Automatic Control Method for Street Lights in Unideal Lighting Environments Based on Deep Learning

Abstract

In response to the control problem and power consumption problem of outdoor illumination in imperfect lighting environments, a deep learning based automatic control method for street luminaires in imperfect lighting environments is studied and an automatic control model for street lights in an imperfect lighting environment based on deep learning is constructed. Use sensors to collect temperature, humidity, air pressure, and haze values that are significantly correlated with the brightness of ilumination in the same environment. Based on the collected data, use a deep learning short-term memory network to predict the current street illumination brightness, and use the Whale Optimization Algorithm to optimize network parameters. Using window filtering and one-dimensional Kalman filtering to filter the predicted data of illumination, the predicted street illuminance data after filtering is compared with the expected values. Based on this, a discretized PID controller (proportional–integral–derivative controller) is used to output the dimming value to achieve street lamp control. The experimental results show that this method can accurately predict the current characteristic of street lamps, and has good brightness control results in poor lighting environments, as well as better energy-saving performance.