Power optimization of 1:2 and 1:4 photonic crystal based optical power splitters/combiners using machine learning algorithms

Optical power splitters play a vital role in signal distribution, network expansion, and both balanced and unbalanced power splitting in cost-efficient fiber optic systems. Similarly, optical power combiners are essential for signal aggregation, upstream transmission, and balanced network design. In this article, we propose the design of two power splitters—3 dB and 6 dB Y-shaped configurations—that also function as power combiners using two-dimensional photonic crystal waveguides. The performance of these devices has been analyzed using the finite difference time domain (FDTD) algorithm, and their operational parameters have been optimized through the K-means clustering and Particle Swarm Optimization algorithms. As a result of this optimization, the devices achieve precise 3 dB and 6 dB power splitting across all output ports with an efficiency of 99 %. Their fast response time (0.4 and 0.5 picoseconds for 3 dB and 6 dB respectively), high power delivery efficiency, precise power splitting/combining capabilities, and Machine Learming (ML) – driven optimization make these splitters/combiners highly suitable for advanced fiber optic networks.