{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:29:09Z","timestamp":1776680949273,"version":"3.51.2"},"reference-count":35,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100015812","name":"Universidad Militar Nueva Granada\u2014Vicerrector\u00eda de investigaciones","doi-asserted-by":"publisher","award":["INV-ING-3947"],"award-info":[{"award-number":["INV-ING-3947"]}],"id":[{"id":"10.13039\/501100015812","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Currently, various pruning strategies including different methods and distribution types are commonly used to reduce the number of FLOPs and parameters in deep learning models. However, their impact on actual energy savings remains insufficiently studied, particularly in resource-constrained settings. To address this, we introduce PruneEnergyAnalyzer, an open-source Python tool designed to evaluate the energy efficiency of pruned models. Starting from the unpruned model, the tool calculates the energy savings achieved by pruned versions provided by the user, and generates comparative visualizations based on previously applied pruning hyperparameters such as method, distribution type (PD), compression ratio (CR), and batch size. These visual outputs enable the identification of the most favorable pruning configurations in terms of FLOPs, parameter count, and energy consumption. As a demonstration, we evaluated the tool with 180 models generated from three architectures, five pruning distributions, three pruning methods, and four batch sizes, using another previous library (e.g. FlexiPrune). This experiment revealed the significant impact of the network architecture on Energy Reduction, the non-linearity between FLOPs savings and energy savings, as well as between parameter reduction and energy efficiency. It also showed that the batch size strongly influences the energy consumption of the pruned model. Therefore, this tool can support researchers in making pruning policy decisions that also take into account the energy efficiency of the pruned model.<\/jats:p>","DOI":"10.3390\/bdcc9080200","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T08:51:41Z","timestamp":1754038301000},"page":"200","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PruneEnergyAnalyzer: An Open-Source Toolkit for Evaluating Energy Consumption in Pruned Deep Learning Models"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8899-8298","authenticated-orcid":false,"given":"Cesar","family":"Pachon","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Universidad Militar Nueva Granada, Bogota 110111, Colombia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6687-1429","authenticated-orcid":false,"given":"Cesar","family":"Pedraza","sequence":"additional","affiliation":[{"name":"Department of Systems and Industrial Engineering, Universidad Nacional de Colombia, Bogota 111321, Colombia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3864-818X","authenticated-orcid":false,"given":"Dora","family":"Ballesteros","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Universidad Militar Nueva Granada, Bogota 110111, Colombia"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s44163-024-00118-3","article-title":"AI: The Future of Humanity","volume":"4","author":"Rawas","year":"2024","journal-title":"Discov. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100277","DOI":"10.1016\/j.hybadv.2024.100277","article-title":"AI revolutionizing industries worldwide: A comprehensive overview of its diverse applications","volume":"7","author":"Rashid","year":"2024","journal-title":"Hybrid Adv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., and Swart, T.G. (2024). A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications. Information, 15.","DOI":"10.3390\/info15120755"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"122666","DOI":"10.1016\/j.eswa.2023.122666","article-title":"A comprehensive survey on applications of transformers for deep learning tasks","volume":"241","author":"Islam","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ersavas, T., Smith, M.A., and Mattick, J.S. (2024). Novel applications of Convolutional Neural Networks in the age of Transformers. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-60709-z"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Alwakid, G., Gouda, W., Humayun, M., and Sama, N.U. (2022). Melanoma Detection Using Deep Learning-Based Classifications. Healthcare, 10.","DOI":"10.3390\/healthcare10122481"},{"key":"ref_8","first-page":"100164","article-title":"Autonomous Driving Architectures: Insights of Machine Learning and Deep Learning Algorithms","volume":"6","author":"Bachute","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"108998","DOI":"10.1016\/j.engappai.2024.108998","article-title":"An embedded end-to-end voice assistant","volume":"136","author":"Lazzaroni","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6017","DOI":"10.1109\/ACCESS.2023.3349022","article-title":"A Systematic Analysis of Enhancing Cyber Security Using Deep Learning for Cyber Physical Systems","volume":"12","author":"Gaba","year":"2024","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wermelinger, M. (2023, January 15\u201318). Using GitHub Copilot to Solve Simple Programming Problems. Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1, New York, NY, USA. SIGCSE 2023.","DOI":"10.1145\/3545945.3569830"},{"key":"ref_12","unstructured":"PyTorch Team (2025, February 06). Deep Learning Energy Measurement and Optimization | PyTorch. Available online: https:\/\/pytorch.org\/blog\/zeus\/."