PENERAPAN ALGORITMA GENETIKA DAN PARTICLE SWARM OPTIMIZATION UNTUK MENINGKATKAN PENGATURAN SISTEM CERDAS DALAM LINGKUNGAN SMART CITY
Abstract
In an increasingly complex city, smart technology emerges as the pivotal solution to confront challenges such as traffic congestion, security matters, efficient energy consumption, and optimal resource utilization within Smart Cities. This study aims to elevate the intelligent system management in the Smart City milieu by implementing Genetic Algorithms and Particle Swarm Optimization algorithms, both anticipated to tackle these issues adeptly. The data processing involves meticulous steps, encompassing data preprocessing to rectify outliers and fill in missing values. The prepared dataset is then segregated into training and testing sets. The training dataset serves to instruct the Genetic Algorithm and Particle Swarm Optimization models, while the testing data gauges the resulting model's performance. The experimental outcomes reveal that the amalgamation of Genetic Algorithm and Particle Swarm Optimization successfully attains an 88% accuracy rate. This outcome underscores an enhancement in the performance of the intelligent systems in the Smart City context. In conclusion, the integration of genetic algorithms aids in the pursuit of evolutionary solutions, mirroring natural evolutionary processes, whereas Particle Swarm Optimization leverages particle iterations to ascertain optimal solutions. Their symbiotic merger furnishes a robust approach to unearthing optimal solutions for multifarious Smart City quandaries. This research encourages further exploration into alternative optimization algorithms and larger, more representative datasets, thereby potentially yielding a more substantial contribution to the advancement of intelligent technology for the future Smart City.
Keywords: genetic algoritm, Particle swarm optimization, smart city, smart system
Downloads
References
[2] J. Belissent, "Getting Clever about Smart Cities: New Opportunities Require New Business Models." Forrester Research, Inc.: Cambridge, MA, USA, 2010.
[3] A. Hasibuan dan O. Krianto, "Smart City, Konsep Kota Cerdas Sebagai Alternatif Penyelesaian Masalah Perkotan Kabupaten/Kota, Di KotaKota Besar Provinsi Sumatera Utara." Buletin Utama Teknik, vol. 14(2), pp. 127-135, 2019.
[4] B. Smith, A. Johnson, dan D. Davis, "Particle Swarm Optimization for Smart City Street Lighting Management: Energy-Saving and Security Considerations." International Journal of Sustainable Technology, vol. 7(3), pp. 245-260, 2019.
[5] Q. Chen, L. Wu, dan G. Zhang, "Enhancing Energy Efficiency in Smart Grids using Grey Wolf Optimizer." International Journal of Electrical Power & Energy Systems, vol. 8(3), pp. 245-260, 2019.
[6] J. Kim, S. Park, dan H. Lee, "Optimization of Waste Management in Smart City using Ant Colony Optimization." Waste Technology Journal, vol. 10(4), pp. 456-470, 2020.
[7] A. S. Ibrahim dan A. Al-Sherbaz, "A survey of particle swarm optimization applications in smart cities." In 2018 IEEE 5th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), pp. 160-165, 2018.
[8] J. Wang dan S. Wang, "A multi-objective optimization algorithm based on genetic algorithm for smart city construction." Wireless Communications and Mobile Computing, vol. 2019, pp. 1-8.
[9] J. Jiang, J. Zhang, dan Y. Zheng, "Research on Smart City Development Based on Genetic Algorithm." In 2020 International Conference on Intelligent Medicine and Health (ICIMH), pp. 189-192, 2020.
[10] A. Sharma dan A. Sharma, "Particle swarm optimization (PSO) for economic load dispatch (ELD) of smart grids in smart cities." In 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp. 320-325, 2021.
[11] Dataset Smart City available link to https://kaggle.com/datasets
