Intelligent street lamp control system based on LSTM and Bayesian optimization

Peilong Lu; Yan Li; Zhengyi Ma; Han Qiao

doi:10.1117/12.2680557

16 June 2023 Intelligent street lamp control system based on LSTM and Bayesian optimization

Peilong Lu, Yan Li, Zhengyi Ma, Han Qiao

Proceedings Volume 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023); 1270203 (2023) https://doi.org/10.1117/12.2680557
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 2023, Changsha, China

Abstract

We have put forward an approach to control street lamps which is based on Long Short-Term Memory Network (LSTM for short) and Bayesian optimization. This approach imports meteorological conditions, natural light intensity, and other factors to train the network model in order to adaptively adjust the brightness of road network lighting equipment. The brightness of lighting equipment would transform according to the weather and natural light intensity conditions. Compared with MLP, XGBoost and LSTM, the model built by this method has the characteristics of small error and high precision.

Citation Download Citation

Peilong Lu, Yan Li, Zhengyi Ma, and Han Qiao "Intelligent street lamp control system based on LSTM and Bayesian optimization", Proc. SPIE 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 1270203 (16 June 2023); https://doi.org/10.1117/12.2680557

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