{
  "id": "2307.11434",
  "version": "v1",
  "published": "2023-07-21T08:55:23.000Z",
  "updated": "2023-07-21T08:55:23.000Z",
  "title": "Batching for Green AI -- An Exploratory Study on Inference",
  "authors": [
    "Tim Yarally",
    "Luís Cruz",
    "Daniel Feitosa",
    "June Sallou",
    "Arie van Deursen"
  ],
  "comment": "8 pages, 4 figures, 1 table. Accepted at Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA) 2023",
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CV",
    "cs.SE"
  ],
  "abstract": "The batch size is an essential parameter to tune during the development of new neural networks. Amongst other quality indicators, it has a large degree of influence on the model's accuracy, generalisability, training times and parallelisability. This fact is generally known and commonly studied. However, during the application phase of a deep learning model, when the model is utilised by an end-user for inference, we find that there is a disregard for the potential benefits of introducing a batch size. In this study, we examine the effect of input batching on the energy consumption and response times of five fully-trained neural networks for computer vision that were considered state-of-the-art at the time of their publication. The results suggest that batching has a significant effect on both of these metrics. Furthermore, we present a timeline of the energy efficiency and accuracy of neural networks over the past decade. We find that in general, energy consumption rises at a much steeper pace than accuracy and question the necessity of this evolution. Additionally, we highlight one particular network, ShuffleNetV2(2018), that achieved a competitive performance for its time while maintaining a much lower energy consumption. Nevertheless, we highlight that the results are model dependent.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-07-21T08:55:23.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "exploratory study",
      "green ai",
      "neural networks",
      "energy consumption rises",
      "lower energy consumption"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}