Combining Machine Learning and Classical Optimization Techniques in Vehicle to Vehicle Communication Network

  • Mutasem HamdanEmail author
  • Khairi HamdiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11871)


In this paper a new optimization technique has been proposed to take the advantage of both the Hungarian Algorithm and Deep Q-Learning Neural Network (DQN) to solve the frequency and power resources allocation problem in Vehicle to Vehicle (V2V) future networks. The result shows a better performance for the sum of cellular users throughput, reducing the complexity of the classical optimization methods, overcome the huge State-Action matrix in Q-learning and provides wireless environment features to approximate the Q-values.


Deep Q-Learning Network Vehicle to vehicle network Reinforcement Learning Radio resource management Ultra Reliable Low Latency communications Maximum weigh matching 


  1. 1.
    3GPP-TR-8.824: Study on physical layer enhancements for NR ultra-reliable and low latency case (URLLC) (2019)Google Scholar
  2. 2.
    3GPP-TR-TS-122-185: 122 185, LTE; service requirements for V2X services (3GPP TS 22.185 version 15.0.0 release 15) (2018)Google Scholar
  3. 3.
    Liang, L., Li, G.Y., Xu, W.: Resource allocation for D2D-enabled vehicular communications. IEEE Trans. Commun. 65(7), 3186–3197 (2017)CrossRefGoogle Scholar
  4. 4.
    Mei, J., Zheng, K., Zhao, L., Teng, Y., Wang, X.: A latency and reliability guaranteed resource allocation scheme for LTE V2V communication systems. IEEE Trans. Wireless Commun. 17(6), 3850–3860 (2018)CrossRefGoogle Scholar
  5. 5.
    Parsaeefard, S., Sharafat, A.R., Mokari, N.: Robust Resource Allocation in Future Wireless Networks. Springer, Cham (2017). Scholar
  6. 6.
    Sun, W., Ström, E.G., Brännström, F., Sou, K.C., Sui, Y.: Radio resource management for D2D-based V2V communication. IEEE Trans. Veh. Technol. 65(8), 6636–6650 (2015)CrossRefGoogle Scholar
  7. 7.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)zbMATHGoogle Scholar
  8. 8.
    Ye, H., Li, G.Y., Juang, B.H.F.: Deep reinforcement learning based resource allocation for V2V communications. IEEE Trans. Veh. Technol. 68(4), 3163–3173 (2019)CrossRefGoogle Scholar
  9. 9.
    Yu, F.R., He, Y.: Reinforcement learning and deep reinforcement learning. Deep Reinforcement Learning for Wireless Networks. SECE, pp. 15–19. Springer, Cham (2019). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of EEEThe University of ManchesterManchesterUK

Personalised recommendations