{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:00:41Z","timestamp":1775073641316,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>The rapid growth of smart home technologies, driven by the expansion of the Internet of Things (IoT), has introduced both opportunities and challenges in automating daily routines and orchestrating device interactions. Traditional rule-based automation systems often fall short in adapting to dynamic conditions, integrating heterogeneous devices, and responding to evolving user needs. To address these limitations, this study introduces a novel smart home orchestration framework that combines generative Artificial Intelligence (AI), Retrieval-Augmented Generation (RAG), and the modular OSGi framework. The proposed system allows users to express requirements in natural language, which are then interpreted and transformed into executable service bundles by large language models (LLMs) enhanced with contextual knowledge retrieved from vector databases. These AI-generated service bundles are dynamically deployed via OSGi, enabling real-time service adaptation without system downtime. Manufacturer-provided device capabilities are seamlessly integrated into the orchestration pipeline, ensuring compatibility and extensibility. The framework was validated through multiple use-case scenarios involving dynamic device discovery, on-demand code generation, and adaptive orchestration based on user preferences. Results highlight the system\u2019s ability to enhance automation efficiency, personalization, and resilience. This work demonstrates the feasibility and advantages of AI-driven orchestration in realising intelligent, flexible, and scalable smart home environments.<\/jats:p>","DOI":"10.3390\/fi17050198","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:05:57Z","timestamp":1745989557000},"page":"198","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging Retrieval-Augmented Generation for Automated Smart Home Orchestration"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3861-1226","authenticated-orcid":false,"given":"Negin","family":"Jahanbakhsh","sequence":"first","affiliation":[{"name":"ETSIS de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Calle Nikola Tesla S\/N, 28038 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4506-6284","authenticated-orcid":false,"given":"Mario","family":"Vega-Barbas","sequence":"additional","affiliation":[{"name":"ETSIS de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Calle Nikola Tesla S\/N, 28038 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1183-4401","authenticated-orcid":false,"given":"Iv\u00e1n","family":"Pau","sequence":"additional","affiliation":[{"name":"ETSIS de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Calle Nikola Tesla S\/N, 28038 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5423-7627","authenticated-orcid":false,"given":"Lucas","family":"Elvira-Mart\u00edn","sequence":"additional","affiliation":[{"name":"ETSIS de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Calle Nikola Tesla S\/N, 28038 Madrid, Spain"}]},{"given":"Hirad","family":"Moosavi","sequence":"additional","affiliation":[{"name":"ETSIS de Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Calle Nikola Tesla S\/N, 28038 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0830-6621","authenticated-orcid":false,"given":"Carolina","family":"Garc\u00eda-V\u00e1zquez","sequence":"additional","affiliation":[{"name":"Facultad de Dise\u00f1o y Tecnolog\u00eda, University of Design, Innovation and Technology, 28016 Madrid, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"ref_1","unstructured":"Rajuroy, A., Johnson Mary, B., and Liang, W. (2025, April 01). Personalized Smart Home Environment Management Using Context-Aware Reinforcement Learning. Available online: https:\/\/www.researchgate.net\/publication\/387820872_Personalized_Smart_Home_Environment_Management_Using_Context-Aware_Reinforcement_Learning."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TCE.2007.339507","article-title":"Enhancing Residential Gateways: OSGi Service Composition","volume":"53","author":"Redondo","year":"2007","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_3","first-page":"91","article-title":"Internet of robotic things\u2013converging sensing\/actuating, hyperconnectivity, artificial intelligence and IoT platforms","volume":"Volume 4","author":"Vermesan","year":"2022","journal-title":"Internet of Things: The Call of the Edge"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Anik, S.M.H., Gao, R., Zhong, H., Wang, X., and Meng, N. (2024). Automation Configuration in Smart Home Systems: Challenges and Opportunities. arXiv.","DOI":"10.1145\/3731450"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mouine, M., and Saied, M.A. (2022, January 10\u201316). Event-Driven Approach for Monitoring and Orchestration of Cloud and Edge-Enabled IoT Systems. Proceedings of the IEEE International Conference on Cloud Computing, Barcelona, Spain.","DOI":"10.1109\/CLOUD55607.2022.00049"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4485","DOI":"10.1007\/s12652-019-01572-z","article-title":"Smart Home Reasoning Systems: A Systematic Literature Review","volume":"12","author":"Mekuria","year":"2021","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rahimi, H., Trentin, I.F., Boissier, O., and