Planning of transient operational modes of large gas transportation systems using an iterative linear-quadratic regulator and differentiated physics methods
UDC: 519.673
DOI: -
Authors:
BELINSKY A.V.
1
1 NIIGazekonomika, Moscow, Russia
Keywords: digital modeling, non-stationary mode, optimization, gas transportation system, differentiable programming, neural network
Annotation:
It is impossible to imagine control of technological modes operation of large gas transportation systems (GTS) without using specialized computer technologies designed to model and support management decisions. Modern gas transportation systems (GTS) are characterized by large lengths, significant differences between the current technological modes and the design ones and an increase of gas consumption unevenness. Perfection of the operational management of such systems requires the development of an appropriate methodological and algorithmic base for optimal planning of their operational modes. The author of the article proposes a new algorithm for solving some problems of planning non-stationary modes of GTS. The algorithm is based on a simulation non-stationary hybrid model of a large GTS and its computer implementation based on the paradigm of differentiable physics and the use of hardware acceleration of computations on graphic processors (GPU). A distinctive feature of the model is its auto-differentiability. The proposed mathematical, software and hardware modeling methods make it possible to develop a new effective computer technology for solving current computational problems of planning non-stationary modes of GTS operation at the upper control level of the Unified Gas Supply System (UGSS). A mathematical formulation of one problem of non-stationary modes quasi-optimal control is presented. The results of computational experiments performed on examples of real large GTS are given. Some specific features of the approaches considered above, the adequacy of the assumptions made as well as the prospects for further development of differentiable programming methods and algorithms for optimizing non-stationary modes of GTS operation based on them are discussed.
Bibliography:
1. Sukharev M.G., Pankratov V.S., Samoylov R.V. Optimizatsiya nestatsionarnykh rezhimov deystvuyushchikh magistral'nykh gazoprovodov // Gazovaya prom-st'. – 2002. – № 9. – S. 72–75.
2. Sardanashvili S.A. Raschetnye metody i algoritmy (truboprovodnyy transport gaza). – M.: Izd-vo "Neft' i gaz" RGU nefti i gaza im. I.M. Gubkina, 2005. – 577 s.
3. Sukharev M.G., Samoylov R.V. Analiz i upravlenie statsionarnymi i nestatsionarnymi rezhimami transporta gaza. – M.: Izdat. tsentr RGU nefti i gaza (NIU) im. I.M. Gubkina, 2016. – 399 s.
4. Blondel M., Roulet V. The Elements of Differentiable Programming. – 2024. – 451 p. – DOI: arXiv:2403.14606
5. Belinskiy A.V. Differentsiruemaya fizika – osnova tsifrovykh dvoynikov v neftegazovom komplekse // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 12(617). – S. 38–50.
6. Belinskiy A.V. Imitatsionnaya nestatsionarnaya gibridnaya model' krupnoy gazotransportnoy sistemy s apparatnym uskoreniem vychisleniy na graficheskikh protsessorakh // Avtomatizatsiya i informatizatsiya TEK. – 2025. – № 2(619). – S. 34–47.
7. Li Weiwei, Todorov E. Iterative Linear Quadratic Regulator Design for Nonlinear Biological Movement Systems // Proc. of the First Int. Conf. on Informatics in Control, Automation and Robotics, Setúbal, Portugal, Aug. 25–28, 2004. – Vol. 1. – P. 222–229. – DOI: 10.5220/0001143902220229
8. Tassa Yu., Erez T., Todorov E. Synthesis and stabilization of complex behaviors through online trajectory optimization // 2012 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Vilamoura-Algarve, Portugal, Oct. 07–12, 2012. – P. 4906–4913. – DOI: 10.1109/IROS.2012.6386025
9. Jackson B. AL-iLQR Tutorial. – URL: https://bjack205.github.io/papers/AL_iLQR_Tutorial.pdf (data obrashcheniya 12.11.2024).
10. Tassa Yu., Mansard N., Todorov E. Control-limited differential dynamic programming // 2014 IEEE Int. Conf. on Robotics and Automation (ICRA), Hong Kong, China, May 31 – June 07, 2014. – P. 1168–1175. – DOI: 10.1109/ICRA.2014.6907001
11. Särkkä S., García-Fernández Á.F. Temporal Parallelization of Dynamic Programming and Linear Quadratic Control // IEEE Transactions on Automatic Control. – 2023. – Vol. 68, Issue 2. – P. 851–866. – DOI: 10.1109/TAC.2022.3147017
Back to issue