NSGA-II-TLBO algorithm for optimizing campus environment art design scheme
Abstract The study proposes an improved algorithm based on non-dominated sorting genetic algorithm II (NSGA-II) and teaching learning-based optimization algorithm for optimizing campus layout configurations. By introducing teaching learning-based optimization algorithm and combining it with Levy fli...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-08-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-07509-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343154938970112 |
|---|---|
| author | Huicong Wang Meng Zhang Hongwei Yang |
| author_facet | Huicong Wang Meng Zhang Hongwei Yang |
| author_sort | Huicong Wang |
| collection | DOAJ |
| description | Abstract The study proposes an improved algorithm based on non-dominated sorting genetic algorithm II (NSGA-II) and teaching learning-based optimization algorithm for optimizing campus layout configurations. By introducing teaching learning-based optimization algorithm and combining it with Levy flight strategy, the improved algorithm shows significant advantages in multi-objective optimization performance. The Genetic Learning Test (GLT) data set is used to evaluate the efficiency and effectiveness of genetic algorithms in learning and optimization tasks. By designing test problems with different levels of difficulty, it provides a measure of the learning ability and adaptability of the algorithm. The experiment outcomes indicate that in the GLT dataset, the reverse generation distance of the improved algorithm is significantly lower than other compared algorithms. For example, in the GLT2 test, its reverse generation distance is only 0.020, far lower than other algorithms. Meanwhile, its super volume also performs well in the LZ dataset, with a super volume of 0.75 in the LZ2 test, outperforming other algorithms. In practical applications, taking a school in Guangdong Province as an example, the improved algorithm achieves significant results in optimizing campus environment design. In the optimized plan, the annual average thermal radiation optimization of Plan 3 reaches 60.4 Kw h/m2, the optimization range of the hottest week average general thermal climate index is 0.4 ℃, and the optimization range of sky opening width is 1.8%. The above results indicate that the improved algorithm can validly balance the functional, aesthetic, and sustainable goals in campus environment design, and optimize the artistic design scheme of campus environment. The study aims to improve the thermal comfort and overall environmental quality of the campus by optimizing key design elements such as the orientation of campus buildings and the layout of building clusters, creating a healthier and more comfortable learning and working environment for teachers and students. |
| format | Article |
| id | doaj-art-3a4162b2be28434b92ebd4eac166aa7c |
| institution | Kabale University |
| issn | 3004-9261 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Applied Sciences |
| spelling | doaj-art-3a4162b2be28434b92ebd4eac166aa7c2025-08-20T03:43:10ZengSpringerDiscover Applied Sciences3004-92612025-08-017812010.1007/s42452-025-07509-wNSGA-II-TLBO algorithm for optimizing campus environment art design schemeHuicong Wang0Meng Zhang1Hongwei Yang2School of Culture, Tourism and International Education, Henan Polytechnic InstituteSchool of Culture, Tourism and International Education, Henan Polytechnic InstituteSchool of Marxism, Central University of Finance and EconomicsAbstract The study proposes an improved algorithm based on non-dominated sorting genetic algorithm II (NSGA-II) and teaching learning-based optimization algorithm for optimizing campus layout configurations. By introducing teaching learning-based optimization algorithm and combining it with Levy flight strategy, the improved algorithm shows significant advantages in multi-objective optimization performance. The Genetic Learning Test (GLT) data set is used to evaluate the efficiency and effectiveness of genetic algorithms in learning and optimization tasks. By designing test problems with different levels of difficulty, it provides a measure of the learning ability and adaptability of the algorithm. The experiment outcomes indicate that in the GLT dataset, the reverse generation distance of the improved algorithm is significantly lower than other compared algorithms. For example, in the GLT2 test, its reverse generation distance is only 0.020, far lower than other algorithms. Meanwhile, its super volume also performs well in the LZ dataset, with a super volume of 0.75 in the LZ2 test, outperforming other algorithms. In practical applications, taking a school in Guangdong Province as an example, the improved algorithm achieves significant results in optimizing campus environment design. In the optimized plan, the annual average thermal radiation optimization of Plan 3 reaches 60.4 Kw h/m2, the optimization range of the hottest week average general thermal climate index is 0.4 ℃, and the optimization range of sky opening width is 1.8%. The above results indicate that the improved algorithm can validly balance the functional, aesthetic, and sustainable goals in campus environment design, and optimize the artistic design scheme of campus environment. The study aims to improve the thermal comfort and overall environmental quality of the campus by optimizing key design elements such as the orientation of campus buildings and the layout of building clusters, creating a healthier and more comfortable learning and working environment for teachers and students.https://doi.org/10.1007/s42452-025-07509-wCampus environmentNSGA-IITeaching learning-based optimizationLevy flightMulti-objective optimization |
| spellingShingle | Huicong Wang Meng Zhang Hongwei Yang NSGA-II-TLBO algorithm for optimizing campus environment art design scheme Discover Applied Sciences Campus environment NSGA-II Teaching learning-based optimization Levy flight Multi-objective optimization |
| title | NSGA-II-TLBO algorithm for optimizing campus environment art design scheme |
| title_full | NSGA-II-TLBO algorithm for optimizing campus environment art design scheme |
| title_fullStr | NSGA-II-TLBO algorithm for optimizing campus environment art design scheme |
| title_full_unstemmed | NSGA-II-TLBO algorithm for optimizing campus environment art design scheme |
| title_short | NSGA-II-TLBO algorithm for optimizing campus environment art design scheme |
| title_sort | nsga ii tlbo algorithm for optimizing campus environment art design scheme |
| topic | Campus environment NSGA-II Teaching learning-based optimization Levy flight Multi-objective optimization |
| url | https://doi.org/10.1007/s42452-025-07509-w |
| work_keys_str_mv | AT huicongwang nsgaiitlboalgorithmforoptimizingcampusenvironmentartdesignscheme AT mengzhang nsgaiitlboalgorithmforoptimizingcampusenvironmentartdesignscheme AT hongweiyang nsgaiitlboalgorithmforoptimizingcampusenvironmentartdesignscheme |