The mesh topology and point-to-point exchange wireless networks actualize the task of
developing algorithms that increase the efficiency of routing these networks. An important feature of
these networks is to use the limited battery life devices. The algorithm development taking into account
battery level is an urgent task as this factor is one of the important factors affecting the network as a
whole. Preview articles the author developed a new Adaptive Rate Full Echo routing algorithm, which
is based on the Q-Routing algorithm, using the reinforced machine learning methods. In addition the
previous author works a simulation model was presented in the Anylogic simulation system, where the
developed algorithm simulation results were performed. The simulation model Verification is a necessary condition for the correctness and reliability of the data received in it. This article presents the
results of checking the adequacy of the developed simulation model of the Adaptive Rate Full Echo
algorithm by comparing the simulation results with the results of field tests.
1. Shilova Yu.A. Algoritm marshrutizatsii semeystva Q-routing, osnovannyy na
dinamicheskom izmenenii koeffitsientov obucheniya za schet otsenki sredney zaderzhki v
seti. Vestnik Permskogo nauchnogo tsentra. 2015;(2):79-93.
2. Shilova Yu.A., Kavalerov M.V. Razrabotka algoritmov marshrutizatsii semeystva QROUTING dlya mobil'nykh ADHOC setey. Avtomatizirovannye sistemy upravleniya i
informatsionnye tekhnologii: materialy Vseros. nauch.-tekhn. konf., 15 maya 2015, Perm'.
Perm': Izd-vo PNIPU; 2015. s. 441-446.
3. Shilova Y., Kavalerov M., Bezukladnikov I. Full Echo Q-Routing with Adaptive Learning
Rates: A Reinforcement Learning Approach to Network Routing. Proceedings of the 2016
IEEE North West Russia Section Young Researchers in Electrical and Electronic
Engineering Conference, 2016 ElConRusNW, 2-3 February 2016, St. Petersburg. St.
Petersburg: St. Petersburg Electrotechnical Univ. LETI; 2016. p. 365-368.
4. Boyan J., Littman M. Packet Routing In Dynamically Changing Networks: A
Reinforcement Learning Approach. Advances In Neural Information Processing Systems.
1994:671-678.
5. Kumar S., Miikkulainen R. Dual Reinforcement Q-Routing: An On-Line Adaptive Routing
Algorithm. Artificial neural networks in engineering. 1997: 231-238.
6. Choi S., Yeung D.Y., Predictive Q-routing: A memory-based reinforcement learning
approach to adaptive traffic control. Advances in Neural Information Processing Systems.
1996;(8):945-951.
7. Subramanian D., Druschel P., Chen J. Ants and reinforcement learning: A case study in
routing in dynamic networks. IJCAI (2); 1997. p. 832-839.
8. Tao N., Baxter J., Weaver L. A Multi-Agent Policy-Gradient Approach to Network
Routing. ICML, 2001;1. p. 553-560.
9. Sutton R.S., Barto A.G. Reinforcement learning: An introduction. ambridge: MIT press;
1998.
10. Watkins C., Dayan P. Q-learning. Machine learning.1992;8(3):279-292.
11. Shilova Yu.A., Yuzhakov A.A., Bezukladnikov I.I., Kavalerov M.V. Vliyanie koeffitsienta
«skorost' rasprostraneniya ekho» na effektivnost' marshrutizatsii algoritma
AdaptiveRateFullEcho. Vestnik IzhGTU. 2019;22(2):65-72
12. Shilova Yu.A., Kon E.L. Modelirovanie bazovogo protokola Q-Routing v srede Anylogic.
Problemy tekhniki i tekhnologiy telekommunikatsiy (PTiTT-2016): materialy XVII
mezhdunar. nauch.-tekhn. konf., 22-24 noyabrya 2016, Samara. Samara; 2016. c. 131-132.
13. Shilova Y.A. , Bezukladnikov I.I. Influence of the battery life parameter on the Q-routing
algorithm results. 2017 IEEE Conference of Russian Young Researchers in Electrical and
Electronic Engineering (ElConRus): Proc. of the 2017 IEEE Russia Section Young
Researchers in Electrical and Electronic Engineering Conference (2017 ElConRus), 1-3
Febr. 2017, St. Petersburg, Moscow. St. Petersburg: IEEE; 2017. p. 213-217.
Shilova Yulia Aleksandrovna
Email: marissaspiritte@mail.ru
Perm National Research Polytechnic University
Perm, Russian Federation
