Multi-fidelity Bayesian algorithm for antenna optimization

doi:10.23919/JSEE.2022.000137

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (6): 1119-1126.doi: 10.23919/JSEE.2022.000137

• ELECTRONICS TECHNOLOGY • Previous Articles

Multi-fidelity Bayesian algorithm for antenna optimization

Jianxing LI¹(), An YANG¹(), Chunming TIAN¹^,*(), Le YE²(), Badong CHEN³()

¹ School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China
² Institute of Microelectronics, Peking University, Beijing 100871, China
³ Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China

Received:2021-08-25 Online:2022-12-18 Published:2022-12-24
Contact: Chunming TIAN E-mail:jianxingli.china@xjtu.edu.cn;a.lina@stu.xjtu.edu.cn;tianchm@mail.xjtu.edu.cn;yele@pku.edu.cn;chenbd@mail.xjtu.edu.cn
About author:
LI Jianxing was born in 1987. He received his B.S. degree in information engineering, and M.S. and Ph.D. degrees in electromagnetic field and microwave techniques, all from Xi’an Jiaotong University, Xi’an, China, in 2008, 2011, and 2016, respectively. From 2014 to 2016, he was a visiting researcher with the Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA. He is currently an associate professor at Xi’an Jiaotong University. His research interests include microwave and mmWave circuits and antennas, wireless power transfer, AI-aided EM simulation, and multi-functional mmWave antennas. E-mail: jianxingli.china@xjtu.edu.cn

YANG An was born in 1988. He received his B.S. degree in information engineering, and M.S. degree in electronics and communications engineering, both from Xi’an Jiaotong University, Xi’an, China, in 2011 and 2021, respectively. His research interests include AI-adied antenna optimization, radio frequency circuits, and machine learning E-mail: a.lina@stu.xjtu.edu.cn

TIAN Chunming was born in 1974. He received his B.S. degree in applied physics, and M.S. and Ph.D. degrees in radio physics, all from Xidian University, Xi’an, China, in 1997, 2000, and 2003, respectively. He is currently a lecturer at Xi’an Jiaotong University. His research interests include antenna and radio wave propagation, electromagnetics (EM) numerical computation, and EM metamaterial. E-mail: tianchm@mail.xjtu.edu.cn

YE Le was born in 1983. He received his B.S. degree in physics from the Department of Physics, Nanjing University, Nanjing, China, in 2005, and Ph.D. degree in microelectronics from the Institute of Microelectronics, Peking University, Beijing, China, in 2010. he is currently an associate professor at Peking University. His research interests include analog and mixed-signal integrated circuit (IC) design, ultra-low power IC design, computing-in-memory AI chip design, and implanted IC and micro-system for medical applications. E-mail: yele@pku.edu.cn

CHEN Badong was born in 1974. He received his B.S. and M.S. degrees in control theory and engineering from Chongqing University, in 1997 and 2003, respectively, and Ph.D. degree in computer science and technology from Tsinghua University in 2008. He is currently a professor at Xi’an Jiaotong University. His research interests include signal processing, machine learning, artificial intelligence, neural engineering, and robotics. E-mail: chenbd@mail.xjtu.edu.cn
Supported by:
This work was supported by the National Key Research and Development Program of China (2019YFB1803205), the Key Research and Development Project of Shaanxi Province (2019GY-007), the National Natural Science Foundation of China (61801369), and the Fundamental Research Funds for the Central Universities (XZD012021012).

Abstract

Abstract:

In this work, the multi-fidelity (MF) simulation driven Bayesian optimization (BO) and its advanced form are proposed to optimize antennas. Firstly, the multiple objective targets and the constraints are fused into one comprehensive objective function, which facilitates an end-to-end way for optimization. Then, to increase the efficiency of surrogate construction, we propose the MF simulation-based BO (MFBO), of which the surrogate model using MF simulation is introduced based on the theory of multi-output Gaussian process. To further use the low-fidelity (LF) simulation data, the modified MFBO (M-MFBO) is subsequently proposed. By picking out the most potential points from the LF simulation data and re-simulating them in a high-fidelity (HF) way, the M-MFBO has a possibility to obtain a better result with negligible overhead compared to the MFBO. Finally, two antennas are used to testify the proposed algorithms. It shows that the HF simulation-based BO (HFBO) outperforms the traditional algorithms, the MFBO performs more effectively than the HFBO, and sometimes a superior optimization result can be achieved by reusing the LF simulation data.

