A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)
Open accessThe DOI matches its Crossref record; 102 of the 102 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence (Al) models are being produced and used to solve a variety of current and future business and technical problems. Therefore, AI model engineering processes, platforms, and products are acquiring special significance across industry verticals. For achieving deeper automation, the number of data features being used while generating highly promising and productive AI models is numerous, and hence the resulting AI models are bulky. Such heavyweight models consume a lot of computation, storage, networking, and energy resources. On the other side, increasingly, AI models are being deployed in IoT devices to ensure real-time knowledge discovery and dissemination. Real-time insights are of paramount importance in producing and releasing real-time and intelligent services and applications. Thus, edge intelligence through on-device data processing has laid down a stimulating foundation for real-time intelligent enterprises and environments. With these emerging requirements, the focus turned towards unearthing competent and cognitive techniques for maximally compressing huge AI models without sacrificing AI model performance. Therefore, AI researchers have come up with a number of powerful optimization techniques and tools to optimize AI models. This paper is to dig deep and describe all kinds of model optimization at different levels and layers. Having learned the optimization methods, this work has highlighted the importance of having an enabling AI model optimization framework.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Better Privacy/Security: Edge computing can assist in increasing confidentiality and security by lowering the quantity of information that has to be transferred over the Internet and by offering more command over the processes and storage of confidential documents [164].”
From Edge AI: A survey (2023) · cites this paper as [164]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The upshot of this is improved uptime and dependability for AI applications that are essential to business operations [164].”
From Edge AI: A survey (2023) · cites this paper as [164]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Edge AI has the potential to revolutionize industries by enabling intelligent and autonomous devices that can make real-time decisions based on sensor data [164].”
From Edge AI: A survey (2023) · cites this paper as [164]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
Deng, L. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2211477 · Cited by 4,836
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215 · cited 1×
“So, the system has to access off-chip DRAM access which has latency and energy requirements higher than other computer operations [78].”
BackgroundChannel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647 · cited 1×
“So, filter pruning and channel pruning [48] are correlated [49].”
BackgroundEdge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
Luo, J.-H., Wu, J., & Lin, W. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.541 · Cited by 1,832
Automated Machine Learning: Methods, Systems, Challenges
(2019) · The Springer Series on Challenges in Machine Learning · doi:10.1007/978-3-030-05318-5 · Cited by 1,485
Research works printed but not linked: 8
- Hsu T.M.-H. Qi H. Brown M. Measuring the effects of nonidentical data distribution for federated visual classification arXiv 2019 1909.06335
- Yu F. Zhang W. Qin Z. Xu Z. Wang D. Liu C. Tian Z. Chen X. Heterogeneous Federated Learning arXiv 2020 10.48550/arXiv.2008.06767 2008.06767 · DOI
- Li D. Wang J. FedMD: Heterogenous federated learning via model distillation arXiv 2019 1910.03581
- Denil M. Shakibi B. Dinh L. Ranzato M.A. de Freitas N. Predicting Parameters in Deep Learning Advances in Neural Information Processing Systems 26 (NIPS 2013), Proceedings of the Advances in Neural Information Processing Systems 26 (NIPS 2013), Lake Tahou, NV, USA, 5–10 December 2013 Burges C.J. Bottou L. Welling M. Ghahramani Z. Weinberger K.Q. Curran Associates Inc. Red Hook, NY, USA 2013 9781632660244
