轨道交通对聚集式人流的疏导性,实现感知任务在城市不同区域的选择性分发。并以任务所需人数和移动距离的最小化作为手段,完成降低系统总激励成本的目的。实验结果表明,该算法与同类算法相比,可以在完成相同任务集合的前提下,通过优化任务分发过程实现更少的任务参与者分发方案,以达到降低感知任务成本的目的。Abstract: With the current development of mobile terminal devices and the popularity of 5G technology, there is an increasing demand for mobile group intelligence awareness. However, the current distribution methods for sensing tasks still suffer from inefficient, costly and unstable transmission, which limits greatly the completion of sensing terminal tasks. For this reason, an Incentive Cost Task Distribution Model (ICTDM) and a User Number Task Distribution Model (UNTDM) based on the good coverage of urban rail transit and the predictability of urban rail transit are proposed. The selective distribution of sensory tasks in different areas of the city is achieved through the sparseness of rail traffic for aggregated pedestrian flows. And the minimization of the number of people required for the task and the distance moved is used as a means to accomplish the purpose of reducing the total incentive cost of the system. Experimental results show that this algorithm can achieve fewer task participant distribution schemes by optimizing the task distribution process to reduce the cost of perceived tasks compared with similar algorithms, while completing the same set of tasks.
-
表 1 模型相关符号表
符号 意义 符号 意义 A 感知任务区域 e1 用户上车站点 γ 具体任务位置 e2 用户下车站点 c 任务聚类区域 B 实际上车乘客数 o 子区域中心坐标 I 预测下车乘客 s 地铁站点 r 各任务需要人数 t 需要分发的任务 h 各任务需要时间 T 待分发任务集合 m 可选参与者数量 G 子区域覆盖情况 N 可分发的任务数 U 可选参与者集合 w(r) 任务大小 v 参与者步行速度 q 任务传输耗时 D 总移动距离 φ 任务传输速率 P 用户集合 Q 用户停留时间 表 2 智能卡数据格式
序号 数据项 数据类型 0 开始标识 int 1 进站时间 datetime 2 进站站点 int 3 进站闸机通道 int 4 到达标识 int 5 出站时间 datetime 6 出站站点 int 7 出站闸机通道 int 8 一卡通号 nvarchar 9 票卡类型 int 表 3 模型参数设置
参数 取值 参数 取值 N 1120 h 5 min m 3000 φ 1 MB/s v 40 m/min w(r) 0.2~2.0 MB r 3 表 4 实验软硬件环境
类别 型号 服务器 Sugon W580-G20 系统 CentOS release 7.3.1611 内核 3.10.0-514.26.2.el7.x86_64 CPU Intel Xeon(R) E5-2609 v3 GPU 2 * Tesla K80 表 5 算法应用场景对比
总成本 耗时 所需参与者 应用场景 ICTDM 最低 较高 较少 延时容忍的日常场景 UNTDM 较低 较低 最少 低延时的应急场景 -
[1] XIAO Fu, JIANG Zhifei, XIE Xiaohui, et al. An energy-efficient data transmission protocol for mobile crowd sensing[J]. Peer-to-Peer Networking and Applications, 2017, 10(3): 510–518. doi: 10.1007/s12083-016-0497-5 [2] LI He, OTA K, DONG Mianxiong, et al. Mobile crowdsensing in software defined opportunistic networks[J]. IEEE Communications Magazine, 2017, 55(6): 140–145. doi: 10.1109/MCOM.2017.1600719 [3] LI Hanshang, LI Ting, WANG Weichao, et al. Dynamic participant selection for large-scale mobile crowd sensing[J]. IEEE Transactions on Mobile Computing, 2019, 18(12): 2842–2855. doi: 10.1109/TMC.2018.2884945 [4] JIANG Weijin, LV Sijian, WANG Yang, et al. Computational experimental study on social organization behavior prediction problems[J]. IEEE Transactions on Computational Social Systems, 2021, 8(1): 148–160. doi: 10.1109/TCSS.2020.3017818 [5] JIANG Weijin, LV Sijian, JIANG Yirong, et al. Evolutionary dynamics modeling of symbolic social network structure equilibrium[J]. China Communications, 2020, 17(10): 229–240. doi: 10.23919/JCC.2020.10.017 [6] 刘琰, 郭斌, 吴文乐, 等. 