Energy Efficient Street Lighting for Urban Development: A Hybrid ANOVA - GA Framework

Year 2026, Volume: 10 Issue: 2 , 351 - 363 , 01.05.2026

Kazi Amrin Kabir , Sudip Mandal , Parag Kumar Guha Thakurta

https://doi.org/10.31127/tuje.1762113

https://izlik.org/JA27GH47YR

Abstract

An efficient urban development requires a reduction of carbon footprint through innovative and sustainable infrastructure planning. Traditional optimization techniques often suffer from slow convergence and limited energy savings as a result of their extensive parameter tuning without statistical filtering. To address this challenge, an energy-efficient street lighting framework is proposed here by integrating the concept of Analysis of Variance (ANOVA) and Genetic Algorithm (GA) named as ANOVA-GA. Initially, multiple lighting parameters such as pole height, boom angle, boom length, light type, and voltage are evaluated in the standard lighting software Dialux to obtain a dataset that identifies their impact on energy use and the overlap of illumination. These design parameters are statistically analyzed using Type II ANOVA to determine their significance in reducing energy consumption. Only the most impactful parameters evaluated earlier are retained in the GA for optimization. The GA then searches for an optimal combination of these parameters that minimizes energy consumption while meeting lighting standards. By embedding ANOVA, the method reduces the dimensionality of the solution space, and which in turn accelerates convergence. The proposed framework achieves an annual energy consumption of 182 kWh/year, outperforming traditional single and hybrid framework. It reduces the number of poles required per kilometer by 25%. Furthermore, the proposed hybrid optimization framework is spatially validated and utilized by the concept of geographical information system (GIS), where a reduced number of pole counts and wider spacing are achieved without compromising illumination quality. The integration of simulation, optimization, and geospatial planning makes the proposed work highly applicable to obtain significant energy savings for sustainable urban lighting in smart city planning.

Keywords

Analysis of Variance (ANOVA) , Genetic Algorithm (GA) , Geographical Information System (GIS) , Streetlight , Energy consumption.

Ethical Statement

The authors declare no conflicts of interest.

