FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206013722> ?p ?o ?g. }

• W4206013722 endingPage "102804" @default.
• W4206013722 startingPage "102804" @default.
• W4206013722 abstract "• QoT prediction problem in optical networks is elaborated, including the main QoT influence factors, QoT metrics, and QoT prediction strategies. • The QoT prediction model construction is reviewed from four aspects, i.e., ML algorithm selection, dataset generation, ML frameworks, construction process of QoT prediction model. • Three kinds of QoT prediction solutions are traditional ML based QoT prediction models, transfer learning or/and active learning assisted QoT prediction models, and APLMs with ML. • Some future research directions are proposed, including digital twin based QoT prediction and transfer learning assisted light-trees QoT prediction, pre-weighted input features for QoT prediction, and improvement in adaptability of QoT prediction model. In optical networks, a connection (e.g., light-path and light-tree) is set up to carry data from its source to destination(s). When the optical signal transmits through the fiber links and optical devices, the quality of transmission (QoT) degrades due to various physical layer impairments (PLIs), including linear and nonlinear impairments. QoT is an important metric that determines the availability of a connection. Therefore, the QoT guarantee is the premise of successful connection establishment in optical networks. QoT prediction before connections establishment can provide guidance for the routing and resources allocation of connections. In order to receive the correct signal at the receiving end, during network planning design margins are introduced to compensate the inaccuracy of the QoT prediction model itself and its inputs. Improving the accuracy of prediction can make better use of network resources and reduce margins. With the help of strong computing power and data acquisition based on software defined optical network (SDON), machine learning (ML) based models are more suitable for QoT prediction than analytical models that are difficult to derive and computationally heavy. This paper provides an overview on the applications of ML technologies in QoT prediction. Firstly, we elaborate the QoT problem in optical networks, including main QoT influence factors, QoT metrics, and QoT prediction strategies. Then, suitable ML algorithms, the generation of sample data, ML frameworks and the construction of QoT prediction model, are briefly introduced. Next, three solutions of QoT prediction using various ML technologies in recent studies and their practical feasibility are reviewed and discussed in detail. Finally, based on the existing researches, we present some future research directions about the improvement of QoT prediction." @default.
• W4206013722 created "2022-01-25" @default.
• W4206013722 creator A5000244314 @default.
• W4206013722 creator A5006496929 @default.
• W4206013722 creator A5022526821 @default.
• W4206013722 creator A5044757881 @default.
• W4206013722 creator A5068378063 @default.
• W4206013722 date "2022-01-01" @default.
• W4206013722 modified "2023-10-15" @default.
• W4206013722 title "A survey on QoT prediction using machine learning in optical networks" @default.
• W4206013722 cites W1565206818 @default.
• W4206013722 cites W1675807599 @default.
• W4206013722 cites W1824964336 @default.
• W4206013722 cites W1980346416 @default.
• W4206013722 cites W1991329089 @default.
• W4206013722 cites W1999631531 @default.
• W4206013722 cites W2045328657 @default.
• W4206013722 cites W2060184834 @default.
• W4206013722 cites W2094195976 @default.
• W4206013722 cites W2117416428 @default.
• W4206013722 cites W2154992728 @default.
• W4206013722 cites W2167770189 @default.
• W4206013722 cites W2230508580 @default.
• W4206013722 cites W2238313612 @default.
• W4206013722 cites W2441610205 @default.
• W4206013722 cites W2507413285 @default.
• W4206013722 cites W2566947163 @default.
• W4206013722 cites W2592219426 @default.
• W4206013722 cites W2592469385 @default.
• W4206013722 cites W2594369284 @default.
• W4206013722 cites W2745723384 @default.
• W4206013722 cites W2775596497 @default.
• W4206013722 cites W2782717155 @default.
• W4206013722 cites W2786530623 @default.
• W4206013722 cites W2787811863 @default.
• W4206013722 cites W2789546260 @default.
• W4206013722 cites W2789611500 @default.
• W4206013722 cites W2789930327 @default.
• W4206013722 cites W2790165588 @default.
• W4206013722 cites W2793024511 @default.
• W4206013722 cites W2793477598 @default.
• W4206013722 cites W2798760831 @default.
• W4206013722 cites W2798915608 @default.
• W4206013722 cites W2798967212 @default.
• W4206013722 cites W2883295335 @default.
• W4206013722 cites W2885792477 @default.
• W4206013722 cites W2888353605 @default.
• W4206013722 cites W2890645375 @default.
• W4206013722 cites W2891869894 @default.
• W4206013722 cites W2892971304 @default.
• W4206013722 cites W2893911944 @default.
• W4206013722 cites W2894189411 @default.
• W4206013722 cites W2901474018 @default.
• W4206013722 cites W2903054686 @default.
• W4206013722 cites W2915431577 @default.
• W4206013722 cites W2916940669 @default.
• W4206013722 cites W2917350099 @default.
• W4206013722 cites W2951309479 @default.
• W4206013722 cites W2955064870 @default.
• W4206013722 cites W2957479875 @default.
• W4206013722 cites W2963275094 @default.
• W4206013722 cites W2971189838 @default.
• W4206013722 cites W2972578887 @default.
• W4206013722 cites W2974498915 @default.
• W4206013722 cites W2976987664 @default.
• W4206013722 cites W2980227124 @default.
• W4206013722 cites W2999690985 @default.
• W4206013722 cites W3006729569 @default.
• W4206013722 cites W3008696318 @default.
• W4206013722 cites W3008715599 @default.
• W4206013722 cites W3009067229 @default.
• W4206013722 cites W3009810111 @default.
• W4206013722 cites W3009851327 @default.
• W4206013722 cites W3009929121 @default.
• W4206013722 cites W3009963993 @default.
• W4206013722 cites W3010422375 @default.
• W4206013722 cites W3011703836 @default.
• W4206013722 cites W3026881745 @default.
• W4206013722 cites W3035804929 @default.
• W4206013722 cites W3035926310 @default.
• W4206013722 cites W3038105246 @default.
• W4206013722 cites W3041974506 @default.
• W4206013722 cites W3080803028 @default.
• W4206013722 cites W3087920449 @default.
• W4206013722 cites W3088531132 @default.
• W4206013722 cites W3088747148 @default.
• W4206013722 cites W3089196880 @default.
• W4206013722 cites W3089275085 @default.
• W4206013722 cites W3089308774 @default.
• W4206013722 cites W3097847617 @default.
• W4206013722 cites W3101357614 @default.
• W4206013722 cites W3102123752 @default.
• W4206013722 cites W3103337000 @default.
• W4206013722 cites W3110461717 @default.
• W4206013722 cites W3115243282 @default.
• W4206013722 cites W3116615680 @default.
• W4206013722 cites W3119734556 @default.
• W4206013722 cites W3120020704 @default.

• next