• 1. pICA Emulator
  • 1.1. Table of Contents
  • 1.2. Description
  • 1.3. Requirements
  • 1.4. Getting Started
    • 1.4.1. Option1: Install in a Vagrant managed VM (Highly Recommended)
    • 1.4.2. Option2: Install on user's custom VM or directly on host OS (Ubuntu20.04)
  • 1.5. Install docker image of pICA
  • 1.6. Run pICA in the Emulator
  • 1.7. Citation
  • 1.8. About Us
  • 1.9. License

This application emulate the Progressive Independent Component Analysis (pICA) in the network, it is based on the comnetsemu. A pICA demonstrator can be accessed on pICA-Demo.

Please install vagrant and Virtualbox on the host OS to build the testbed VM.

Please run follow steps to setup the emulator. Assume the source directory of pICA-emu project is ~/pICA-emu.

1. Create the testbed VM using Vagrant on your host OS.

   cd ~/pICA-emu || exit
   vagrant up testbed

   Then run vagrant ssh testbed to login into the VM. Following steps should be run inside the VM.

2. Install docker-ce and add docker into user group

   cd ~/comnetsemu/util
   bash ./install.sh -d
   
   sudo groupadd docker
   sudo gpasswd -a vagrant docker
   newgrp docker
   sudo systemctl start docker
   
   cd /home/vagrant/comnetsemu/test_containers || exit
   sudo bash ./build.sh

3. Upgrade ComNetsEmu Python module and all dependencies automatically inside VM

   cd ~/comnetsemu/util
   bash ./install.sh -u

4. Run test to make sure the ComNetsEmu is installed correctly (optional).

   cd ~/comnetsemu
   sudo make test

   Only run following steps when all tests passed without any errors. Otherwise, please create issues on Github from Zuo Xiang.

1. Install the comnetsemu and simpleemu on your host OS.

   cd ~/pICA-emu/emu-installer || exit
   bash ./install.sh

2. Run test to make sure the ComNetsEmu is installed correctly (optional).

   cd ~/comnetsemu
   sudo make test

   Only run following steps when all tests passed without any errors. Otherwise, please create issues on Github from Zuo Xiang.

1. Build the docker image of pICA.

   cd /vagrant
   sudo bash ./build_docker_images.sh

   For ARM64 users, please run

   cd /vagrant
   sudo bash ./build_docker_images_arm64.sh

   After this step, you should see the image with name pica_dev when running docker image ls. You should change your work path inside the VM for following steps.

1. Run the topology in the folder /vagrant/emulator:

   cd /vagrant/emulator
   sudo python3 ./topo.py

   You should see the prompt mininet> when the network configuration is finished. And five terminals are popped up, you can identify client, server, VNF, swich, and a controller by looking at the host name (e.g., @client) in the shell.

   The number of VNFs is defined as 2 in topo.py. For an arbitary number of VNFs, please define the value of n_vnf in topo_n_vnf.py and run topo_n_vnf.py instead of topo.py.

2. Please firstly run server.py inside the server's shell, then the rest. The default work mode is compute-and-forward (cf). With the flag sf on the client, the work mode will be changed to store-and-forward. With the flag data_id on the client, an integer value is expected to set the id of test data set. With the flag n_test on the client, an integer value is expected to set the evaluation rounds.

   # in the server terminal
   sudo python3 ./server.py
   
   # in the vnf terminal
   sudo python3 ./vnf.py
   
   # in the client terminal
   sudo python3 ./client.py cf data_id n_test

If you like our repository, please cite our papers.

``` 
@Article{wu2022picaextension,
    author  = {Wu, Huanzhuo and Shen, Yunbin and Xiao, Xun and Nguyen, Giang T. and Hecker, Artur and Fitzek, Frank H.-P.},
    title   = {Accelerating Industrial IoT Acoustic Data Separation with In-Network Computing},
    doi     = {10.1109/JIOT.2022.3176974},
    pages   = {1--15},
    groups  = {my_paper},
    journal = {IEEE Internet of Things Journal},
    year    = {2022},
    }
```

We are researchers at the Deutsche Telekom Chair of Communication Networks (ComNets) at TU Dresden, Germany. Our focus is on in-network computing.

• Huanzhuo Wu - [email protected] or [email protected]
• Yunbin Shen - [email protected] or [email protected]

This project is licensed under the MIT license.