Key words: antenna optimization, Bayesian optimization (BO), multiple-output Gaussian process, multi-fidelity (MF), low-fidelity (LF) simulation reuse

Jianxing LI, An YANG, Chunming TIAN, Le YE, Badong CHEN. Multi-fidelity Bayesian algorithm for antenna optimization[J]. Journal of Systems Engineering and Electronics, 2022, 33(6): 1119-1126.

Figures/Tables 9

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Table 1

Fig 6

Fig 7

Table 2

References 30

1	COSTA A, SILVA C, TORQUATO M, et al Parallel implementation of particle swarm optimization on FPGA. IEEE Trans. on Circuits and Systems II: Express Briefs, 2019, 66 (11): 1875- 1879. doi: 10.1109/TCSII.2019.2895343
2	DU W B, YING W, YAN G, et al Heterogeneous strategy particle swarm optimization. IEEE Trans. on Circuits and Systems II: Express Briefs, 2017, 64 (4): 467- 471. doi: 10.1109/TCSII.2016.2595597
3	SINGH P, ROSSI M, COUCKUYT I, et al Constrained multi-objective antenna design optimization using surrogates. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 2017, 30, E2248. doi: 10.1002/jnm.2248
4	LI H T, ZHOU J Z, KANG L, et al Optimization design of skin antenna based on Bayesian optimization. Proc. of the IEEE International Symposium on Microwave, Antenna, Propagation, and EMC Technologies, 2017, 78- 83.
5	WU Q, WANG H M, HONG W Multistage collaborative machine learning and its application to antenna modeling and optimization. IEEE Trans. on Antennas and Propagation, 2020, 68 (5): 3397- 3409. doi: 10.1109/TAP.2019.2963570
6	KOZIEL S, OGURTSOV S Multi-objective design of antennas using variable-fidelity simulations and surrogate models. IEEE Trans. on Antennas and Propagation, 2013, 61 (12): 5931- 5939. doi: 10.1109/TAP.2013.2283599
7	KOZIEL S, BEKASIEWICZ A, COUCKUYT I, et al Efficient multi-objective simulation-driven antenna design using co-Kriging. IEEE Trans. on Antennas and Propagation, 2014, 62 (11): 5900- 5905. doi: 10.1109/TAP.2014.2354673
8	KOZIEL S, OGURTSOV S, ZIENIUTYCZ W, et al Fast simulation-driven design of a planar UWB dipole antenna with an integrated balun. IEEE Antennas and Propagation Letters, 2015, 14, 366- 369.
9	KOZIEL S, BEKASIEWICZ A, ZIENIUTYCZ W Expedited EM-driven multiobjective antenna design in highly dimensional parameter spaces. IEEE Antennas and Wireless Propagation Letters, 2014, 13, 631- 634. doi: 10.1109/LAWP.2014.2313698
10	LIU B, ALIAKBARIAN H, MA Z K, et al An efficient method for antenna design optimization based on evolutionary computation and machine learning techniques. IEEE Trans. on Antennas and Propagation, 2014, 62 (1): 7- 18. doi: 10.1109/TAP.2013.2283605
11	JAIN S K, PATNAIK A, SINHA S N Design of custom-made stacked patch antennas: a machine learning approach. International Journal of Machine Learning and Cybernetics, 2013, 4, 189- 194. doi: 10.1007/s13042-012-0084-x
12	TAK J, KANTEMUR A, SHARMA Y, et al A 3-D-printed W-band slotted waveguide array antenna optimized using machine learning. IEEE Antennas and Wireless Propagation Letters, 2018, 17 (11): 2008- 2012. doi: 10.1109/LAWP.2018.2857807
13	LYU W L, XUE P, YANG F, et al An efficient Bayesian optimization approach for automated optimization of analog circuits. IEEE Trans. on Circuits and Systems I: Regular Papers, 2018, 65 (6): 1954- 1967. doi: 10.1109/TCSI.2017.2768826