},{"key":"ref_13","unstructured":"Hamilton, J. (2025, July 27). Data Center and Cloud Innovation. Keynote at CIDR 2024. Available online: https:\/\/mvdirona.com\/jrh\/talksandpapers\/JamesHamiltonCIDR2024.pdf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Alizadeh, N., and Castor, F. (2024, January 14\u201315). Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures. Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering\u2013Software Engineering for AI, New York, NY, USA. CAIN \u201924.","DOI":"10.1145\/3644815.3644967"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Martinez, M. (2024). The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines. arXiv.","DOI":"10.1145\/3696630.3728704"},{"key":"ref_16","first-page":"886","article-title":"Learning Low Resource Consumption CNN Through Pruning and Quantization","volume":"10","author":"Qi","year":"2022","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/TSUSC.2021.3060690","article-title":"AdaPrune: An Accelerator-Aware Pruning Technique for Sustainable CNN Accelerators","volume":"7","author":"Li","year":"2022","journal-title":"IEEE Trans. Sustain. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"40439","DOI":"10.1109\/ACCESS.2024.3371251","article-title":"Deployment of Machine Learning Algorithms on Resource-Constrained Hardware Platforms for Prosthetics","volume":"12","author":"Just","year":"2024","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"36055","DOI":"10.1109\/ACCESS.2024.3367002","article-title":"Pruning with Scaled Policy Constraints for Light-Weight Reinforcement Learning","volume":"12","author":"Park","year":"2024","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"109558","DOI":"10.1016\/j.asoc.2022.109558","article-title":"SeNPIS: Sequential Network Pruning by class-wise Importance Score","volume":"129","author":"Ballesteros","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"115041","DOI":"10.1109\/ACCESS.2020.3003810","article-title":"Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-Rays","volume":"8","author":"Rajaraman","year":"2020","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4269","DOI":"10.1109\/TAI.2024.3366497","article-title":"Distilled Gradual Pruning with Pruned Fine-Tuning","volume":"5","author":"Fontana","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, T.J., Chen, Y.H., Emer, J., and Sze, V. (2017\u20131, January 29). A method to estimate the energy consumption of deep neural networks. Proceedings of the 2017 51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/ACSSC.2017.8335698"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yang, T.J., Chen, Y.H., and Sze, V. (2017, January 21\u201326). Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107606","DOI":"10.1016\/j.future.2024.107606","article-title":"Reducing inference energy consumption using dual complementary CNNs","volume":"165","author":"Kinnas","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"25865","DOI":"10.1364\/OE.495425","article-title":"Implementation of energy-efficient convolutional neural networks based on kernel-pruned silicon photonics","volume":"31","author":"Huang","year":"2023","journal-title":"Opt. Express"},{"key":"ref_27","unstructured":"Zhang, Q., Zhang, R., Sun, J., and Liu, Y. (2023). How Sparse Can We Prune A Deep Network: A Fundamental Limit Viewpoint. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pachon, C.G., Pinzon-Arenas, J.O., and Ballesteros, D. (2024). Pruning Policy for Image Classification Problems Based on Deep Learning. Informatics, 11.","DOI":"10.3390\/informatics11030067"},{"key":"ref_29","first-page":"195","article-title":"Principled Pruning of Bayesian Neural Networks Through Variational Free Energy Minimization","volume":"5","author":"Beckers","year":"2024","journal-title":"IEEE Open J. Signal Process."},{"key":"ref_30","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Goel, A., Tung, C., Lu, Y.H., and Thiruvathukal, G.K. (2020, January 2\u201316). A Survey of Methods for Low-Power Deep Learning and Computer Vision. Proceedings of the 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), New Orleans, LA, USA.","DOI":"10.1109\/WF-IoT48130.2020.9221198"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.neucom.2021.07.045","article-title":"Pruning and quantization for deep neural network acceleration: A survey","volume":"461","author":"Liang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_33","unstructured":"Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"101858","DOI":"10.1016\/j.softx.2024.101858","article-title":"FlexiPrune: A Pytorch tool for flexible CNN pruning policy selection","volume":"27","author":"Pachon","year":"2024","journal-title":"SoftwareX"},{"key":"ref_35","unstructured":"Pachon Suescun, C.G., Ballesteros L, D.M., and Pedraza, C. (2025, July 27). PruneEnergyAnalizer. Available online: https:\/\/data.mendeley.com\/datasets\/cc2cd723hb\/1."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/8\/200\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:20:53Z","timestamp":1760034053000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/8\/200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["bdcc9080200"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9080200","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,1]]}}}