{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:47:50Z","timestamp":1769042870251,"version":"3.49.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T00:00:00Z","timestamp":1694217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF Career","award":["2114499"],"award-info":[{"award-number":["2114499"]}]},{"name":"NSF Ascent","award":["2132904"],"award-info":[{"award-number":["2132904"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>Continuous monitoring of areas nearby the electric grid is critical for preventing and early detection of devastating wildfires. Existing wildfire monitoring systems are intermittent and oblivious to local ambient risk factors, resulting in poor wildfire awareness. Ambient sensor suites deployed near the gridlines can increase the monitoring granularity and detection accuracy. However, these sensors must address two challenging and competing objectives at the same time. First, they must remain powered for years without manual maintenance due to their remote locations. Second, they must provide and transmit reliable information if and when a wildfire starts. The first objective requires aggressive energy savings and ambient energy harvesting, while the second requires continuous operation of a range of sensors. To the best of our knowledge, this paper presents the first self-sustained cyber-physical system that dynamically co-optimizes the wildfire detection accuracy and active time of sensors. The proposed approach employs reinforcement learning to train a policy that controls the sensor operations as a function of the environment (i.e., current sensor readings), harvested energy, and battery level. The proposed cyber-physical system is evaluated extensively using real-life temperature, wind, and solar energy harvesting datasets and an open-source wildfire simulator. In long-term (5 years) evaluations, the proposed framework achieves 89% uptime, which is 46% higher than a carefully tuned heuristic approach. At the same time, it averages a 2-minute initial response time, which is at least 2.5\u00d7 faster than the same heuristic approach. Furthermore, the policy network consumes 0.6 mJ per day on the TI CC2652R microcontroller using TensorFlow Lite for Micro, which is negligible compared to the daily sensor suite energy consumption.<\/jats:p>","DOI":"10.1145\/3608100","type":"journal-article","created":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T13:33:18Z","timestamp":1694266398000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["A Self-Sustained CPS Design for Reliable Wildfire Monitoring"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5943-0230","authenticated-orcid":false,"given":"Yigit","family":"Tuncel","sequence":"first","affiliation":[{"name":"University of Wisconsin - Madison, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9312-236X","authenticated-orcid":false,"given":"Toygun","family":"Basaklar","sequence":"additional","affiliation":[{"name":"University of Wisconsin - Madison, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1264-5730","authenticated-orcid":false,"given":"Dina","family":"Carpenter-Graffy","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5045-5535","authenticated-orcid":false,"given":"Umit","family":"Ogras","sequence":"additional","affiliation":[{"name":"University of Wisconsin - Madison, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,9,9]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2019.01.004"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2018.2801725"},{"issue":"8","key":"e_1_3_2_4_2","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.3390\/rs14081874","article-title":"Earth observation mission of a 6U CubeSat with a 5-meter resolution for wildfire image classification using convolution neural network approach","volume":"14","author":"Azami Muhammad Hasif bin","year":"2022","unstructured":"Muhammad Hasif bin Azami, Necmi Cihan Orger, Victor Hugo Schulz, Takashi Oshiro, and Mengu Cho. 2022. Earth observation mission of a 6U CubeSat with a 5-meter resolution for wildfire image classification using convolution neural network approach. Remote Sensing 14, 8 (2022), 1874.","journal-title":"Remote Sensing"},{"key":"e_1_3_2_5_2","unstructured":"Barani Design. MeteoTemp RH+T. (n.d.). https:\/\/static1.squarespace.com\/static\/597dc443914e6bed5fd30dcc\/t\/618a9376bd08d7243005ce49\/1636471677532\/MeteoTemp-DataSheet.pdf accessed Mar 2023."},{"key":"e_1_3_2_6_2","article-title":"tinyMAN: Lightweight energy manager using reinforcement learning for energy harvesting wearable IoT devices","author":"Basaklar Toygun","year":"2022","unstructured":"Toygun Basaklar, Yigit Tuncel, and Umit Y. Ogras. 