Supporting Institution

National Institute of Technology, Durgapur

Thanks

National Institute of Technology, Durgapur

References

• 1. Sahak, A. S., & Karsli, F. (2024). A new approach for the assessment of urban eco-environmental quality based on remote sensing: A case study of Herat city, Afghanistan. Journal of Spatial Science, 69(3), 937–962.
• 2. Sancino, A., Stafford, M., Braga, A., & others. (2022). What can city leaders do for climate change? Insights from the C40 Cities Climate Leadership Group network. Regional Studies, 56(7), 1224–1233.
• 3. Dey, R., & Thakurta, P. K. G. (2024). Energy efficient routing for improving lifetime in MWSN: A clustering approach. Turkish Journal of Engineering, 8(4), 666–676. https://doi.org/10.31127/tuje.1481281.
• 4. Jägerbrand, A. K. (2015). New framework of sustainable indicators for outdoor LED (light emitting diodes) lighting and SSL (solid state lighting). Sustainability, 7(1), 1028–1063.
• 5. Belloni, E., Massaccesi, A., Moscatiello, C., & others. (2024). Implementation of a new solar-powered street lighting system: Optimization and technical-economic analysis using artificial intelligence. IEEE Access.
• 6. Umamaheswari, S. (2020). Smart street lighting in smart cities: A transition from traditional street lighting. In Security and privacy applications for smart city development (pp. 117–133). Springer.
• 7. Pardo-Bosch, F., Pujadas, P., Morton, C., & others. (2021). Sustainable deployment of an electric vehicle public charging infrastructure network from a city business model perspective. Sustainable Cities and Society, 71, 102957.
• 8. Rabaza, O., Molero-Mesa, E., Aznar-Dols, F., & others. (2018). Experimental study of the levels of street lighting using aerial imagery and energy efficiency calculation. Sustainability, 10(12), 4365.
• 9. Kabir, K. A., Sikdar, P. L., & GuhaThakurta, P. K. (2022). Energy efficient street lighting: A GIS approach. In Proceedings of the 6th International Conference on Advance Computing and Intelligent Engineering: ICACIE 2021 (pp. 583–593). Springer.
• 10. Pardo-Bosch, F., Blanco, A., Sesé, E., & others. (2022). Sustainable strategy for the implementation of energy efficient smart public lighting in urban areas: Case study in San Sebastian. Sustainable Cities and Society, 76, 103454.
• 11. Dizon, E., & Pranggono, B. (2022). Smart streetlights in smart city: A case study of Sheffield. Journal of Ambient Intelligence and Humanized Computing, 1–16.
• 12. Uysal, M. P. (2025). A formal and integrated approach to engineering machine learning processes: A method base for project management. Turkish Journal of Engineering, 9(1), 152–178. https://doi.org/10.31127/tuje.1527734.
• 13. Fombuwing, B., & TekbıyıkErsoy, N. (2024). Modeling electricity generation and consumption in Cameroon. Turkish Journal of Engineering, 8(4), 593–602. https://doi.org/10.31127/tuje.1440376.
• 14. Öz, İ. (2024). Minimizing satellite residence time in the GEO region through elevated eccentricity method. Turkish Journal of Engineering, 8(3), 416–426. https://doi.org/10.31127/tuje.1395250.
• 15. Patra, B., & Kisku, D. R. (2025). Exploring Bengali image descriptions through the combination of diverse CNN architectures and transformer decoders. Turkish Journal of Engineering, 9(1), 64–78. https://doi.org/10.31127/tuje.1507442.
• 16. Sikdar, P. L., Kar, S., & Thakurta, P. K. G. (2024). ANNEGA: An artificial neural network embedded genetic algorithm approach for energy efficient street lighting. Evolutionary Intelligence, 17(5), 4029–4045.
• 17. Sikdar, P. L., Kar, S., & Thakurta, P. K. G. (2022). Multiobjective energy efficient street lighting framework: A data analysis approach. Applied Intelligence, 52(15), 17237–17263.
• 18. Pizzuti, S., Moretti, F., Annunziato, M., & others. (2013). Advanced street lighting control through neural network ensembling. In The Second International Conference on Smart Systems, Devices and Technologies (pp. 81). IARIA, XPS Press.
• 19. Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197.
• 20. Viswanathan, S., &Ravichandran, K. S. (2024). Gain-based green ant colony optimization for 3D path planning on remote sensing images. Spectrum of Operational Research, 2(1), 92–113.
• 21. Jafari-Nikpay, M., Arabzade-Nosratabad, Z., &Momayezi, F. (2025). Optimizing smart home energy management with branch and bound method: A novel model for daily and weekly scheduling of smart appliances. Spectrum of Operational Research, 3(1), 252–274.
• 22. Sahoo, S., et al. (2025). A review of multi-criteria decision-making (MCDM) applications to solve energy management problems from 2010–2025: Current state and future research. Spectrum of Decision Making and Applications, 2(1), 219–241.
• 23. Arabahmadi, R., Mohammadi, M., Samizadeh, M., Rabbani, M., &Gharibi, K. (2023). Facility location optimization for technical inspection centers using multi-objective mathematical modeling considering uncertainty. Journal of Soft Computing and Decision Analytics, 1(1), 181–208.
• 24. Kabir, K. A., GuhaThakurta, P. K., & Kar, S. (2025). An intelligent geographic information system-based framework for energy efficient street lighting. Signal, Image and Video Processing, 19(4), 305.
• 25. Asif, M., Shams, S., Hussain, S., & others. (2022). Adaptive control of streetlights using deep learning for the optimization of energy consumption during late hours. Energies, 15(17), 6337.
• 26. Sutopo, W., Mardikaningsih, I. S., Zakaria, R., & others. (2020). A model to improve the implementation standards of street lighting based on solar energy: A case study. Energies, 13(3), 630.
• 27. Falchi, F., Cinzano, P., Duriscoe, D., & others. (2016). The new world atlas of artificial night sky brightness. Science Advances, 2(6), e1600377.
• 28. Gasparovsky, D., Janiga, P., & Raditschova, J. (2021). Typical values of energy performance indicators in road lighting. Advances in Electrical and Electronic Engineering, 19(2).
• 29. Gagliardi, G., Lupia, M., Cario, G., & others. (2020). Advanced adaptive street lighting systems for smart cities. Smart Cities, 3(4), 1495–1512.
• 30. Tukymbekov, D., Saymbetov, A., Nurgaliyev, M., & others. (2021). Intelligent autonomous street lighting system based on weather forecast using LSTM. Energy, 231, 120902.
• 31. Mohandas, P., Dhanaraj, J. S. A., & Gao, X. Z. (2019). Artificial neural network based smart and energy efficient street lighting system: A case study for residential area in Hosur. Sustainable Cities and Society, 48, 101499.