TY - JOUR
T1 - Federated Learning for Task and Resource Allocation in Wireless High-Altitude Balloon Networks
AU - Wang, Sihua
AU - Chen, Mingzhe
AU - Yin, Changchuan
AU - Saad, Walid
AU - Hong, Choong Seon
AU - Cui, Shuguang
AU - Poor, H. Vincent
N1 - Funding Information:
This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1800802; in part by the Natural Science Foundation of China under Grant 61629101 and Grant 61671086; in part by the Beijing Natural Science Foundation under Grant KZ201911232046; in part by the Beijing Laboratory Funding under Grant 2020BJLAB01; in part by the 111 Project under Grant B17007; in part by the MSIT (Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program (IITP-2021-2015- 0-00742) supervised by the IITP; in part by the Key Area Research and Development Program of Guangdong Province under Grant 2018B030338001; in part by the Shenzhen Outstanding Talents Training Fund; in part by the Guangdong Research Project under Grant 2017ZT07X152; in part by the U.S. National Science Foundation under Grant CCF-1908308; and in part by the National Science Foundation under Grant CNS-1814477.
Publisher Copyright:
© 2014 IEEE.
PY - 2021/12/15
Y1 - 2021/12/15
N2 - In this article, the problem of minimizing energy and time consumption for task computation and transmission in mobile-edge computing-enabled balloon networks is investigated. In the considered network, high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational capabilities to process the computational tasks offloaded from their associated users. Since the data size of each user's computational task varies over time, the HABs must dynamically adjust their resource allocation schemes to meet the users' needs. This problem is posed as an optimization problem, whose goal is to minimize the energy and time consumption for task computation and transmission by adjusting the user association, service sequence, and task allocation schemes. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables HABs to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the predictions of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real-city cellular traffic data show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 15.4% compared to a conventional centralized method.
AB - In this article, the problem of minimizing energy and time consumption for task computation and transmission in mobile-edge computing-enabled balloon networks is investigated. In the considered network, high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational capabilities to process the computational tasks offloaded from their associated users. Since the data size of each user's computational task varies over time, the HABs must dynamically adjust their resource allocation schemes to meet the users' needs. This problem is posed as an optimization problem, whose goal is to minimize the energy and time consumption for task computation and transmission by adjusting the user association, service sequence, and task allocation schemes. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables HABs to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the predictions of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real-city cellular traffic data show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 15.4% compared to a conventional centralized method.
KW - Federated learning (FL)
KW - Support vector machine (SVM)
KW - Task offloading
KW - User association
UR - http://www.scopus.com/inward/record.url?scp=85105866133&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105866133&partnerID=8YFLogxK
U2 - 10.1109/JIOT.2021.3080078
DO - 10.1109/JIOT.2021.3080078
M3 - Article
AN - SCOPUS:85105866133
SN - 2327-4662
VL - 8
SP - 17460
EP - 17475
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 24
ER -