2022. tinyMAN: Lightweight energy manager using reinforcement learning for energy harvesting wearable IoT devices. arXiv:2202.09297 (2022).","journal-title":"arXiv:2202.09297"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","first-page":"5413","DOI":"10.1109\/IGARSS47720.2021.9553108","volume-title":"IEEE International Geoscience and Remote Sensing Symposium IGARSS","author":"Azami Muhammad Hasif bin","year":"2021","unstructured":"Muhammad Hasif bin Azami et\u00a0al. 2021. Demonstration of wildfire detection using image classification onboard CubeSat. In IEEE International Geoscience and Remote Sensing Symposium IGARSS. 5413\u20135416."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/s18072104"},{"key":"e_1_3_2_9_2","unstructured":"Greg Brockman et\u00a0al. 2016. OpenAI Gym. (2016). arXiv:arXiv:1606.01540"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16484"},{"issue":"53","key":"e_1_3_2_11_2","first-page":"157","article-title":"V12. 1: User\u2019s manual for CPLEX","volume":"46","author":"Cplex IBM ILOG","year":"2009","unstructured":"IBM ILOG Cplex. 2009. V12. 1: User\u2019s manual for CPLEX. International Business Machines Corporation 46, 53 (2009), 157.","journal-title":"International Business Machines Corporation"},{"issue":"2","key":"e_1_3_2_12_2","first-page":"1","article-title":"The 10% wind speed rule of thumb for estimating a wildfire\u2019s forward rate of spread in forests and shrublands","volume":"76","author":"Cruz Miguel G.","year":"2019","unstructured":"Miguel G. Cruz and Martin E. Alexander. 2019. The 10% wind speed rule of thumb for estimating a wildfire\u2019s forward rate of spread in forests and shrublands. Annals of Forest Science 76, 2 (2019), 1\u201311.","journal-title":"Annals of Forest Science"},{"key":"e_1_3_2_13_2","unstructured":"Cubic. Low Power Particle Sensor PM2105L. (n.d.). https:\/\/en.gassensor.com.cn\/IndoorPMSensor\/info_itemid_1830.html accessed Mar 2023."},{"issue":"1","key":"e_1_3_2_14_2","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1038\/s41598-021-03882-9","article-title":"Forest fire detection system using wireless sensor networks and machine learning","volume":"12","author":"Dampage Udaya","year":"2022","unstructured":"Udaya Dampage, Lumini Bandaranayake, Ridma Wanasinghe, Kishanga Kottahachchi, and Bathiya Jayasanka. 2022. Forest fire detection system using wireless sensor networks and machine learning. Scientific Reports 12, 1 (2022), 46.","journal-title":"Scientific Reports"},{"key":"e_1_3_2_15_2","article-title":"Tensorflow lite micro: Embedded machine learning on tinyml systems","author":"David Robert","year":"2020","unstructured":"Robert David et\u00a0al. 2020. Tensorflow lite micro: Embedded machine learning on tinyml systems. arXiv:2010.08678 (2020).","journal-title":"arXiv:2010.08678"},{"key":"e_1_3_2_16_2","first-page":"460","volume-title":"IEEE 3rd World Forum on Internet of Things (WF-IoT)","author":"Dias Gabriel Martins","year":"2016","unstructured":"Gabriel Martins Dias, Maddalena Nurchis, and Boris Bellalta. 2016. Adapting sampling interval of sensor networks using on-line reinforcement learning. In IEEE 3rd World Forum on Internet of Things (WF-IoT). 460\u2013465."},{"key":"e_1_3_2_17_2","unstructured":"Fire Danger Forecast. Wildland Fire Potential Index (WFPI). (n.d.). https:\/\/www.usgs.gov\/fire-danger-forecast\/wildland-fire-potential-index-wfpi accessed Mar 2023."},{"key":"e_1_3_2_18_2","unstructured":"Forest Service. National Fire Danger Rating System. (n.d.). https:\/\/www.fs.usda.gov\/detail\/scnfs\/home\/?cid=fseprd634957 accessed Mar 2023."},{"key":"e_1_3_2_19_2","first-page":"7","volume-title":"Proceedings of the Workshop on Energy Harvesting & Energy-neutral Sensing Systems","author":"Fraternali Francesco","year":"2018","unstructured":"Francesco Fraternali, Bharathan Balaji, and Rajesh Gupta. 2018. Scaling configuration of energy harvesting sensors with reinforcement learning. In Proceedings of the Workshop on Energy Harvesting & Energy-neutral Sensing Systems. 7\u201313."},{"key":"e_1_3_2_20_2","first-page":"1587","volume-title":"International Conference on Machine Learning","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, Herke Hoof, and David Meger. 2018. Addressing function approximation error in actor-critic methods. In International Conference on Machine Learning. PMLR, 1587\u20131596."},{"key":"e_1_3_2_21_2","first-page":"3622","volume-title":"IEEE Geoscience and Remote Sensing Symposium","author":"Gangestad Joseph W.","year":"2014","unstructured":"Joseph W. Gangestad, Darren W. Rowen, and Brian S. Hardy. 