Intelligent autonomous street lighting system based on weather forecast using LSTM

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. (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This paper discusses an autonomous street lighting system with adaptive energy consumption based on weather forecast, which is completely powered by solar panels and can improve the energy efficiency of the street lighting system. By adjusting the brightness levels of lamps and forecasting energy generation by solar panels, the system shows stable and sustainable performance in simulations under random weather conditions for 1000 days.