HARDWARE AND SOFTWARE MEANS FOR DYNAMIC RECONFIGURATION OF A GROUP OF SMALL SPACE VEHICLES
Abstract
The goal of the study is to automate the control of a group of nanosatellites in conditions of its
variable number by updating its state based on sending and processing broadcast requests between
nanosatellites and using the Transformer neural network. A neural network is needed to make predi ctions
about the state of the spacecraft network. The problem of ensuring connectivity of a network of
nanosatellites is studied, which comes down to the implementation of adaptive network control with
assessment and prediction of the state of communication channels between pairs of devices based on a
neural network. Dynamic reconfiguration and machine learning of a network of devices have been developed.
Algorithmic tools have been defined for the initial training of a neural network and its subs equent
additional training, taking into account the preprocessing of the original sparse or fully connected
data sets about the network of devices. Upon completion of training on synthetic data, the created
neural network is able to predict the quality of communication, taking into account line of sight, signal
attenuation depending on distance and the state of the nanosatellite hardware platform. The developed
software system performs deterministic reconfiguration based on the current state of the nanosatellite
network and adaptive reconfiguration based on historical data by analyzing the hidden patterns of
nanosatellite functioning using the Transformer neural network. To predict the quality of communication,
a functional is used to connect the geodetic coordinates of pairs of satellites and the vectors of
their states with the elements of the matrix of the quality of communication between nanosatellites with
a given initial time, the value of the time interval, and the value of the sampling step of the measurement
process. The use of neural networks implemented on GPUs made it possible to predict possible
states of nanosatellites and carry out reconfiguration of the constellation ahead of schedule, including
removing “problematic” nanosatellites from the network.
References
2012, 159 p.
2. Spiridonov A.A., Veligan V.A., SHalatonin I.A. [i dr.]. Nizkoorbital'nye gruppirovki malorazmernykh
kosmicheskikh apparatov [Low-orbit groupings of small-sized spacecraft], Kvantovaya elektronika:
Mater. XIII Mezhdunarodnoy nauchno-tekhnicheskoy konferentsii [Quantum electronics: Proceedings
of the XIII International Scientific and Technical Conference]. Minsk: BelGU, 2021, pp. 421-424.
3. Potyupkin A.Yu. Upravlenie mnogosputnikovymi orbital'nymi gruppirovkami [Control of multisatellite
orbital constellations], Raketno-kosmicheskoe priborostroenie i informatsionnye sistemy
[Rocket and space instrumentation and information systems], 2020, Vol. 7, Issue 3, pp. 61-70.
4. Zheltov S.Yu., Kalyaev I.A., Kos'yanchuk V.V., Mel'nik E.V., Zybin E.Yu. Rekonfiguratsiya sistem
upravleniya vozdushnykh sudov [Reconfiguration of aircraft control systems]. Moscow: Rossiyskaya
akademiya nauk, 2021, 204 p.
5. Popkov G.V. Mesh-seti: perspektivy razvitiya, vozmozhnye primeneniya [Mesh networks: development
prospects, possible applications], Problemy informatiki [Problems of computer science], 2012,
No. 3 (15), pp. 74-79.
6. Aganesov A.V., Makarenko S.I. Balansirovka informatsionno nagru ki me hdu vo dushnym i
kosmicheskim segmentami ob"edinenno vo dushno kosmichesko seti svya i, postroenno na osnove
mesh-tekhnologii [Balancing the information load between the air and space segments of an integrated
aerospace communication network built on the basis of mesh technology], Naukoemkie tekhnologii v
kosmicheskikh issledovaniyakh Zemli [Science-intensive technologies in space research of the Earth],
2016, Vol. 8, No. 1, pp. 17-25.
7. Zatsepin E.S. Kharakteristiki protokolov v mesh-setyakh [Characteristics of protocols in mesh networks],
Modelirovanie, optimizatsiya i informatsionnye tekhnologii [Modeling, optimization and information
technologies], 2015, No. 1 (8). Available at: https://moit.vivt.ru/wp-content/uploads/
2015/04/Zatsepin_1_15_1.pdf.
