Genetic algorithm enhanced by machine learning in dynamic aperture optimization

Abstract

With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given "elite" status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. The machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.

Adaptive Machine Learning for Robust Diagnostics and Control of Time-Varying Particle Accelerator Components and Beams

“…Recent ML applications for accelerators include ML-enhanced genetic optimization [5], utilizing surrogate models for simulation-based optimization studies and for estimating beam characteristics [6][7][8][9][10], Bayesian and GP approaches for accelerator tuning [11][12][13][14][15][16], various applications at the Large Hardon Collider including optics corrections and detecting faulty beam position monitors [17][18][19], powerful polynomial chaos expansion-based surrogate models for uncertainty quantification have been developed [20], and RL tools have been developed for online accelerator optimization [21][22][23][24][25]. One challenge faced by many ML approaches is the fact that as accelerators and their beams change with time, the ML models that were trained with previously collected data are no longer accurate because they are being applied to a different system than the one which they have been trained for.…”

Neural network-based multiobjective optimization algorithm for nonlinear beam dynamics

“…And, a combination of MOGA and MOPSO has more potential of avoiding local optima than using the MOGA or MOPSO alone [12]. Moreover, accelerator scientists are now exploring different machine learning enhanced MOGAs [14][15][16][17][18]. The basic consideration is that the dataset fX n ; Y n g continuously produced and accumulated by the MOGA can be used as the training data of machine learning, so as to reveal some hidden properties of the data which, in turn, helps to speed up the convergence and/or increase the diversity among solutions.…”

“…One approach is to combine MOGA with data clustering (e.g., [14,15]), namely, using K-means clustering for each generation to find the "elite" variable range covered by the individuals that have high objective performance. The new competitive offspring individuals are then generated within the elite variable range and used to replace the original data in the population, which can result in faster convergence.…”

Parametrization, characterization, and optimization of double-bend achromat cell

“…These codes have been successfully used to optimize the design of many light sources [15][16][17]. More recently, utilizing enormous computing power, the multiobjective genetic algorithm [18,19] was introduced and enhanced by machine learning [20] to directly optimize the dynamic aperture. Despite these practical improvements, the relationship between the driving terms and dynamic aperture is still elusive.…”