2014. Forest fires, sunglint, and a solar eclipse: Responsive remote sensing with AeroCube-4. In IEEE Geoscience and Remote Sensing Symposium. 3622\u20133625."},{"key":"e_1_3_2_22_2","unstructured":"Gurobi Optimization LLC. 2023. Gurobi Optimizer Reference Manual. (2023). https:\/\/www.gurobi.com accessed Mar 2023."},{"issue":"29","key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"884","DOI":"10.21105\/joss.00884","article-title":"pvlib python: A python package for modeling solar energy systems","volume":"3","author":"Holmgren William F.","year":"2018","unstructured":"William F. Holmgren, Clifford W. Hansen, and Mark A. Mikofski. 2018. pvlib python: A python package for modeling solar energy systems. Journal of Open Source Software 3, 29 (2018), 884.","journal-title":"Journal of Open Source Software"},{"issue":"3","key":"e_1_3_2_24_2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.3390\/fire2030047","article-title":"Severe fire danger index: A forecastable metric to inform firefighter and community wildfire risk management","volume":"2","author":"Jolly W. Matt","year":"2019","unstructured":"W. Matt Jolly, Patrick H. Freeborn, Wesley G. Page, and Bret W. Butler. 2019. Severe fire danger index: A forecastable metric to inform firefighter and community wildfire risk management. Fire 2, 3 (2019), 47.","journal-title":"Fire"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","first-page":"69359","DOI":"10.1109\/ACCESS.2020.2986507","article-title":"Machine learning-based energy-saving framework for environmental states-adaptive wireless sensor network","volume":"8","author":"Kang Jaewoong","year":"2020","unstructured":"Jaewoong Kang, Jongmo Kim, Minhwan Kim, and Mye Sohn. 2020. Machine learning-based energy-saving framework for environmental states-adaptive wireless sensor network. IEEE Access 8 (2020), 69359\u201369367.","journal-title":"IEEE Access"},{"issue":"4","key":"e_1_3_2_26_2","doi-asserted-by":"crossref","first-page":"32\u2013es","DOI":"10.1145\/1274858.1274870","article-title":"Power management in energy harvesting sensor networks","volume":"6","author":"Kansal Aman","year":"2007","unstructured":"Aman Kansal, Jason Hsu, Sadaf Zahedi, and Mani B. Srivastava. 2007. Power management in energy harvesting sensor networks. ACM Trans. Embedd. Comput. Syst. 6, 4 (2007), 32\u2013es.","journal-title":"ACM Trans. Embedd. Comput. Syst."},{"key":"e_1_3_2_27_2","volume-title":"Photovoltaic Array Performance Model","author":"King David L.","year":"2004","unstructured":"David L. King, Jay A. Kratochvil, and William Earl Boyson. 2004. Photovoltaic Array Performance Model. Vol. 8. Citeseer."},{"key":"e_1_3_2_28_2","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap Timothy P.","year":"2015","unstructured":"Timothy P. Lillicrap et\u00a0al. 2015. Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015).","journal-title":"arXiv:1509.02971"},{"key":"e_1_3_2_29_2","article-title":"QoS and energy aware cooperative routing protocol for wildfire monitoring wireless sensor networks","author":"Maalej Mohamed","year":"2013","unstructured":"Mohamed Maalej, Sofiane Cherif, and Hichem Besbes. 2013. QoS and energy aware cooperative routing protocol for wildfire monitoring wireless sensor networks. The Scientific World Journal (2013).","journal-title":"The Scientific World Journal"},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Kevin McGrattan Randall McDermott Craig Weinschenk and Glenn Forney. 2013. Fire Dynamics Simulator Technical Reference Guide Sixth Edition. (2013).","DOI":"10.6028\/NIST.SP.1018e6"},{"key":"e_1_3_2_31_2","article-title":"Learning to navigate in cities without a map","volume":"31","author":"Mirowski Piotr","year":"2018","unstructured":"Piotr Mirowski et\u00a0al. 2018. Learning to navigate in cities without a map. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.3390\/su141912270"},{"key":"e_1_3_2_33_2","unstructured":"National Interagency Fire Center. Wildfires and Acres. (n.d.). https:\/\/www.nifc.gov\/fire-information\/statistics\/wildfires accessed Mar 2023."},{"key":"e_1_3_2_34_2","unstructured":"NRG Systems. NRG S1 ANEMOMETER. (n.d.). https:\/\/www.nrgsystems.com\/blog\/anemometer-wind-speed-threshold\/ accessed Mar 2023."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"692706","DOI":"10.3389\/ffgc.2021.692706","article-title":"Cell2Fire: A cell-based forest fire growth model to support strategic landscape management planning","volume":"4","author":"Pais Cristobal","year":"2021","unstructured":"Cristobal Pais, Jaime Carrasco, David L. Martell, Andres Weintraub, and David L. Woodruff. 