14	COWEN-RIVERS A, LYU W L, WANG Z, et al. HEBO: heteroscedastic evolutionary Bayesian optimization. https://arXiv:2012.03826.
15	LIU J W, TUNGUZ B, TITERICZ G. GPU accelerated exhaustive search for optimal ensemble of black-box optimization algorithms. https://arXiv:2012.04201.
16	AWAD N H, SHALA G, DENG D, et al. Squirrel: a switching hyperparameter optimizer. https://arXiv:2012.08180.
17	SAZANOVICH M, NIKOLSKAYA A, BELOUSOV Y, et al. Solving black-box optimization challenge via learning search space partition for local Bayesian optimization. https://arXiv:2012.10335.
18	WU J J, CAO M L, SHAN L P, et al. Higher performance for AutoML: the benefit of various ensemble Bayesian optimization strategy. https://valohaichirpprod.blob.core.windows.net/papers/duxiaoman.pdf.
19	ALLEN J C, ARCEO D, HANSEN P Optimal lossy matching by Pareto fronts. IEEE Trans. on Circuits and Systems II: Express Briefs, 2008, 55 (6): 497- 501. doi: 10.1109/TCSII.2007.916721
20	LEDESMA S, RUIZ-PINALES J, CERDA-VILLAFANA G, et al A hybrid method to design wire antennas: design and optimization of antennas using artificial intelligence. IEEE Antennas and Propagation Magazine, 2015, 57 (4): 23- 31. doi: 10.1109/MAP.2015.2453912
21	ALVAREZ M A. Multiple-output Gaussian processes. http://gpss.cc/gpss17/slides/multipleOutputGPs.pdf.
22	ALVAREZ M A, ROSASCO L, LAWRENCE N D Kernels for vector-valued functions: a review. Foundations and Trends in Machine Learning, 2012, 4 (3): 195- 266. doi: 10.1561/2200000036
23	WANG B, CHEN T Gaussian process regression with multiple response variables. Chemometrics and Intelligent Laboratory Systems, 2015, 142, 159- 165. doi: 10.1016/j.chemolab.2015.01.016
24	MORENO-MUNOZ P, ARTES-RODRIGUEZ A, ALVAREZ M A Heterogeneous multi-output Gaussian process prediction. Proc. of the International Conference on Neural Information Processing Systems, 2018, 6711- 6720.
25	SWERSKY K, SNOEK J, ADAMS R P Multi-task Bayesian optimization. Advances in Neural Information Processing Systems, 2013, 2004- 2012.
26	RASMUSSEN C E, WILLIAMS C K I. Gaussian processes for machine learning. Cambridge, MA: MIT Press, 2006.
27	SHAHRIARI B, SWERSKY K, WANG Z, et al Taking the human out of the loop: a review of Bayesian optimization. Proceedings of the IEEE, 2016, 104 (1): 148- 175. doi: 10.1109/JPROC.2015.2494218
28	NOGUEIRA F. Bayesian optimization: open source constrained global optimization tool for Python. https://github.com/fmfn/BayesianOptimization.
29	GPy. A Gaussian process framework in python. http://github.com/SheffieldML/GPy.
30	GAFT. A genetic algorithm framework in python. http://github.com/SheffieldML/GPy.

Algorithm	Objective function value	Max S₁₁/dB	Min realized gain/dB	AR/dB
HFBO	4.3, 6.8, 6.3, 6.1, 6.8	−15.2, −13.6, −23.6, −13.6, −16.1	6.3, 6.3, 6.4, 6.3, 6.4	2.90, 2.62, 2.88, 2.69, 2.68
M-MFBO	6.2, 5.2, 5.8, 6.8, 6.4	−17.3, −11.0, −13.6, −17.2, −21.1	6.4, 6.2, 6.3, 6.4, 6.4	2.76, 2.72, 2.72, 2.69, 2.82

Algorithm	Objective function value	S₁₁/dB	Realized gain/dB
HFBO	21.69	−14.78	6.54
	21.90	−14.63	6.58
	21.56	−14.05	6.58
M-MFBO	21.66→22.30	−12.92	6.77
	21.53→21.53	−15.45	6.50
	21.02→21.69	−15.92	6.51

Multi-fidelity Bayesian algorithm for antenna optimization

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 9

References 30

Related Articles 0

Recommended Articles

Metrics

Comments