[3] [3] YU M, YI Y, REXFORD J, et al. Rethinking virtual network embedding: substrate support for path splitting and migration[J]. ACM SIGCOMM Computer Communication Review, 2008, 38(2): 17-29.

[4] [4] FISCHER A, BOTERO J F, BECK M T, et al. Virtual Network Embedding: A Survey[J]. IEEE Communications Surveys & Tutorials, 2013, 15(4): 1888-1906.

[5] [5] FENGQING L, QINGJI Z, XU Z, et al. Virtual Topology Reconfigurat-

          ion in WDM Optical Networks[J]. ACTA PHOTONICA SINICA, 2003, 32(10): 1175-1180.

[6] [6] CHOWDHURY M, RAHMAN M R, BOUTABA R. Virtual network embedding algorithms with coordinated node and link mapping [J]. IEEE/ACM Transactions on networking, 2011, 20(1): 206-219.

[7] [7] cation Review, 2011, 41(2): 38-47.

          CHENG X, SU S, ZHANG Z, et al. Virtual network embedding through topology-aware node ranking[J]. ACM SIGCOMM Computer Communi-

[8] [8] CHOWDHURY N M, RAHMAN M R, BOUTABA R. Virtual network embedding with coordinated node and link mapping [C]// IEEE INFOCOM 2009, Apr 19-25, 2009, Riode Janeiro, Brazil. Piscataway: IEEE, 2009:783-791.

[9] [9] YOU X, WANG X, CHEN A, et al. A coordinated algorithm with resource evaluation for service function chain allocation [C]// 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Oct. 8-10, 2016, Atlanta, USA. Piscataway: IEEE, 2016: 45-49.

[10] [10] WANG Y, LU P, LU W, et al. Cost-efficient virtual network function graph (vNFG) provisioning in multidomain elastic optical networks[J]. Journal of Lightwave Technology, 2017, 35(13): 2712-2723.

[11] [11] WHITE, DOUGLAS J. Dynamic programming, Markov chains, and the method of successive approximations[J]. Journal of Mathematical Analysis and Applications, 1963, 6(3): 373-376.

[12] [12] SUTTON R S, BARTO A G. Introduction to reinforcement learning[M]. Cambridge: MIT press, 1998.

[13] [13] WATKINS C J C H , DAYAN P . Technical Note: Q-Learning[J]. Machine Learning, 1992, 8(3-4): 279-292.

[14] [14] LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[J]. arXiv preprint: 1509.02971, 2015.

[15] [15] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-533.

[17] [17] MOKHTAR A, AZIZOGLU M. Adaptive wavelength routing in all-optical networks[J]. IEEE/ACM Transactions on Networking, 1998, 6(2):197-206.