ICALEPCS2019 - List of Authors (Gaio, G.)

Paper	Title	Page
MOPHA044	Development of Ethernet Based Real-Time Applications in Linux Using DPDK	297
	G. Gaio, G. Scalamera Elettra-Sincrotrone Trieste S.C.p.A., Basovizza, Italy
	In the last decade Ethernet has become the most popular way to interface hardware devices and instruments to the control system. Lower cost per connection, reuse of existing network infrastructures, very high data rates, good noise rejection over long cables and finally an easier maintainability of the software in the long term are the main reasons of its success. In addition, the need of low latency systems of the High Frequency Trading community has boosted the development of new strategies, such as CPU isolation, to run real-time applications in plain Linux with a determinism of the order of microseconds. DPDK (Data Plane Development Kit), an open source software solution mainly sponsored by Intel, addresses the request of high determinism over Ethernet by bypassing the network stack of Linux and providing a more friendly framework to develop tasks which are even able to saturate a 100 Gbit connection. Benchmarks regarding the real-time performance and preliminary results of employing DPDK in the acquisition of beam position monitors for the fast orbit feedback of the Elettra storage ring will be presented.
	Poster MOPHA044 [2.626 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA044
About •	paper received ※ 29 September 2019 paper accepted ※ 08 October 2019 issue date ※ 30 August 2020
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WEPHA021	Free-Electron Laser Optimization with Reinforcement Learning	1122
	N. Bruchon, G. Fenu, F.A. Pellegrino, E. Salvato University of Trieste, Trieste, Italy G. Gaio, M. Lonza Elettra-Sincrotrone Trieste S.C.p.A., Basovizza, Italy
	Reinforcement Learning (RL) is one of the most promising techniques in Machine Learning because of its modest computational requirements with respect to other algorithms. RL uses an agent that takes actions within its environment to maximize a reward related to the goal it is designed to achieve. We have recently used RL as a model-free approach to improve the performance of the FERMI Free Electron Laser. A number of machine parameters are adjusted to find the optimum FEL output in terms of intensity and spectral quality. In particular we focus on the problem of the alignment of the seed laser with the electron beam, initially using a simplified model and then applying the developed algorithm on the real machine. This paper reports the results obtained and discusses pros and cons of this approach with plans for future applications.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-WEPHA021
About •	paper received ※ 30 September 2019 paper accepted ※ 09 October 2019 issue date ※ 30 August 2020
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Development of Ethernet Based Real-Time Applications in Linux Using DPDK

297

G. Gaio, G. Scalamera
Elettra-Sincrotrone Trieste S.C.p.A., Basovizza, Italy

In the last decade Ethernet has become the most popular way to interface hardware devices and instruments to the control system. Lower cost per connection, reuse of existing network infrastructures, very high data rates, good noise rejection over long cables and finally an easier maintainability of the software in the long term are the main reasons of its success. In addition, the need of low latency systems of the High Frequency Trading community has boosted the development of new strategies, such as CPU isolation, to run real-time applications in plain Linux with a determinism of the order of microseconds. DPDK (Data Plane Development Kit), an open source software solution mainly sponsored by Intel, addresses the request of high determinism over Ethernet by bypassing the network stack of Linux and providing a more friendly framework to develop tasks which are even able to saturate a 100 Gbit connection. Benchmarks regarding the real-time performance and preliminary results of employing DPDK in the acquisition of beam position monitors for the fast orbit feedback of the Elettra storage ring will be presented.

Poster MOPHA044 [2.626 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA044

About •

paper received ※ 29 September 2019 paper accepted ※ 08 October 2019 issue date ※ 30 August 2020

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WEPHA021

Free-Electron Laser Optimization with Reinforcement Learning

1122

N. Bruchon, G. Fenu, F.A. Pellegrino, E. Salvato
University of Trieste, Trieste, Italy
G. Gaio, M. Lonza
Elettra-Sincrotrone Trieste S.C.p.A., Basovizza, Italy

Reinforcement Learning (RL) is one of the most promising techniques in Machine Learning because of its modest computational requirements with respect to other algorithms. RL uses an agent that takes actions within its environment to maximize a reward related to the goal it is designed to achieve. We have recently used RL as a model-free approach to improve the performance of the FERMI Free Electron Laser. A number of machine parameters are adjusted to find the optimum FEL output in terms of intensity and spectral quality. In particular we focus on the problem of the alignment of the seed laser with the electron beam, initially using a simplified model and then applying the developed algorithm on the real machine. This paper reports the results obtained and discusses pros and cons of this approach with plans for future applications.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-WEPHA021

About •

paper received ※ 30 September 2019 paper accepted ※ 09 October 2019 issue date ※ 30 August 2020

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)