Skip to content

Latest commit

 

History

History
45 lines (36 loc) · 1.67 KB

README.md

File metadata and controls

45 lines (36 loc) · 1.67 KB

Code supplementary for the CILP paper

CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing. IJCAI - 2022.

CILP Approach

We present a novel VM provisioner CILP in this paper that uses a Transformer based co-simulated imitation learner.

Quick Start Guide

To run the code, install required packages using

pip3 install matplotlib scikit-learn
pip3 install -r requirements.txt
pip3 install torch==1.7.1+cpu torchvision==0.8.2+cpu -f https://download.pytorch.org/whl/torch_stable.html

To run the code with the required provisioner and dataset use the following

python3 main.py --provisioner <provisioner> --workload <workload>

Here <provisioner> can be one of ACOARIMA, ACOLSTM, DecisionNN, SemiDirect, UAHS, Narya, CAHS, CILP_IL, CILP_Trans and CILP. Also, <workload> can be one of Azure2017, Azure2019 and Bitbrain.

Sample command:

python3 main.py --provisioner CILP --workload Azure2017

To run the code with the required scheduler, modify line 104 of main.py to one of the several options including LRMMTR, RF, RL, RM, Random, RLRMMTR, TMCR, TMMR, TMMTR, GA, GOBI.

Cite this work

Our work is published in IEEE TMSM journal. Cite using the following bibtex entry.

@article{tuli2023cilp,
  author={Tuli, Shreshth and Casale, Giuliano and Jennings, Nicholas R.},
  journal={IEEE Transactions on Network and Service Management}, 
  title={{CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing}}, 
  year={2023}
}

License

BSD-3-Clause. Copyright (c) 2023, Shreshth Tuli. All rights reserved.

See License file for more details.