Recognition, analysis and study of swarm intelligence application of Physarum optimization algorithm in architecture and urbanism

The amazing behaviors observed in nature form attractive sources of inspiration for solving real-world problems. Swarm intelligence computations are very important among nature-inspired computations because they focus on the social behavior of centralized, self-organized systems. Swarm intelligence is inspired by the behavior of some animals or insects, such as ants, termites, birds, fish, and organisms. This is caused by sudden behaviors from local interactions between the particles themselves and forms intelligent behaviors at the group level. Robustness and resilience make swarm intelligence a successful design model for algorithms that deal with growing complex problems. Physarum Polycephalum is one of the organisms who’s intelligent, complex and social behavior of the particles that make up its food resources, and the construction of strong networks to achieve this goal, motivate the use of Physarum Polycephalum to solve challenging optimization problems in architecture and urbanism. The aim of this study is to try to further study and recognize the characteristics and efficiency of swarm intelligence algorithms, and to measure the ability of the Physarum optimization algorithm in dealing with the challenges posed in the problem area. In fact, this study aims to measure the ability and performance of the Physarum optimization algorithm in dealing with four parameters defined in the problem as an example of existing challenges, including faults, historic buildings, underpasses and bridges and intersections, to investigate in shaping the Tehran Urban Railway Network, in order to take an effective step in the field of functional and behavioral growth of the Physarum optimization algorithm. The research method in the present study is analytical-descriptive method and collecting materials based on library method and searching for some principles and rules governing natural phenomena, which have been studied with the help of software modeling, simulation and investigation. In the first part of this research, with the help of library studies, an attempt has been made to obtain a correct analysis and complete knowledge of swarm intelligence algorithms. It then evaluates the Physarum optimization algorithm as one of nature-inspired algorithms and collective intelligence in network formation. After examining the location of the mentioned parameters in relation to the existing network and Tehran metro stations, their boundaries are determined in the problem space to provide the conditions for formulation for the algorithm. In the next step, the Physarum optimization algorithm is introduced to formulate the problem space. As is clear (Map 2), this algorithm avoids obstacles and tries to find the best and most optimal way to reach the stations or defining points in the problem. Searching for problem space (Tehran city) by the algorithm continues to the extent that it makes sure to search the entire problem space and access all points. The findings and exit maps obtained from the Physarum pathfinding in the problem area indicate the correct identification of the defining barriers and the accurate and, of course, innovative formulation of the Tehran Urban Railway Network. Physarum's optimization algorithm has been able to accurately and without error perform network configuration with defined barriers.