The dataset, provided by Shanghai Telecom, contains more than 7.2 million records of accessing the Interent through 3,233 base stations from 9,481 mobile phones for six months. For example, the following figure shows the distribution of base stations. Each node denotes a base station in Shanghai, China. This dataset could help researchers to evaluate their solution in mobile edge computing topic such as edge server placement, service migration, service recommendation, etc.
As shown in the following table, the Telecom dataset shows 6 parameters such as Month, Data, Start Time, End Time, Base Station Location, Mobile Phone ID. The trajectory of users can be found by the dataset.
Telecom Parameters
ID
Parameter Name
Description
1
Month
The month when one record happens
2
Date
The date when one record happens
3
Start Time
The time when a record starts
4
End Time
The time when a record ends
5
Base Station Location
The longitude and latitude of the base station where the mobile phones access the Interent
6
User ID
Mobile phone
The following figure shows when and where the user accessed the Internet by mobile phone.
The telecom dataset is available free of charge for educational and non-commercial purposes. The Telecom data should be used in any scientific or educational study/research. Redistribution of this data to any other third party is not permited.In exchange, we kindly request that you make available to us the results of running the telecom dataset. You must cite the following papers when using this Telecom dataset.
[1] Yuanzhe Li, Ao Zhou, Xiao Ma, Shangguang Wang, Profit-aware Edge Server Placement, IEEE Internet of Things Journal, 2022, vol.9, no.1 ,pp.55-67 [PDF] [Sourcecode]
[2] Y. Guo, S. Wang, A. Zhou, J. Xu, J. Yuan, C. Hsu. User Allocation‐aware Edge Cloud Placement in Mobile Edge Computing, Software: Practice and Experience, vol. 50, no. 5, pp. 489-502, 2020.[PDF] [Sourcecode]
[3] S. Wang, Y. Guo, N. Zhang, P. Yang, A. Zhou, X. Shen. Delay-aware Microservice Coordination in Mobile Edge Computing: A Reinforcement Learning Approach, IEEE Transactions on Mobile Computing, vol. 20, no.3, pp.939-953, 2021. [PDF]
Your comments and suggestions are welcome. Please send your comments by email: sgwangATbuptDOTeduDOTcn. We will publish more detailed Telecom dataset from China 20+ Provinces later. The data attribute includes Phone Nunber，Location Area Code，CI，APN，IMEI，SGSN IP，GGSN IP，Start Time，End Time，Duration，Uplink Traffic, Downlink Traffic, RATType, Source IP, Source Port, Destination IP, Destination Port, Status Code, URL, User Agent, Content-Type, Date.