2021. Cell2Fire: A cell-based forest fire growth model to support strategic landscape management planning. Frontiers in Forests and Global Change 4 (2021), 692706.","journal-title":"Frontiers in Forests and Global Change"},{"issue":"32","key":"e_1_3_2_36_2","doi-asserted-by":"crossref","first-page":"2003598","DOI":"10.1002\/adfm.202003598","article-title":"Multilayered cylindrical triboelectric nanogenerator to harvest kinetic energy of tree branches for monitoring environment condition and forest fire","volume":"30","author":"Pang Yaokun","year":"2020","unstructured":"Yaokun Pang et\u00a0al. 2020. Multilayered cylindrical triboelectric nanogenerator to harvest kinetic energy of tree branches for monitoring environment condition and forest fire. Advanced Functional Materials 30, 32 (2020), 2003598.","journal-title":"Advanced Functional Materials"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","first-page":"111868","DOI":"10.1016\/j.enconman.2019.111868","article-title":"Design of novel electromagnetic energy harvester to power a deicing robot and monitoring sensors for transmission lines","volume":"197","author":"Paul Sarbajit","year":"2019","unstructured":"Sarbajit Paul and Junghwan Chang. 2019. Design of novel electromagnetic energy harvester to power a deicing robot and monitoring sensors for transmission lines. Energy Conversion and Management 197 (2019), 111868.","journal-title":"Energy Conversion and Management"},{"issue":"4","key":"e_1_3_2_38_2","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/TSMC.2018.2815988","article-title":"A distributed control framework of multiple unmanned aerial vehicles for dynamic wildfire tracking","volume":"50","author":"Pham Huy Xuan","year":"2018","unstructured":"Huy Xuan Pham, Hung Manh La, David Feil-Seifer, and Matthew C. Deans. 2018. A distributed control framework of multiple unmanned aerial vehicles for dynamic wildfire tracking. IEEE Transactions on Systems, Man, and Cybernetics 50, 4 (2018), 1537\u20131548.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"e_1_3_2_39_2","first-page":"1","volume-title":"IEEE International Conference on Mobile Adhoc and Sensor Systems","author":"Shah Kunal","year":"2007","unstructured":"Kunal Shah and Mohan Kumar. 2007. Distributed independent reinforcement learning (DIRL) approach to resource management in wireless sensor networks. In IEEE International Conference on Mobile Adhoc and Sensor Systems. 1\u20139."},{"key":"e_1_3_2_40_2","volume-title":"Field and Service Robotics","author":"Shah Shital","year":"2017","unstructured":"Shital Shah, Debadeepta Dey, Chris Lovett, and Ashish Kapoor. 2017. AirSim: High-fidelity visual and physical simulation for autonomous vehicles. In Field and Service Robotics. arXiv:arXiv:1705.05065https:\/\/arxiv.org\/abs\/1705.05065"},{"key":"e_1_3_2_41_2","unstructured":"STMicro. Multiprotocol LPWAN 32-bit Arm\u00ae Cortex\u00ae-M4 MCUs. (n.d.). https:\/\/www.st.com\/resource\/en\/datasheet\/stm32wle5jb.pdf accessed Mar 2023."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2010.2101311"},{"key":"e_1_3_2_43_2","unstructured":"Texas Instruments Inc.CC2652R. [Online] https:\/\/www.ti.com\/product\/CC2652R accessed March 2023. (n.d.)."},{"key":"e_1_3_2_44_2","unstructured":"The European Commission. Data from the EFFIS database. (n.d.). https:\/\/effis.jrc.ec.europa.eu\/applications\/data-and-services accessed Mar 2023."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3106283"},{"key":"e_1_3_2_46_2","unstructured":"Vanessa Romo. PG&E Pleads Guilty On 2018 California Camp Fire: \u201cOur Equipment Started That Fire\u201d. (n.d.). https:\/\/www.npr.org\/2020\/06\/16\/879008760\/pg-e-pleads-guilty-on-2018-california-camp-fire-our-equipment-started-that-fire accessed Mar 2023."},{"key":"e_1_3_2_47_2","first-page":"639","volume-title":"IEEE International Conference on Unmanned Aircraft Systems (ICUAS)","author":"Yuan Chi","year":"2015","unstructured":"Chi Yuan, Zhixiang Liu, and Youmin Zhang. 2015. UAV-based forest fire detection and tracking using image processing techniques. In IEEE International Conference on Unmanned Aircraft Systems (ICUAS). 639\u2013643."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.3390\/info12010042"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3608100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3608100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:32Z","timestamp":1750178792000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3608100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,9]]},"references-count":47,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3608100"],"URL":"https:\/\/doi.org\/10.1145\/3608100","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,9]]},"assertion":[{"value":"2023-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}