8. Kalyaev I.A., Gayduk A.R. Odnorodnye neyropodobnye struktury v sistemakh vybora deystviy
intellektual'nykh robotov [Homogeneous neural-like structures in action selection systems of intelligent
robots]. Moscow: Izd-vo «YAnus-K», 2000, 280 p.
9. Kalyaev I.A., Gayduk A.R. Staynye printsipy upravleniya v gruppe ob"ektov [Flock principles of control
in a group of objects], Mekhatronika, avtomatizatsiya, upravlenie [Mechatronics, automation, control],
2004, No. 12, pp. 27-38.
10. Kalyaev I.A., Kapustyan S.G., Gayduk A.R. Samoorganizuyushchiesya raspredelennye sistemy
upravleniya gruppami intellektual'nykh robotov, postroennye na osnove setevoy modeli [Selforganizing
distributed systems for managing groups of intelligent robots, built on the basis of a network
model], Upravlenie bol'shimi sistemami: Sb. trudov [Management of large systems: Collection
of works], 2010, No. 30-1, pp. 605-639.
11. Kalyaev I.A., Mel'nik E.V. Detsentralizovannye sistemy komp'yuternogo upravleniya [Decentralized
computer control systems]. Rostov-on-Don: Yuzhnyy nauchnyy tsentr RAN, 2011, 196 p.
12. Kalyaev I.A., Kapustyan S.G., Gayduk A.R. Raspredelennye sistemy planirovaniya deystviy
kollektivov robotov [Distributed systems for planning the actions of teams of robots]. Moscow:
I datel'stvo «Yanus-K», 2002, 292 p.
13. Kalyaev I.A., Gayduk A.R., Kapustyan S.G. Modeli i algoritmy kollektivnogo upravleniya v gruppakh
robotov [Models and algorithms for collective control in groups of robots]. Moscow: OOO
Izdatel'skaya firma "Fiziko-matematicheskaya literatura", 2009, 280 p.
14. Kalyaev I.A., Gayduk A.R., Kapustyan S.G. Upravlenie kollektivom intellektual'nykh ob"ektov na
osnove staynykh printsipov [Management of a collective of intellectual objects based on flock principles],
Vestnik Yuzhnogo nauchnogo tsentra RAN [Bulletin of the Southern Scientific Center of the
Russian Academy of Sciences], 2005, Vol. 1, No. 2, pp. 20-27.
15. Kalyaev A.I., Kalyaev I.A. Metod mul'tiagentnogo dispetchirovaniya resursov v oblachnykh
vychislitel'nykh sredakh [Method of multi-agent resource dispatching in cloud computing environments],
Izvestiya Rossiyskoy akademii nauk. Teoriya i sistemy upravleniya [Izvestia of the Russian
Academy of Sciences. Theory and control systems], 2016, No. 2, pp. 51-63.
16. Emel'yanov S.G. [i dr.]. Vybor arkhitektury neyronnoy seti dlya realizatsii kognitivnykh funktsiy
setevogo programmnogo obespecheniya upravleniya gruppirovkoy vzaimodeystvuyushchikh malykh
kosmicheskikh apparatov [Selecting a neural network architecture for implementing cognitive functions
of network software for controlling a group of interacting small spacecraft], Izvestiya Yugozapadnogo
gosudarstvennogo universiteta. Seriya «Upravlenie, vychislitel'naya tekhnika, informatika.
Meditsinskoe priborostroenie» [News of the South-Western State University. Series “Management,
computer technology, information science. Medical instrumentation"], 2023, Vol. 13, No. 4, pp. 8-26.
17. Usatyuk V.S., Egorov S.I., Loktionov A.P., Titenko E.A., Chernetskaya I.E. Arkhitektura neyronnykh
setey na osnove kodov na grafakh [Architecture of neural networks based on graph codes], Izvestiya
YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2023, No. 5 (235), pp. 81-92.
18. Tensorflow. Available at: https://www.tensorflow.org/?hl=ru (accessed 29.01.2024).
19. Cafe. Available at: https://caffe.berkeleyvision.org (accessed 29.01.2024).
20. osgEarth. Available at: https://github.com/gwaldron/osgearth (accessed 29.01.2024).
21. Qt. Available at: https://github.com/qt (accessed 29.01.2024).
22. Keras. Available at: https://keras.io (accessed 29.01.2024).
