Abstract
Mobile WiFi is a newly emerging service in recent years, which provides convenience for users to access online resources and increases revenues for operators via services such as advertisements and application promotions. However, in practice, the prohibitively high system implementation and operational costs, especially the costs of perpetual data traffic, hinder the further deployment of mobile WiFi services. In this paper, we present MIMU, a usage inference system for data traffic saving suitable for ubiquitous mobile WiFi services. We demonstrate the performance of the system via an example from the real-world nationwide edge computing mobile WiFi infrastructure. To address the impact of diverse user behaviors, we investigate the WiFi network usage from the perspective of users and devices, focusing on two unique features of mobile WiFi: user mobility regularity and access irregularity. In particular, we first design a deep learning-based two-dimension usage predictor to infer the future mobile WiFi usage with 1) a user dimension model with temporal attention addressing dominant users with heavy bus WiFi usage, and 2) a device dimension model with spatial attention addressing diverse WiFi usage and connection. Based on the results of the predictor, an application of content caching is implemented in an iterative fashion to save the data traffic. We evaluate MIMU by real-world bus WiFi system data sets of three major cities with 6,643 bus WiFi devices and 150k daily active users in total. Our results show that MIMU outperforms state-of-the-art methods in terms of usage inference. Moreover, we summarize the lessons learned from our large-scale bus WiFi system investigation.
- AALSMEER. 2017. Staying connected: why WiFi in public transportation is the future. https://www.mondicon.com/news/Why-Wifi-in-transportation-is-the-future.html.Google Scholar
- Mikhail Afanasyev, Tsuwei Chen, Geoffrey M Voelker, and Alex C Snoeren. 2010. Usage patterns in an urban WiFi network. IEEE/ACM Transactions on Networking (TON) 18, 5 (2010), 1359--1372.Google ScholarDigital Library
- Sehyun Bae, Daehyun Ban, Dahyeon Han, Jiyoung Kim, Kyu-haeng Lee, Sangsoon Lim, Woojin Park, and Chong-kwon Kim. 2015. Streetsense: Effect of bus wi-fi aps on pedestrian smartphone. In Proceedings of the 2015 Internet Measurement Conference. ACM, 347--353.Google ScholarDigital Library
- Aruna Balasubramanian, Ratul Mahajan, Arun Venkataramani, Brian Neil Levine, and John Zahorjan. 2008. Interactive wifi connectivity for moving vehicles. ACM SIGCOMM Computer Communication Review 38, 4 (2008), 427--438.Google ScholarDigital Library
- Hugo Barbosa, Marc Barthelemy, Gourab Ghoshal, Charlotte R James, Maxime Lenormand, Thomas Louail, Ronaldo Menezes, José J Ramasco, Filippo Simini, and Marcello Tomasini. 2018. Human mobility: Models and applications. Physics Reports 734 (2018), 1--74.Google ScholarCross Ref
- David P Blinn, Tristan Henderson, and David Kotz. 2005. Analysis of a Wi-Fi hotspot network. In Papers presented at the 2005 workshop on Wireless traffic measurements and modeling. USENIX Association, 1--6.Google Scholar
- Vladimir Brik, Shravan Rayanchu, Sharad Saha, Sayandeep Sen, Vivek Shrivastava, and Suman Banerjee. 2008. A measurement study of a commercial-grade urban wifi mesh. In Proceedings of the 8th ACM SIGCOMM conference on Internet measurement. ACM, 111--124.Google ScholarDigital Library
- Vladimir Bychkovsky, Bret Hull, Allen Miu, Hari Balakrishnan, and Samuel Madden. 2006. A measurement study of vehicular internet access using in situ Wi-Fi networks. In Proceedings of the 12th annual international conference on Mobile computing and networking. ACM, 50--61.Google ScholarDigital Library
- China Telecom. 2017. China Telecom 4G Data Plan Rate. https://www.189.cn/bj/support/tariff/ydtc/71929.html.Google Scholar
- China Telecom. 2017. China Telecom 4G Data Plan Rate. https://www.189.cn/ln/support/tariff/package/52346.html.Google Scholar
- E Clayirci and Ian F. Akyildiz. 2002. User mobility pattern scheme for location update and paging in wireless systems. IEEE Transactions on Mobile Computing 99, 3 (2002), 236--247.Google ScholarDigital Library
- George E Dahl, Tara N Sainath, and Geoffrey E Hinton. 2013. Improving deep neural networks for LVCSR using rectified linear units and dropout. In 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 8609--8613.Google ScholarCross Ref
