Application of Gradient Descent Optimization in Optimal Location Selection for Fire Stations in Newly Built Cities

Authors

  • Junjie Wu
  • Yiyang Zhang
  • Yuqing Zhuang
  • Zhuoer Huang
  • Ziyu Wang

DOI:

https://doi.org/10.61173/00csgd68

Keywords:

Gradient descent, Penalty method, Optimal location

Abstract

Fires have been one of the most common disasters threatening human lives. The location of a fire station is critical to firefighting and saving people as well as properties. This paper discusses the situation of finding an optimal location for a fire station in a newly built city. In addition, this paper aims to explore the applications of gradient descent optimization in practical problems. Two gradient descent algorithms are used to minimize the average response time for a fire call. The model for the average response time is built step by step. The first part considers the fire frequency distribution in the area only. The second part adds a weight to each box based on the population and wealth distribution. In the third part, the spread of fires is taken into consideration, and we use the penalty method to convert this constrained problem into an unconstrained one.

References

[1] Bottou, L. (2010). Large-Scale Machine Learning with Stochastic Gradient Descent. International Conference on Computational Statistics.

[2] Loshchilov, I., & Hutter, F. (2016). SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv: Learning

[3] Ighalo, J.O., Adeniyi, A.G., & Marques, G. (2020). Application of linear regression algorithm and stochastic gradient descent in a machine‐learning environment for predicting biomass higher heating value. Biofuels, 14.

[4] Meerschaert, M. M. (2013a). 3.2 Multivariable Optimization. In Mathematical modeling (pp. 66–67). Amsterdam: Elsevier.

[5] Liu, H., Hu, J., Li, Y., & Wen, Z. (2020). 7.1 The Penalty Methods. In Zui You Hua: Jian Mo, Suan Fa Yu Li Lun = optimization: Modeling, algorithm and Theory (pp. 297–304). Beijing: Gao deng jiao yu chu ban she.

Downloads

Published

2024-08-14

Issue

Vol. 2 No. 4 (2024): Volume 2, Issue 4

Section

Articles

License

Copyright (c) 2024 by the authors.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.