Ramparany, F. (2021). SMASH: A Semantic-enabled Multi-agent Approach for Self-adaptation of Human-centered IoT. arXiv.","DOI":"10.1007\/978-3-030-85739-4_17"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.techfore.2018.08.015","article-title":"A Systematic Review of the Smart Home Literature: A User Perspective","volume":"138","author":"Papagiannidis","year":"2019","journal-title":"Technol. Forecast. Soc. Change"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ghai, A.S., Rawat, V., Gupta, V.K., and Ghai, K. (2024, January 29\u201331). Artificial Intelligence in System and Software Engineering for Auto Code Generation. Proceedings of the 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT), Greater Noida, India.","DOI":"10.1109\/ICEECT61758.2024.10738945"},{"key":"ref_10","unstructured":"Kanewala, T.A. (2014). Strategies and Tradeoffs in Designing and Implementing Embedded DSLs. [Ph.D. Thesis, Indiana University]."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhong, L., and Wang, Z. (2024, January 20\u201327). Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i19.30185"},{"key":"ref_12","unstructured":"Sevenhuijsen, M., Etemadi, K., and Nyberg, M. (2024). VeCoGen: Automating Generation of Formally Verified C Code with Large Language Models. arXiv."},{"key":"ref_13","unstructured":"Ramachandran, A. (2025, April 01). Advancing Retrieval-Augmented Generation (RAG): Innovations, Challenges, and the Future of AI Reasoning. Available online: https:\/\/www.researchgate.net\/publication\/388722115_Advancing_Retrieval-Augmented_Generation_RAG_Innovations_Challenges_and_the_Future_of_AI_Reasoning."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Almutairi, R., Bergami, G., and Morgan, G. (2024). Advancements and Challenges in IoT Simulators: A Comprehensive Review. Sensors, 24.","DOI":"10.3390\/s24051511"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.dcan.2022.10.016","article-title":"A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications","volume":"10","author":"Nayak","year":"2024","journal-title":"Digit. Commun. Netw."},{"key":"ref_16","unstructured":"Hall, R.S., and Cervantes, H. (2004, January 5\u20138). An OSGi Implementation and Experience Report. Proceedings of the IEEE Consumer Communications and Networking Conference (CCNC 2004), Las Vegas, NV, USA."},{"key":"ref_17","unstructured":"(2024, December 21). OSGi Modularity and Services-Tutorial. Available online: https:\/\/www.vogella.com\/tutorials\/OSGi\/article.html."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"12418","DOI":"10.1016\/j.eswa.2012.04.077","article-title":"OSGi-based smart home architecture for heterogeneous network","volume":"39","author":"Cheng","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_19","first-page":"1","article-title":"Challenges in Integration of Heterogeneous Internet of Things","volume":"2022","author":"Noaman","year":"2022","journal-title":"Sci. Program."},{"key":"ref_20","first-page":"102","article-title":"Unveiling security, privacy, and ethical concerns of ChatGPT","volume":"2","author":"Wu","year":"2024","journal-title":"J. Intell. Inf."},{"key":"ref_21","unstructured":"Gama, K., and Donsez, D. (2024, October 12). A Survey on Approaches for Addressing Dependability Attributes in the OSGi Service Platform. Available online: https:\/\/www.researchgate.net\/figure\/Basic-Service-Oriented-Architecture-In-the-case-of-OSGi-the-binding-establishes-a_fig1_220630771."},{"key":"ref_22","unstructured":"MQTT (2024, April 01). The Standard for IoT Messaging. Available online: https:\/\/mqtt.org\/."},{"key":"ref_23","unstructured":"Pinecone Docs (2024, August 02). The Vector Database to Build Knowledgeable AI: Pinecone. Available online: https:\/\/docs.pinecone.io\/guides\/get-started\/overview."},{"key":"ref_24","unstructured":"(2024, November 14). Pretrained Models-Sentence Transformers Documentation. Available online: https:\/\/www.sbert.net\/docs\/sentence_transformer\/pretrained_models.html."},{"key":"ref_25","unstructured":"(2024, July 15). Apache Felix OSGi Tutorial: Apache Felix. Available online: https:\/\/felix.apache.org\/documentation\/tutorials-examples-and-presentations\/apache-felix-osgi-tutorial.html."},{"key":"ref_26","unstructured":"OSGi Working Group (2024, June 09). Getting Started with OSGi: The Eclipse Foundation. Available online: https:\/\/www.osgi.org\/resources\/where-to-start\/."},{"key":"ref_27","unstructured":"OpenAI (2024, October 16). API Platform|The Most Powerful Platform for Building AI Products. Available online: https:\/\/openai.com\/api."},{"key":"ref_28","unstructured":"(2024, June 01). Maven Repository: Search\/Browse\/Explore. Available online: https:\/\/mvnrepository.com\/."},{"key":"ref_29","unstructured":"Bndtools (2024, May 20). OSGi Starter. Available online: https:\/\/bndtools.org\/workspace\/osgi-starter.html."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/5\/198\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:24:33Z","timestamp":1760030673000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/5\/198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["fi17050198"],"URL":"https:\/\/doi.org\/10.3390\/fi17050198","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]}}}