移动群智感知多任务参与者优选方法研究[J]. 计算机学报, 2017, 40(8): 1872–1887. doi: 10.11897/SP.J.1016.2017.01872LIU Yan, GUO Bin, WU Wenle, et al. Multitask-oriented participant selection in mobile crowd sensing[J]. Chinese Journal of Computers, 2017, 40(8): 1872–1887. doi: 10.11897/SP.J.1016.2017.01872 [7] JIANG Weijin and LV Sijian. Hierarchical deployment of deep neural networks based on fog computing inferred acceleration model[J]. Cluster Computing, To be published. doi: 10.1007/s10586-021-03298-0 [8] 陈忠辉, 凌献尧, 冯心欣, 等. 基于模糊C均值聚类和随机森林的短时交通状态预测方法[J]. 电子与信息学报, 2018, 40(8): 1879–1886. doi: 10.11999/JEIT171090CHEN Zhonghui, LING Xianyao, FENG Xinxin, et al. Short-term traffic state prediction approach based on FCM and random forest[J]. Journal of Electronics &Information Technology, 2018, 40(8): 1879–1886. doi: 10.11999/JEIT171090 [9] 安健, 彭振龙, 桂小林, 等. 群智感知中基于公交系统的任务分发机制研究[J]. 计算机学报, 2019, 42(2): 295–308. doi: 10.11897/SP.J.1016.2019.00295AN Jian, PENG Zhenlong, GUI Xiaolin, et al. Research on task distribution mechanism based on public transit system in crowd sensing[J]. Chinese Journal of Computers, 2019, 42(2): 295–308. doi: 10.11897/SP.J.1016.2019.00295 [10] ZHANG Yanru, JIANG Chunxiao, SONG Lingyang, et al. Incentive mechanism for mobile crowdsourcing using an optimized tournament model[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(4): 880–892. doi: 10.1109/JSAC.2017.2680798 [11] ZHANG Maotian, YANG Panlong, TIAN Chang, et al. Toward optimum crowdsensing coverage with guaranteed performance[J]. IEEE Sensors Journal, 2016, 16(5): 1471–1480. doi: 10.1109/JSEN.2015.2501371 [12] ZHANG Daqing, XIONG Haoyi, WANG Leye, et al. CrowdRecruiter: Selecting participants for piggyback crowdsensing under probabilistic coverage constraint[C]. Proceedings of 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Seattle, United States, 2014: 703–714. doi: 10.1145/2632048.2632059. [13] ALSWAILIM M A, HASSANEIN H S, and ZULKERNINE M. A reputation system to evaluate participants for participatory sensing[C]. Proceedings of 2016 IEEE Global Communications Conference (GLOBECOM), Washington, USA, 2016: 1–6. doi: 10.1109/GLOCOM.2016.7841540. [14] GUO Bin, LIU Yan, WU Wenle, et al. ActiveCrowd: A framework for optimized multitask allocation in mobile crowdsensing systems[J]. IEEE Transactions on Human-Machine Systems, 2017, 47(3): 392–403. doi: 10.1109/THMS.2016.2599489 [15] KARALIOPOULOS M, TELELIS O, and KOUTSOPOULOS I. User recruitment for mobile crowdsensing over opportunistic networks[C]. Proceedings of 2015 IEEE Conference on Computer Communications (INFOCOM), Hong Kong, China, 2015: 2254–2262. doi: 10.1109/INFOCOM.2015.7218612. [16] LI Zhidu, LIU Hailiang, and WANG Ruyan. Service benefit aware multi-task assignment strategy for mobile crowd sensing[J]. Sensors, 2019, 19(21): 4666. doi: 10.3390/s19214666