Dynamic gate assignment algorithm based on attentional convolution network

Zhiwei Xing; Qianqian Zhang; Zhaoxin Chen; Qian Luo

doi:10.1117/12.2645059

30 August 2022 Dynamic gate assignment algorithm based on attentional convolution network

Zhiwei Xing, Qianqian Zhang, Zhaoxin Chen, Qian Luo

Proceedings Volume 12309, International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2022); 123092V (2022) https://doi.org/10.1117/12.2645059
Event: International Conference on Advanced Manufacturing Technology and Manufacturing System (ICAMTMS 2022), 2022, Shijiazhuang, China

Abstract

Dynamic gate assignment process is a sequential decision process. The change of flights schedule will affect the flight gate allocation plan of flights in the same time period and subsequent periods. The use of airport gates is based on complex business logic rules. When writing flight gate allocation algorithms, business rules need to be transformed into parameterized mathematical models, in which a large number of parameters such as weights and thresholds need to be set by employees based on their subjective experience. The feasible solution of the model based on subjective empirical parameters is different from the actual decision of operators. As a result, the outputs obtained by the optimization algorithm cannot meet the actual needs of operators. In order to complete the dynamic assignment of gates in a sequential decision mode that close to the manual operation strategy of flight delay recovery, this paper takes single flight gate assignment as the assignment strategy and adopts a trust region policy optimization algorithm based on attention network to solve the problem, which is aimed at reducing the blindness of subjective setting of priority parameters in the algorithm and the complexity of the artificial adjustment parameters, so that the allocation results of the optimization algorithm can be more practical.

Citation Download Citation

Zhiwei Xing, Qianqian Zhang, Zhaoxin Chen, and Qian Luo "Dynamic gate assignment algorithm based on attentional convolution network", Proc. SPIE 12309, International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2022), 123092V (30 August 2022); https://doi.org/10.1117/12.2645059

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
11 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Mathematical modeling

Convolution

Feature extraction

Optimization (mathematics)

Performance modeling

Image processing

Show All Keywords

Keywords/Phrases

Search In:

Publication Years