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.
1. Cheng, C. A., Wu, H. C. A cost-effective electronic lighting driver with high- power-factor and soft-switching for supplying a led street-light lamp // International Transactions on Electrical Energy Systems, 2021, Vol. 31, #3, pp. e12801.1‑e12801.16.
2. Liu, Y., Dong, Y., Zhu, T., Ma, D., Proppe, A., Chen, B., Zheng, C., Hou, Y., Lee, S., Sun, B. and Jung, E.H. Bright and stable light-emitting diodes based on perovskite quantum dots in perovskite matrix // Journal of the American Chemical Society, 2021, Vol. 143, #38, pp. 15606–15615.
3. Li, X., Chen, J., Liu, Z., Deng, Z., Huang, Q., Huang, J., Guo, W. (Ce, Gd): YAG-Al2O3 composite ceramics for high-brightness yellow light-emitting diode applications // Journal of the European Ceramic Society, 2020, Vol. 2, #3, pp. 1121–1131.
4. Hung, L.W., Anderson, S. J., Pipkin, A., Fristrup, K. Changes in night sky brightness after a countywide led retrofit // Journal of Environmental Management, 2021, Vol. 292, #12, pp. 112776.
5. Kotulski, L., Basiura, A., Wojnicki, I., Siuchta, S. Lighting system modernization as a source of green energy // Energies, 2021, Vol. 14, #10, pp. 2771.
6. Portnov, B. A., Saad, R., Trop, T. Interactive scenario-based assessment approach of urban street lighting and its application to estimating energy saving benefits // Energies, 2021, Vol. 14, #2, pp. 378.
7. Ernst, S., Kotulski, L., Lerch, T., Rad, M., Wojnicki, I. Application of reactive power compensation algorithm for large-scale street lighting // Journal of Computational Science, 2021, Vol. 51, pp. 101338.1–101338.8.
8. Tukymbekov, D., Saymbetov, A., Nurgaliyev, M., Kuttybay, N., Dosymbetova, G., Svanbayev, Y. Intelligent autonomous street lighting system based on weather forecast using lstm // Energy, 2021, Vol. 231, pp. 120902.1–120902.13.
9. Yoomak, S., Ngaopitakkul, A. Development of sustainable nanogrid road lighting systems // IEEE Transactions on Intelligent Transportation Systems, 2020, Vol. 22, #11, pp. 6682–6699.
10. Li, H., Wang, X., Zhang, K., Wu, S., Li, L. A neural network-based approach for the detection of heavy precipitation using GNSS observations and surface meteorological data // Journal of Atmospheric and Solar-Terrestrial Physics, 2021, Vol. 225, #1, pp. 105763.
11. Abbas, H. A. A new adaptive deep neural network controller based on sparse auto-encoder for the antilock bracking system systems subject to high constraints // Asian Journal of Control, 2021, Vol. 23, #5, pp. 2145–2156.
12. Kim, J. M., Ha, I.D. Deep learning-based residual control chart for count data // Quality Engineering, 2022, Vol. 34, #3, pp. 370–381.
13. Yu, Y., Zhang, M. Control chart recognition based on the parallel model of CNN and LSTM with GA optimization // Expert Systems with Applications, 2021, Vol. 185, pp. 115689.1–115689.14.
14. Gupta, S., Nguyen, D., Rana, S., Venkatesh, S., Kuttichira, D.P. Verification of integrity of deployed deep learning models using Bayesian optimization // Knowledge-Based Systems, 2022, Vol. 241, pp. 108238.1–108238.12.
15. Liu, Y., Li, D., Wan, S., Wang, F., Qi, L. A long short‐term memory‐based model for greenhouse climate prediction // International Journal of Intelligent Systems, 2021, Vol. 37, #1, pp. 135–151.
16. Hassanein, W. S., Ahmed, M. M., Mosaad, M. I., Abu-Siada, A. Estimation of transmission line parameters using voltage-current measurements and whale optimization algorithm // Energies, 2021, Vol. 14, #11, 3239.
17. Muller, M., Hagg, A., Strickstrock, R., Hülsmann, M., Asteroth, A., Kirschner, K. N., Reith, D. Determining lennard-jones parameters using multiscale target data through presampling- enhanced, surrogate-assisted global optimization // Journal of Chemical Information and Modeling, 2023, Vol. 63, #7, pp. 1872–1881.
18. Ai, M., Wang, P. Ma, W. Research and application of smart streetlamp based on fuzzy control method // Procedia Computer Science, 2021, Vol. 183, #4, pp. 341–348.
19. Yan, J. J., Wang, Z. Error Correction Method for Vector Sensor in Street Lamp Energy Saving Control System // Computer Simulation, 2021, Vol. 38, #1, pp. 256–260.
20. Niu, Z, J., Zhang, P., Cui, Y., Zhang, Jun., Z. PID control of an omnidirectional mobile platform based on an RBF neural network controller // Industrial Robot, 2022, Vol. 49, #1, pp. 65–75.

• Previous article
• Next article

• deep learning
• poor lighting
• automatic control of street lights
• long and short-term memory
• brightness (illuminance) prediction
• Kalman filtering
• PID controller