- Van Leeuwen J. On the construction of huffman trees Proceedings of the Third International Colloquium on Automata, Languages and Programming Edinburgh, UK 20–23 July 1976 382 410
- Sun X. Wang N. Chen C.-y. Ni J.-M. Agrawal A. Cui X. Venkataramani S. El Maghraoui K. Srinivasan V. Gopalakrishnan K. Ultra-low precision 4-bit training of deep neural networks Proceedings of the 34th International Conference on Neural Information Processing Systems Vancouver, BC, Canada 6–12 December 2020 1796 1807
- Alkadhmawee A.A. Lu S. AlShawi S.I. An energy-efficient heuristic based routing protocol in wireless sensor networks Int. J. Innov. Res. Inf. Secur. 2016 3 5 9
- Pleiss G. Chen D. Huang G. Li T. van der Maaten L. Kilian Weinberger Q. Memory-Efficient Implementation of DenseNets arXiv 2017 1707.06990
Cited by
Items 101–161 of 161
A study on Social Empowerment of AI for Revolutionizing Humankind
Vijayeeta, P., Pattnayak, P., & Mohanty, K. (2023) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit59427.2023.10431326
Edge AI in Cloud Computing for Sustainable Development
Dhibar, K., Maji, P., Mondal, H. K., & Parbat, G. (2023) · Advances in environmental engineering and green technologies book series · doi:10.4018/979-8-3693-0338-2.ch009
Explorando redes neurais e engenharia do conhecimento uma revisão narrativa
Weber, L. (2024) · Cadernos do IME - Série Informática · doi:10.12957/cadinf.2024.81290 · Cited by 1
Limited Resources Usage of Deep-Learning-Based IoT Devices in Healthcare
Gao, X., He, P., Zhou, Y. X., & Qin, X. (2024) · International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings) · doi:10.1109/aibthings63359.2024.10863456
Jacob, J. (2025) · Global Journal of Engineering and Technology Advances · doi:10.30574/gjeta.2025.23.1.0117
Trends, Challenges and New Frontiers of Artificial Intelligence
Chaudhuri, P. P., Dutta, A., Choudhury, S. P., Chowdhury, D. R., & Hazari, R. (2025) · Springer eBooks · doi:10.1007/978-981-96-1501-8_2
The Role of Artificial Intelligence in Enhancing Performance and Power Control of Embedded Systems
Patel, P. K. (2025) · European Journal of Computer Science and Information Technology · doi:10.37745/ejcsit.2013/vol13n327587
EMERGING TRENDS IN AI: A CROSSROADS FOR HUMANITY
Jaglan, R. (2025) · International Journal of Advanced Research in Computer Science · doi:10.26483/ijarcs.v16i3.7287
Utilizando visão computacional para avaliação equitativa de propriedades em áreas urbanas
Landim, N. M. D., Araujo, H. X., Carneiro, L. D. A., & Barbosa, G. V. (2025) · Research Society and Development · doi:10.33448/rsd-v14i7.48995
Sebti, M. R., Dakhia, Z., Macheda, A., Iero, D., Russo, M., & Merenda, M. (2025) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech65624.2025.11091749
Selecting Storage Infrastructure for Distinct Stages of the AI Machine-Learning Pipeline
Aggarwal, M. (2025) · International journal of latest research in engineering and technology. · doi:10.56581/ijlret.11.07.02-16
Efficient Adversarial Detection Frameworks for Vehicle-to-Microgrid Services in Edge Computing
Omara, A., & Kantarcı, B. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162172
Song, D.-I., Bang, W.-C., Shon, M. S., & the Korean Orthopaedic Ultrasound Society (KOUS) (2025) · The Journal of the Korean Orthopaedic Association · doi:10.4055/jkoa.2025.60.3.115
A Survey on Microprocessors Optimization Techniques for AI Tasks on Edge Devices
AlMudaweb, Z., & Ramadan, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00329-4_51
Hagag, M. M. (2025) · Journal of Communication Sciences and Information Technology · doi:10.21608/jcsit.2025.438575.1022
Energy Analysis of Row-Stationary Dataflow in CNN Computation on Microcontrollers
Koppala, M. R. (2024) · Qucosa - Monarch (Chemnitz University of Technology) · doi:10.60687/2025-0048
Tekoäly ja kestävä kehitys: kirjallisuuskatsaus suurten kielimallien ympäristövaikutuksista
Kosunen, M. (2025) · Theseus (Ammattikorkeakoulujen)
van der Noort, R. (. (2024) · Research Repository (Delft University of Technology) · Cited by 1
