Enhanced Particle Swarm Optimization via Reinforcement Learning

Reinforcement Learning ◽

Normal Distribution ◽

Random Number ◽

Optimization Problems ◽

Numerical Test ◽

Particle Swarm ◽

Learning Method ◽

Swarm Optimization ◽

Abstract Particle swarm optimization (PSO) method is a well-known optimization algorithm, which shows good performance in solving different optimization problems. However, PSO usually suffers from slow convergence. In this paper, a reinforcement learning method is used to enhance PSO in convergence by replacing the uniformly distributed random number in the updating function by a random number generated from a well-selected normal distribution. The mean and variance of the normal distribution are estimated from the current state of each individual through a policy net. The historic behavior of the swarm group is learned to update the policy net and guide the selection of parameters of the normal distribution. The proposed algorithm is tested with numerical test functions and the results show that the convergence rate of PSO can be improved with the proposed Reinforcement Learning method (RL-PSO).

Parameter identification of the phenomenological model for magnetorheological fluid dampers using hierarchic enhanced particle swarm optimization

Journal of Mechanical Science and Technology ◽

10.1007/s12206-021-0202-3 ◽

2021 ◽

Vol 35 (3) ◽

pp. 875-887

Author(s):

Jin Guo ◽

Zhendong Li ◽

Mengxuan Zhang

Keyword(s):

Parameter Identification ◽

Phenomenological Model ◽

Particle Swarm ◽

Magnetorheological Fluid ◽

Swarm Optimization ◽

Fluid Dampers ◽

2012 IEEE International Conference on Advanced Communication Control and Computing Technologies (ICACCCT) ◽

Optimal location of FACTS devices using enhanced particle swarm optimization

10.1109/icaccct.2012.6320813 ◽

2012 ◽

Cited By ~ 3

Author(s):

K. Ravi ◽

M. Rajaram

Keyword(s):

Particle Swarm ◽

Optimal Location ◽

Swarm Optimization ◽

Facts Devices ◽

Optimum design of truss structures with frequency constraints by an enhanced particle swarm optimization method with gradient directions based on emigration philosophy

Engineering Optimization ◽

10.1080/0305215x.2021.2011259 ◽

2021 ◽

pp. 1-23

Author(s):

Farsad Salajegheh ◽

Eysa Salajegheh ◽

Saeed Shojaee

Keyword(s):

Optimum Design ◽

Particle Swarm ◽

Optimization Method ◽

Truss Structures ◽

Swarm Optimization ◽

Frequency Constraints ◽

Particle Swarm Optimization Method ◽

Advances in Intelligent Systems and Computing - Soft Computing for Problem Solving ◽

Enhanced Particle Swarm Optimization Technique for Interleaved Inverter Tied Shunt Active Power Filter

10.1007/978-981-13-1592-3_45 ◽

2018 ◽

pp. 571-583

Author(s):

Vijayakumar Gali ◽

Nitin Gupta ◽

R. A. Gupta

Keyword(s):

Optimization Technique ◽

Particle Swarm ◽

Active Power Filter ◽

Active Power ◽

Swarm Optimization ◽

Shunt Active Power Filter ◽

Power Filter ◽

Particle Swarm Optimization Technique ◽

Face Recognition Approach using an Enhanced Particle Swarm Optimization and Support Vector Machine

Journal of Engineering and Applied Sciences ◽

10.36478/jeasci.2019.2982.2987 ◽

2019 ◽

Vol 14 (9) ◽

pp. 2982-2987

Author(s):

Wasan Kadhim Saad ◽

Waheb A. Jabbar ◽

Ahmed Abdul Rudah Abbas

Keyword(s):

Support Vector Machine ◽

Face Recognition ◽

Particle Swarm ◽

Support Vector ◽

Swarm Optimization ◽

Enhanced Particle Swarm Optimization for Path Planning of Unmanned Aerial Vehicles

ECTI Transactions on Computer and Information Technology (ECTI-CIT) ◽

10.37936/ecti-cit.2020141.193991 ◽

2020 ◽

Vol 14 (1) ◽

pp. 67-78

Author(s):

Kai Yit Kok ◽

Parvathy Rajendran

Keyword(s):

Path Planning ◽

Unmanned Aerial Vehicles ◽

Particle Swarm ◽

Swarm Optimization ◽

Aerial Vehicles ◽

Trial And Error Method ◽

The Impact ◽

Enhanced Particle Swarm Optimization ◽

Error Method

This paper presents an enhanced particle swarm optimization (PSO) for the path planning of unmanned aerial vehicles (UAVs). An evolutionary algorithm such as PSO is costly because every application requires different parameter settings to maximize the performance of the analyzed parameters. People generally use the trial-and-error method or refer to the recommended setting from general problems. The former is time consuming, while the latter is usually not the optimum setting for various specific applications. Hence, this study focuses on analyzing the impact of input parameters on the PSO performance in UAV path planning using various complex terrain maps with adequate repetitions to solve the tuning issue. Results show that inertial weight parameter is insignificant, and a 1.4 acceleration coefficient is optimum for UAV path planning. In addition, the population size between 40 and 60 seems to be the optimum setting based on the case studies.