TY - GEN
T1 - Optimizing Rescheduling Intervals Through Using Multi-Armed Bandit Algorithms
AU - Lin, Fuhua
AU - Ali Akber Dewan, M.
AU - Nguyen, Matthew
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7
Y1 - 2018/7
N2 - Well scheduling in oil and gas production in a virtual enterprise is a distributed and online scheduling problem. For such a scheduling problem, planned schedules are subject to unexpected disruptions or under-or over-estimated completion times. To reduce the impact of these uncertain events, schedule revision is necessary to keep the current schedule feasible and optimal in productivity. However, even though frequent schedule revisions may maximize the number of well tasks, it can also increase machine setup and transportation costs. This indicates the necessity of designing a systematic strategy for determining when to carry out schedule revisions. There is no trivial solution to this problem. In this research, we propose an approach to rescheduling interval determination through using a reinforcement learning-multiarmed bandit model. A set of experiments is conducted in a multiagent simulation environment. The results of the experiment demonstrate the effectiveness of the proposed approach in detecting optimal rescheduling intervals.
AB - Well scheduling in oil and gas production in a virtual enterprise is a distributed and online scheduling problem. For such a scheduling problem, planned schedules are subject to unexpected disruptions or under-or over-estimated completion times. To reduce the impact of these uncertain events, schedule revision is necessary to keep the current schedule feasible and optimal in productivity. However, even though frequent schedule revisions may maximize the number of well tasks, it can also increase machine setup and transportation costs. This indicates the necessity of designing a systematic strategy for determining when to carry out schedule revisions. There is no trivial solution to this problem. In this research, we propose an approach to rescheduling interval determination through using a reinforcement learning-multiarmed bandit model. A set of experiments is conducted in a multiagent simulation environment. The results of the experiment demonstrate the effectiveness of the proposed approach in detecting optimal rescheduling intervals.
KW - multi-Armed bandit problem
KW - online machine learning
KW - online scheduling
UR - http://www.scopus.com/inward/record.url?scp=85067850010&partnerID=8YFLogxK
U2 - 10.1109/Cybermatics_2018.2018.00148
DO - 10.1109/Cybermatics_2018.2018.00148
M3 - Published Conference contribution
AN - SCOPUS:85067850010
T3 - Proceedings - IEEE 2018 International Congress on Cybermatics: 2018 IEEE Conferences on Internet of Things, Green Computing and Communications, Cyber, Physical and Social Computing, Smart Data, Blockchain, Computer and Information Technology, iThings/GreenCom/CPSCom/SmartData/Blockchain/CIT 2018
SP - 746
EP - 753
BT - Proceedings - IEEE 2018 International Congress on Cybermatics
T2 - 11th IEEE International Congress on Conferences on Internet of Things, 14th IEEE International Conference on Green Computing and Communications, 11th IEEE International Conference on Cyber, Physical and Social Computing, 4th IEEE International Conference on Smart Data, 1st IEEE International Conference on Blockchain and 18th IEEE International Conference on Computer and Information Technology, iThings/GreenCom/CPSCom/SmartData/Blockchain/CIT 2018
Y2 - 30 July 2018 through 3 August 2018
ER -