Title:
METHOD AND APPARATUS FOR PERFORMING NETWORK OPTIMISATION USING A NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2021/045225
Kind Code:
A3
Abstract:
We apply the techniques of deep reinforcement learning (RL) to the problem of coverage and capacity optimisation (CCO) in wireless networks. This is motivated by the idea that the type of combinatorial optimisation problems encountered in wireless networks are somewhat analogous to strategy games, for which deep RL has already proven to be an effective approach. We use a computer simulation of a small wireless network to generate synthetic data to train a deep Q network (DQN), and evaluate the performance of the DQN with further simulations. We compare the performance of the DQN with a conventional model-based approach. The results show that the DQN achieves slightly better performance than the conventional method, without the need for an explicit model of the environment. The performance is shown to be further improved by using the DQN within a search algorithm.
Inventors:
ARNOTT ROBERT (GB)
SUAREZ ALBERTO (GB)
WELLS PATRICIA (GB)
SUAREZ ALBERTO (GB)
WELLS PATRICIA (GB)
Application Number:
PCT/JP2020/033703
Publication Date:
April 22, 2021
Filing Date:
August 27, 2020
Export Citation:
Assignee:
NEC CORP (JP)
International Classes:
H04W24/02; G06N3/02
Domestic Patent References:
| WO2019007388A1 | 2019-01-10 | |||
| WO2018149898A2 | 2018-08-23 |
Foreign References:
| US20190014487A1 | 2019-01-10 | |||
| US20190150006A1 | 2019-05-16 | |||
| CN109816099A | 2019-05-28 |
Other References:
ALESSIO ZAPPONE ET AL: "Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 5 February 2019 (2019-02-05), XP081026459
SUN R: "Supplementing Neural Reinforcement Learning with Symbolic Methods: Possibilities and Challenges", NEURAL NETWORKS, 1999. IJCNN '99. INTERNATIONAL JOINT CONFERENCE ON WASHINGTON, DC, USA 10-16 JULY 1999, PISCATAWAY, NJ, USA,IEEE, US, vol. 6, 10 July 1999 (1999-07-10), pages 4145 - 4150, XP010372588, ISBN: 978-0-7803-5529-3, DOI: 10.1109/IJCNN.1999.830828
SUN R: "Supplementing Neural Reinforcement Learning with Symbolic Methods: Possibilities and Challenges", NEURAL NETWORKS, 1999. IJCNN '99. INTERNATIONAL JOINT CONFERENCE ON WASHINGTON, DC, USA 10-16 JULY 1999, PISCATAWAY, NJ, USA,IEEE, US, vol. 6, 10 July 1999 (1999-07-10), pages 4145 - 4150, XP010372588, ISBN: 978-0-7803-5529-3, DOI: 10.1109/IJCNN.1999.830828
Attorney, Agent or Firm:
IEIRI Takeshi (JP)
Download PDF: