Intelligent autonomous street lighting system based on weather forecast using LSTM

Didar Tukymbekov, Ahmet Saymbetov, Madiyar Nurgaliyev, Nurzhigit Kuttybay, Gulbakhar Dosymbetova and Yeldos Svanbayev

Energy, 2021, vol. 231, issue C

Abstract: Existing traditional street lighting systems are characterized by a high level of energy consumption compared to automated intelligent systems that offer different operating modes depending on traffic and power system load. The most promising energy sources systems are hybrid installations that switch the load to the grid in adverse weather conditions. Such systems may increase the energy efficiency of the street lighting system, but they are not completely autonomous. In this case, the most important problem is to provide the street lighting system with energy in adverse weather conditions. In this paper, an autonomous street lighting system with adaptive energy consumption based on weather forecast was shown. The proposed street lighting system is completely independent of traditional power sources and is completely powered by solar panels. The main energy consumers of a street lighting system are lamps. The consumption of lamps can be changed to the minimum brightness level required by outdoor lighting standards. Forecasts of energy generation by solar panels can be obtained using LSTM. It is based on weather and solar radiation forecasts data for the coming days. The brightness levels of lamps are calculated and changed using the methods proposed in this paper. The probability of reaching the critical level of batteries does not exceed 0.10% and fluctuates around 0.05% most of the time when simulating for 1000 days under random weather conditions. Simulation of energy consumption by the street lighting system using the proposed method shows stable and sustainable performance in Almaty, Kazakhstan. The obtained results in this work can be used for designing autonomous street lighting and outdoor lighting systems.

Keywords: Intelligent street lighting system; Neural networks; Solar energy; Prediction of PV system output power; Energy efficiency; Wireless sensor networks (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544221011506
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:231:y:2021:i:c:s0360544221011506

DOI: 10.1016/j.energy.2021.120902

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().