Düzbastılar, F. O., & Ceyhan, T. (2025) · Turkish Journal of Fisheries and Aquatic Sciences · doi:10.4194/trjfas27583
Diagnóstico predictivo de motores eléctricos basado en TinyML y análisis de firma de corriente
Delgado, G. B., Delgado, J. B., & Rosales, M. A. F. (2025) · Revista de Investigación en Tecnologías de la Información · doi:10.36825/riti.13.30.006
Optimizing AI Algorithms for Green AI: A Literature Review
Miftah, A. (2026) · المجلة الدولية للعلوم الهندسية وتقنية المعلومات. · doi:10.36602/ijeit.v15i1.812
Adaptive ML-Enabled Edge-Cloud System Framework for Safe and Efficient Autonomous Systems
Cho, E., & Ko, I.-Y. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-11233-0_1
Garg, R., & Kumar, S. (2026) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70345
Fast and Resource-Aware Implementation of Recurrent Neural Network Accelerators on FPGAs
Xaviour, T., & Wang, X. (2025) · doi:10.1109/icm66518.2025.11322468
ByteShield: A Cybersecurity Aware AI Co-Inference Architecture for Edge Cloud Systems
Tibrewala, A. (2025) · IEEE International Conference on Cyber Security and Cloud Computing / IEEE International Conference on Edge Computing and Scalable Cloud (CSCloud/EdgeCom) · doi:10.1109/edgecom66327.2025.00024
An Adaptive Traffic Control System using Combined ML and DL Techniques for City Intersections
Lalitha, R., Manoja, S., Deepika, D., Eshwar, E., & Lathifbasha, L. (2025) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca66444.2025.11382565
Wu, Y., & Guo, Y. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-08486-4 · Cited by 1
Large model–driven edge-cloud collaboration for next-gen animation systems
Wang, C., Zhu, J., & Huang, W.-J. (2026) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-026-00870-0 · Cited by 1
Assessing the potential of LLMs for optimizing SCL-based PLC programs in industrial motion control
Vámos, A. A., Kővári, A., & Kertész, G. (2026) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami68106.2026.11420762
Saha, S., Lilhore, U. K., & Simaiya, S. (2026) · De Gruyter eBooks · doi:10.1515/9783112214374-010
Tyagi, P., Gautam, A., & Mittal, S. (2026) · International Conference on VLSI Design · doi:10.1109/vlsid68508.2026.00015
Yang, X., Wei, A., & Wang, Z. (2025) · IEEE International Conference of Safe Production and Informatization (IICSPI) · doi:10.1109/iicspi66775.2025.11437951
TRU-Net Based AI Model Implementation by Pure C for Real-time Speech Enhancement
Lee, Y., Kim, M., & Park, D. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454348
Robocasting of graphene reinforced biphasic calcium phosphate cement for Bone Tissue Engineering
Roedel, S. G. (2025) · theses.fr (ABES) · doi:10.70675/8636fd08z0c5ez4d6bzbcfbz5553dbdd8b26
Nie, T., Yang, D., Guo, X., Zhu, W., & Su, B. (2026) · Future Internet · doi:10.3390/fi18050242
AI in Your Pocket: The Revolution of On-Device Artificial Intelligence
Saxena, A. (2026) · Synthesis lectures on computer science · doi:10.1007/978-3-032-18322-4_1
Real-Time Threat Detection and AI-Driven Intrusion Prevention Systems
Tripathi, A., Upadhyay, P., & Goel, P. K. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1498-1.ch008
Timing-Constrained Composable Inference for Intermittent Systems Using Reinforcement Learning
Lim, W. S., Cheng, S.-T., Tsai, Y.-T., Tu, C.-H., & Chang, Y.-H. (2026) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3814956
EdgeSense: A Hybrid TinyML and Deep Learning Framework for SNR-Aware Adaptive Data Rate in LoRaWAN
Lodhi, M. A., Sun, X., Mahmood, K., & Lodhi, A. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3695916
Design and Optimization of Low-Power AI Accelerators for Edge Devices
Harshitha, L., B, L. R. U., Vaishnavi, Y., R, J. H., Bindu, S., & Rekha, P. (2026) · International Conference on Knowledge Engineering and Communication Systems (ICKECS) · doi:10.1109/ickecs70176.2026.11527502
Incident Response Planning and Real-Time Event Correlation
Olasehan, O. A. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4581-9.ch003
AI-Driven Adaptive Block Size Optimization for Enhanced Blockchain Network Performance