- Pralhad Deshpande, Anand Kashyap, Chul Sung, and Samir R Das. 2009. Predictive methods for improved vehicular WiFi access. In Proceedings of the 7th international conference on Mobile systems, applications, and services. ACM, 263--276.Google ScholarDigital Library
- Jakob Eriksson, Hari Balakrishnan, and Samuel Madden. 2008. Cabernet: vehicular content delivery using WiFi. In Proceedings of the 14th ACM international conference on Mobile computing and networking. ACM, 199--210.Google ScholarDigital Library
- Zhihan Fang, Boyang Fu, Zhou Qin, Fan Zhang, and Desheng Zhang. 2020. PrivateBus: Privacy Identification and Protection in Large-Scale Bus WiFi Systems. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 1 (2020), 1--23.Google ScholarDigital Library
- Zhihan Fang, Yu Yang, Shuai Wang, Boyang Fu, Zixing Song, Fan Zhang, and Desheng Zhang. 2019. MAC: Measuring the Impacts of Anomalies on Travel Time of Multiple Transportation Systems. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3, 2 (2019), 42.Google ScholarDigital Library
- Monica Ferrari. 2017. Benefits of free on-board Wi-Fi for public transport. https://www.tanaza.com/blog/benefits-of-free-on-board-wi-fi-for-public-transport/.Google Scholar
- Sina Finance. 2016. Do you have WiFi access in your city? http://finance.sina.com.cn/roll/2016-11-17/doc-ifxxwmws3013474.shtml.Google Scholar
- Anastasios Giannoulis, Marco Fiore, and Edward W Knightly. 2008. Supporting vehicular mobility in urban multi-hop wireless networks. In Proceedings of the 6th international conference on Mobile systems, applications, and services. ACM, 54--66.Google ScholarDigital Library
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024--1034.Google Scholar
- Bo Han, Pan Hui, and Aravind Srinivasan. 2011. Mobile data offloading in metropolitan area networks. ACM SIGMOBILE Mobile Computing and Communications Review 14, 4 (2011), 28--30.Google ScholarDigital Library
- Joshua Hare, Lance Hartung, and Suman Banerjee. 2012. Beyond deployments and testbeds: experiences with public usage on vehicular WiFi hotspots. In Proceedings of the 10th international conference on Mobile systems, applications, and services. ACM, 393--406.Google ScholarDigital Library
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web. International World Wide Web Conferences Steering Committee, 173--182.Google ScholarDigital Library
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.Google ScholarDigital Library
- Huashi. 2017. Huashi ViFi Introduction. http://www.visionchina.tv/news_nei.asp?pid=1438.Google Scholar
- Coby Joseph. 2014. How providing Wi-Fi can increase mass transit ridership. http://thecityfix.com/blog/wifi-increase-mass-transit-transport-ridership-bus-metro-coby-joseph/.Google Scholar
- Kyunghan Lee, Joohyun Lee, Yung Yi, Injong Rhee, and Song Chong. 2013. Mobile data offloading: How much can WiFi deliver? IEEE/ACM Transactions on Networking (ToN) 21, 2 (2013), 536--550.Google ScholarDigital Library
- Jialun Liu, Yifan Sun, Chuchu Han, Zhaopeng Dou, and Wenhui Li. 2020. Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2970--2979.Google ScholarCross Ref
- Siwei Liu, Iadh Ounis, Craig Macdonald, and Zaiqiao Meng. 2020. A Heterogeneous Graph Neural Model for Cold-Start Recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2029--2032.Google ScholarDigital Library
- Wenping Liu, Jiangchuan Liu, Hongbo Jiang, Bicheng Xu, Hongzhi Lin, Guoyin Jiang, and Jing Xing. 2016. WiLocator: WiFi-sensing based real-time bus tracking and arrival time prediction in urban environments. In Distributed Computing Systems (ICDCS), 2016 IEEE 36th International Conference on. IEEE, 529--538.Google ScholarCross Ref
- Ratul Mahajan, John Zahorjan, and Brian Zill. 2007. Understanding WiFi-based connectivity from moving vehicles. In Proceedings of the 7th ACM SIGCOMM conference on Internet measurement. ACM, 321--326.Google ScholarDigital Library
- Vinicius FS Mota, Daniel F Macedo, Yacine Ghamri-Doudane, and José Marcos S Nogueira. 2013. On the feasibility of WiFi offloading in urban areas: The Paris case study. In Wireless Days (WD), 2013 IFIP. IEEE, 1--6.Google ScholarCross Ref
- Seung-Taek Park and Wei Chu. 2009. Pairwise preference regression for cold-start recommendation. In Proceedings of the third ACM conference on Recommender systems. 21--28.Google ScholarDigital Library
- Michael J Pazzani and Daniel Billsus. 2007. Content-based recommendation systems. In The adaptive web. Springer, 325--341.Google ScholarDigital Library
