TY - GEN
T1 - A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation
AU - Cheng, Jiaming
AU - Nguyen, Duong Thuy Anh
AU - Wang, Lele
AU - Nguyen, Duong Tung
AU - Bhargava, Vijay K.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Edge Computing (EC) offers a superior user experience by positioning cloud resources in close proximity to end users. The challenge of allocating edge resources efficiently while maximizing profit for the EC platform remains a sophisticated problem, especially with the added complexity of the online arrival of resource requests. To address this challenge, we propose to cast the problem as a multi-Armed bandit problem and develop two novel online pricing mechanisms, the Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm and the Min-Max Optimal algorithm, for heterogeneous edge resource allocation. These mechanisms operate in real-Time and do not require prior knowledge of demand distribution, which can be difficult to obtain in practice. The proposed posted pricing schemes allow users to select and pay for their preferred resources, with the platform dynamically adjusting resource prices based on observed historical data. Numerical results show the advantages of the proposed mechanisms compared to several benchmark schemes derived from traditional bandit algorithms, including the Epsilon-Greedy, basic UCB, and Thompson Sampling algorithms.
AB - Edge Computing (EC) offers a superior user experience by positioning cloud resources in close proximity to end users. The challenge of allocating edge resources efficiently while maximizing profit for the EC platform remains a sophisticated problem, especially with the added complexity of the online arrival of resource requests. To address this challenge, we propose to cast the problem as a multi-Armed bandit problem and develop two novel online pricing mechanisms, the Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm and the Min-Max Optimal algorithm, for heterogeneous edge resource allocation. These mechanisms operate in real-Time and do not require prior knowledge of demand distribution, which can be difficult to obtain in practice. The proposed posted pricing schemes allow users to select and pay for their preferred resources, with the platform dynamically adjusting resource prices based on observed historical data. Numerical results show the advantages of the proposed mechanisms compared to several benchmark schemes derived from traditional bandit algorithms, including the Epsilon-Greedy, basic UCB, and Thompson Sampling algorithms.
KW - Bandit learning
KW - Edge computing
KW - online pricing.
UR - http://www.scopus.com/inward/record.url?scp=85165634719&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85165634719&partnerID=8YFLogxK
U2 - 10.1109/NetSoft57336.2023.10175461
DO - 10.1109/NetSoft57336.2023.10175461
M3 - Conference contribution
AN - SCOPUS:85165634719
T3 - 2023 IEEE 9th International Conference on Network Softwarization: Boosting Future Networks through Advanced Softwarization, NetSoft 2023 - Proceedings
SP - 277
EP - 281
BT - 2023 IEEE 9th International Conference on Network Softwarization
A2 - Bernardos, Carlos J.
A2 - Martini, Barbara
A2 - Rojas, Elisa
A2 - Verdi, Fabio Luciano
A2 - Zhu, Zuqing
A2 - Oki, Eiji
A2 - Parzyjegla, Helge
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE International Conference on Network Softwarization, NetSoft 2023
Y2 - 19 June 2023 through 23 June 2023
ER -