# EPAM: A Predictive Energy Model for Mobile AI

arXiv: https://arxiv.org/abs/2303.01509 · HTML: https://mlsanity.com/paper/2303.01509/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [SqueezeBERT: What can computer vision teach NLP about efficient neural networks?](https://mlsanity.com/paper/2006.11316/) (2020)
- [Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices](https://mlsanity.com/paper/2005.05085/) (2020)
- [Towards Accurate and Reliable Energy Measurement of NLP Models](https://mlsanity.com/paper/2010.05248/) (2020)
- [LEAF + AIO: Edge-Assisted Energy-Aware Object Detection for Mobile Augmented Reality](https://mlsanity.com/paper/2205.13770/) (2022)
- [Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications](https://mlsanity.com/paper/2011.13075/) (2020)

## Built on by (most cited first, 4 of 4)

- [Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices](https://mlsanity.com/paper/2310.18329/) (2023)
- [lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models](https://mlsanity.com/paper/2510.06126/) (2025)
- [PlatformX: An End-to-End Transferable Platform for Energy-Efficient Neural Architecture Search](https://mlsanity.com/paper/2510.08993/) (2025)
- [A Performance Analysis Modeling Framework for Extended Reality Applications in Edge-Assisted Wireless Networks](https://mlsanity.com/paper/2405.07033/) (2024)

## Abstract (arXiv)

Artificial intelligence (AI) has enabled a new paradigm of smart applications -- changing our way of living entirely. Many of these AI-enabled applications have very stringent latency requirements, especially for applications on mobile devices (e.g., smartphones, wearable devices, and vehicles). Hence, smaller and quantized deep neural network (DNN) models are developed for mobile devices, which provide faster and more energy-efficient computation for mobile AI applications. However, how AI models consume energy in a mobile device is still unexplored. Predicting the energy consumption of these models, along with their different applications, such as vision and non-vision, requires a thorough investigation of their behavior using various processing sources. In this paper, we introduce a comprehensive study of mobile AI applications considering different DNN models and processing sources, focusing on computational resource utilization, delay, and energy consumption. We measure the latency, energy consumption, and memory usage of all the models using four processing sources through extensive experiments. We explain the challenges in such investigations and how we propose to overcome them. Our study highlights important insights, such as how mobile AI behaves in different applications (vision and non-vision) using CPU, GPU, and NNAPI. Finally, we propose a novel Gaussian process regression-based general predictive energy model based on DNN structures, computation resources, and processors, which can predict the energy for each complete application cycle irrespective of device configuration and application. This study provides crucial facts and an energy prediction mechanism to the AI research community to help bring energy efficiency to mobile AI applications.