Kdn-users September 2019

kdn-users@knowledgedefinednetworking.org

3 participants
7 discussions

Normalisation
by Nathan Sowatskey 11 Nov '19

11 Nov '19

Hi In the demo code, for example in: https://github.com/knowledgedefinednetworking/demo-routenet/blob/master/dem… A form of normalisation is applied: predictions = 0.54*preds + 0.37 This is consistent with the parse() function here: https://github.com/knowledgedefinednetworking/demo-routenet/blob/master/cod… if k == 'delay': features[k] = (features[k] - 0.37) / 0.54 if k == 'traffic': features[k] = (features[k] - 0.17) / 0.13 if k == 'link_capacity': features[k] = (features[k] - 25.0) / 40.0 There is another case here: https://github.com/knowledgedefinednetworking/network-modeling-GNN/blob/mas… if k == 'delay': features[k] = (tf.math.log(features[k]) + 1.78) / 0.93 if k == 'traffic': features[k] = (features[k] - 0.28) / 0.15 if k == 'jitter': features[k] = (features[k] - 1.5) / 1.5 if k == 'link_capacity': features[k] = (features[k] - 27.0) / 14.86 if k == 'queue_sizes': features[k] = (features[k] - 16.5) / 15.5 What is the basis for this normalisation and those specific constants please? Why does the normalisation in routenet_with_link_cap and routenet_with_forwarding_nodes differ? Many thanks Nathan

3 5

GBN topology
by Nathan Sowatskey 30 Oct '19

30 Oct '19

Hi On this page: https://github.com/knowledgedefinednetworking/Unveiling-the-potential-of-GN… I have seen that there is this data set: http://knowledgedefinednetworking.org/data/GBN.zip It is described as having been used for evaluation, but I can’t find anything else that refers to it. Can anyone tell me more please? Many thanks Nathan

3 11

Normalisation in the demo.ipynb incompatible with training code
by Nathan Sowatskey 09 Oct '19

09 Oct '19

Hi I have noted that the normalisation applied in the demo notebook here: https://github.com/knowledgedefinednetworking/demo-routenet/blob/master/dem… Does not apply the same normalisation as the code here: https://github.com/knowledgedefinednetworking/demo-routenet/blob/master/cod… Specifically, delay is not normalised in the demo notebook. The demo notebook loads a checkpoint from here: https://github.com/knowledgedefinednetworking/demo-routenet/tree/master/tra… <https://github.com/knowledgedefinednetworking/demo-routenet/tree/master/tra…> This model, then, was created without normalising the delay also. That implies that the code that was used to train that model is not the same code that is in the routenet_with_link_cap.py code at the link above. In simpler terms, the demo notebook prediction does not work if the delay is normalised as at routenet_with_link_cap.py#L85. So, the code for training given in this repository is not compatible with the demo notebook and the trained model used as an example. Regards Nathan

2 5

Trained models
by Nathan Sowatskey 25 Sep '19

25 Sep '19

Hi This page: https://github.com/knowledgedefinednetworking/Unveiling-the-potential-of-GN… Has links for trained models from eight months ago. This page: https://github.com/knowledgedefinednetworking/demo-routenet/tree/master/tra… Has links for trained models from three months ago. Can anyone explain how these sets of trained model data are related please? Many thanks Nathan

2 1

NSF net topology diagram compared to NED file
by Nathan Sowatskey 10 Sep '19

10 Sep '19

Hi The NSF net topology is, I think, represented in this diagram: https://github.com/knowledgedefinednetworking/NetworkModelingDatasets/blob/… The same network is also, I think, represented by the NED file in this compressed tar: http://knowledgedefinednetworking.org/data/datasets_v0/nsfnet.tar.gz That NED file is also here in my project: https://github.com/Data-Science-Projects/demo-routenet/blob/master/tests/un… In that NED file, I see these connections: node2.port[2] <--> Channel10kbps <--> node5.port[0]; node4.port[1] <--> Channel40kbps <--> node5.port[1]; node5.port[2] <--> Channel10kbps <--> node12.port[0]; node5.port[3] <--> Channel10kbps <--> node13.port[0]; In my (refactored from original code) I have these values for the connections at https://github.com/Data-Science-Projects/demo-routenet/blob/master/src/rout… [{0: 1, 1: 3, 2: 2}, {0: 0, 1: 2, 2: 7}, {0: 0, 1: 1, 2: 5}, {0: 0, 1: 4, 2: 8}, {0: 3, 1: 5, 2: 6}, {0: 2, 1: 4, 2: 12, 3: 13}, {0: 4, 1: 7}, {0: 1, 1: 6, 2: 10}, {0: 3, 1: 9, 2: 11}, {0: 8, 1: 10, 2: 12}, {0: 7, 1: 9, 2: 11, 3: 13}, {0: 8, 1: 10, 2: 12}, {0: 5, 1: 9, 2: 11}, {0: 5, 1: 10}] Node 5 is: {0: 2, 1: 4, 2: 12, 3: 13}, which means node 5 is connected to nodes 2, 4, 12 and 13. In the diagram, node 5 is connected to 2, 4, 12 and 8. Does anyone have any ideas as to where the discrepancy is coming from please? Many thanks Nathan

2 1

How to use OMNeT++ to run the network simulations
by Nathan Sowatskey 10 Sep '19

10 Sep '19

Hi Can anyone here help me understand how to run the network simulations with OMNeT++ to recreate the original data pipeline please? Many thanks Nathan

2 1

kdn CN domain and keyword
by Peter Liu 02 Sep '19

02 Sep '19

(Please forward this to your CEO, because this is urgent. Thanks) This is a formal email. We are the Domain Registration Service company in China. Here I have something to confirm with you. On August 6, 2019, we received an application from Kaiqian Ltd requested "kdn" as their internet keyword and China (CN) domain names (kdn.cn, kdn.com.cn, kdn.net.cn, kdn.org.cn). But after checking it, we find this name conflict with your company name or trademark. In order to deal with this matter better, it's necessary to send email to you and confirm whether your company have association with this Chinese company or not? Best Regards *************************************** Peter Liu | Service & Operations Manager China Registry (Head Office) | 6012, Xingdi Building, No. 1698 Yishan Road, Shanghai 201103, China Tel: +86-02164193517 | Fax: +86-02164198327 | Mob: +86-13816428671 Email: peter(a)chinaregistry.org Web: www.chinaregistry.org *************************************** This email contains privileged and confidential information intended for the addressee only. If you are not the intended recipient, please destroy this email and inform the sender immediately. We appreciate you respecting the confidentiality of this information by not disclosing or using the information in this email.

2 1

2026

2025

2024

2023

2022

2021

2020

2019

Kdn-users September 2019