Kumar, K. (2026) · International Conference on Innovations in Computational Intelligence (ICICI) · doi:10.1109/icici68867.2026.11564849
Esnaola, L., Ramón, H. D., & Lanzarini, L. C. (2026) · El Servicio de Difusión de la Creación Intelectual (National University of La Plata)
Senapati, A., Pattnaik, A., Jena, S. P., & Chakravarty, S. (2026) · International Conference on Computing, Communication and Green Engineering (CCGE) · doi:10.1109/ccge67142.2026.11581889
A reconfigurable adder for an efficient MAC in DNNs applications on edge device
Sharma, J., Maurya, A., Jha, K. K., & Singh, D. (2026) · Concurrent Engineering · doi:10.1177/1063293x261464844
DynaHyEdge: Fine-Grained Privacy-Aware Online Scheduling for Hybrid Edge Services
Cheng, Z.-C., Liao, H.-L., Luo, L.-L., & Ren, B. (2026) · Journal of Computer Science and Technology · doi:10.1007/s11390-025-5695-2
Energy-Efficient Intrusion Detection in IoT Using TinyLSTM and Edge AI
Xavier, S. B., Kathrine, G. J. W., & George, R. M. (2026) · Algorithms for intelligent systems · doi:10.1007/978-3-032-12243-8_9
Islam, M. A., Rahman, M. M., & Chowdhury, M. M. H. (2026) · Scientia. Technology, science and society. · doi:10.59324/stss.2026.3(8).04
Tunnel Eye : AI Based Visual Inspection For Refinery Pipelines
WATTAMWAR, P. J. W. P. J. (2026) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem66552
AI–IoT-Enabled Microclimate Regulation: Designing Climate-Resilient Parks and Plazas
Shafique, A., Tahir, M., & Tyagi, S. (2026) · Urban sustainability · doi:10.1007/978-981-92-1011-4_9
Wu, X., Tao, X., cheng, Y., & Wang, Z. (2026) · Scientific Reports · doi:10.1038/s41598-026-74348-z
Edge-Native Data-Aware Runtime Systems for Distributed AI: Bridging HPC and Edge Workloads
Hendricks, A. (2026) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw71298.2026.00084
Nicose, K., Sukhadeve, S., & Jakkanwar, M. (2026) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-026-00387-1
Almajali, Z. S. (2026) · Clean Energy Science and Technology · doi:10.18686/cest822
A Model for Generating Real Stream Data in Simulated Edge Computing Environments
Xiu, W., Johar, M. G. M., Alkawaz, M. H., & Bian, C. (2026) · Computing and Informatics · doi:10.31577/cai_2026_3_668
Artificial intelligence for power optimization in bluetooth low energy wearables: a narrative review
Al-Neami, A. Q., Hussein, A. F., Aboud, W. S., Alnaimi, F. B. I., & Shurafa, S. M. A. (2026) · Wireless Networks · doi:10.1007/s11276-026-04208-1
EDGE AI: Leveraging Artificial Intelligence in Edge Computing
Labdo, A. U., Pal, B. L., Shah, A. F., Madori, F. I., Azare, Z. Y., & Ubawaru, A. B. (2026) · International journal of recent engineering research and development. · doi:10.56581/ijrerd.11.05.17-24
Liu, H. (2026) · International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC) · doi:10.1109/icdscnc70670.2026.11746385
SDM: A Variation-Tolerant Soft Decision Machine with In-Memory Sigmoid Computation
Wen, B., Xu, Z., Ren, P., Gao, G., Hu, X. S., & Li, C. (2026) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3770743.3804134
IMN-EAI: An Ultra-Low-Power In-Memory Neuromorphic VLSI Architecture for Real-Time Edge AI
Bharathidasan, N., Begum, M. B., P.Vijayakumar, Krishnan, A. S., Artheeswari, B., & Gowtham, V. (2026) · doi:10.1109/worldsuas70880.2026.11766777
Metadata
- Authors
- Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., & Hewage, C.
- Affiliations
- Bharathidasan University (IN)
- Cardiff Metropolitan University (GB)
- Edge AI Division, Reliance Jio Platforms Ltd., Bangalore 560103, Karnataka, India
- University for the Creative Arts (GB)
- Corresponding author
- Surianarayanan, Chellammal
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-01-22
- Volume
- 23
- Issue
- 3
- Pages
- 1279
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9919555
- OpenAlex
- W4317727238
- Cited by
- 131
- References
- 95
- Citations by year
- 2026: 46 · 2025: 43 · 2024: 25 · 2023: 17
- FWCI
- 3.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge AI, model compression, lightweight AI models, IoT devices, on-device processing, real-time inference, optimization framework, energy efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.