Application of a Differential Evolution Algorithm in the Design of Public Lighting Installations Maximizing Energy Efficiency

ABSTRACT This article presents a differential evolution (DE) algorithm that can be used to plan public lighting for streets, roadways, and freeways and maximize the energy efficiency of the installation. The algorithm was applied to a model based on new relationships between the energy efficiency of street lighting systems and geometric parameters such as street width, luminaire height, and distance between poles. These relationships were derived from the regression analysis of a large sample of outputs. The results of this algorithm consisted of the luminaire arrangement (one-sided, two-sided staggered, and two-sided coupled), luminaire height, luminaire type, and pole spacing for the most energy-efficient installation. The input of the algorithm was the lighting class or illuminance level, street width, as well as various other luminaire parameters. When these results were compared with those of DIALux, the performance of this new method was found to be extremely satisfactory. Furthermore, the constraints applied guaranteed compliance with the recommendations of the International Commission on Illumination.

[1]  Daniel Gómez-Lorente,et al.  A simple and accurate model for the design of public lighting with energy efficiency functions based on regression analysis , 2016 .

[2]  Daniel Gómez-Lorente,et al.  A simple method for designing efficient public lighting, based on new parameter relationships , 2013, Expert Syst. Appl..

[3]  Daniel Gómez-Lorente,et al.  A new methodology for calculating roadway lighting design based on a multi-objective evolutionary algorithm , 2013, Expert Syst. Appl..

[4]  Rainer Storn,et al.  Differential Evolution-A simple evolution strategy for fast optimization , 1997 .

[5]  Tim Kovacs,et al.  Genetics-Based Machine Learning , 2012, Handbook of Natural Computing.

[6]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[7]  Simone Gitto,et al.  Economic feasibility of energy efficiency improvements in street lighting systems in Rome , 2018 .

[8]  Francisco Herrera,et al.  Genetics-Based Machine Learning for Rule Induction: State of the Art, Taxonomy, and Comparative Study , 2010, IEEE Transactions on Evolutionary Computation.

[9]  Alan T. Murray,et al.  Spatial Analytics for Enhancing Street Light Coverage of Public Spaces , 2017, LEUKOS.

[10]  C. Fonseca,et al.  GENETIC ALGORITHMS FOR MULTI-OBJECTIVE OPTIMIZATION: FORMULATION, DISCUSSION, AND GENERALIZATION , 1993 .

[11]  Wout van Bommel.  Road Lighting: Fundamentals, Technology and Application , 2014 .

[12]  Consolación Gil,et al.  Evolutionary algorithms for the design of grid-connected PV-systems , 2012, Expert Syst. Appl..

[13]  Colin R. Reeves,et al.  Genetic Algorithms , 1993, Encyclopedia of Database Systems.

[14]  Adam Sędziwy,et al.  A New Approach to Street Lighting Design , 2016 .

[15]  Hannu Hyyppä,et al.  Tutorial: Road Lighting for Efficient and Safe Traffic Environments , 2017 .

[16]  Peter Boyce.  Lighting for Driving: Roads, Vehicles, Signs, and Signals , 2008 .

[17]  A. Peña-García,et al.  Impact of public lighting on pedestrians' perception of safety and well-being , 2015 .

[18]  Miomir Kostic,et al.  Recommendations for energy efficient and visually acceptable street lighting , 2009 .

[19]  Kalyanmoy Deb,et al.  Multi-objective Genetic Algorithms: Problem Difficulties and Construction of Test Problems , 1999, Evolutionary Computation.

[20]  V. Kirincic,et al.  Energy efficiency public lighting management in the cities , 2011 .