- Bozhao Qi, Lei Kang, and Suman Banerjee. 2017. A vehicle-based edge computing platform for transit and human mobility analytics. In Proceedings of the Second ACM/IEEE Symposium on Edge Computing. ACM, 1.Google ScholarDigital Library
- Zhou Qin, Fang Cao, Yu Yang, Shuai Wang, Yunhuai Liu, Chang Tan, and Desheng Zhang. 2020. CellPred: A Behavior-aware Scheme for Cellular Data Usage Prediction. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 1 (2020), 1--24.Google ScholarDigital Library
- Zhou Qin, Zhihan Fang, Yunhuai Liu, Chang Tan, Wei Chang, and Desheng Zhang. 2018. EXIMIUS: A measurement framework for explicit and implicit urban traffic sensing. In Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems. 1--14.Google ScholarDigital Library
- Zhou Qin, Yikun Xian, and Desheng Zhang. 2019. A neural networks based caching scheme for mobile edge networks. In Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 408--409.Google ScholarDigital Library
- Antti Rasmus, Mathias Berglund, Mikko Honkala, Harri Valpola, and Tapani Raiko. 2015. Semi-supervised learning with ladder networks. In Advances in neural information processing systems. 3546--3554.Google Scholar
- John P Rula, James Newman, Fabián E Bustamante, Arash Molavi Kakhki, and David Choffnes. 2018. Mile high wifi: A first look at in-flight internet connectivity. In Proceedings of the 2018 World Wide Web Conference. International World Wide Web Conferences Steering Committee, 1449--1458.Google ScholarDigital Library
- Jiaxing Shen, Jiannong Cao, and Xuefeng Liu. 2019. BaG: Behavior-aware Group Detection in Crowded Urban Spaces using WiFi Probes. In The World Wide Web Conference. ACM, 1669--1678.Google ScholarDigital Library
- Rajkarn Singh, Marco Fiore, Mahesh Marina, Alberto Tarable, and Alessandro Nordio. 2019. Urban Vibes and Rural Charms: Analysis of Geographic Diversity in Mobile Service Usage at National Scale. In The World Wide Web Conference (WWW '19). Association for Computing Machinery, New York, NY, USA, 1724--1734. https://doi.org/10.1145/3308558.3313628Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.Google Scholar
- XinhuaNet. 2017. Beijing: The Free Bus WiFi is Gone. http://www.xinhuanet.com/2017-08/19/c_1121508023.htm.Google Scholar
- XinhuaNet. 2019. Reports of Cellular Data Rate from Major Cellular Operators. http://www.xinhuanet.com/fortune/2019-07/30/c_1124813473.htm.Google Scholar
- Desheng Zhang, Jun Huang, Ye Li, Fan Zhang, Chengzhong Xu, and Tian He. 2014. Exploring human mobility with multi-source data at extremely large metropolitan scales. In Proceedings of the 20th annual international conference on Mobile computing and networking. ACM, 201--212.Google ScholarDigital Library
- Junbo Zhang, Yu Zheng, and Dekang Qi. 2017. Deep spatio-temporal residual networks for citywide crowd flows prediction. In Thirty-First AAAI Conference on Artificial Intelligence.Google ScholarDigital Library
- Xiaolan Zhang, Jim Kurose, Brian Neil Levine, Don Towsley, and Honggang Zhang. 2007. Study of a bus-based disruption-tolerant network: mobility modeling and impact on routing. In Proceedings of the 13th annual ACM international conference on Mobile computing and networking. ACM, 195--206.Google ScholarDigital Library
- Xiaojin Zhu and Andrew B Goldberg. 2009. Introduction to semi-supervised learning. Synthesis lectures on artificial intelligence and machine learning 3, 1 (2009), 1--130.Google Scholar
Index Terms
- MIMU: Mobile WiFi Usage Inference by Mining Diverse User Behaviors
Recommendations
A seamless handover scheme in IPv6-based mobile networks
With the rapid development of wireless technologies, the need to support moving hosts of IPv6-based mobile networks in ubiquitous is growing. Various well-known approaches to optimising the handover latency have been proposed in the literature: MIPv6, ...
A distributed and secured architecture to enhance smooth handoffs in wide area wireless IP infrastructures
Currently, there exist disparate wireless networks, such as Bluetooth for personal areas, wireless LANs (WLANs) for local areas, GSM and UMTS for wide areas. These networks are designed for specific service needs and vary widely in terms of bandwidth, ...
Handoff and Route Optimization in Mobile Networks over IEEE 802.16e
To fulfill the need for on-the-move and uninterrupted internet connectivity in Mobile Networks, IETF NEMO working group was created to extend basic end-host mobility support in Mobile IPv6 MIPv6 protocol. NEMO Basic Support Protocol NEMO has been ...
Comments