{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T08:18:50Z","timestamp":1762157930209,"version":"3.41.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100016300","name":"University of Pittsburgh Center for Research Computing","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016300","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2023,11,30]]},"abstract":"<jats:p>Advances in deep vision techniques and the ubiquity of smart cameras will drive the next generation of video analytics. However, video analytics applications consume vast amounts of energy as deep learning techniques are power-hungry. In this article, we focus on a parking video analytics platform and propose RL-CamSleep, a deep reinforcement learning-based technique, to actuate the cameras to reduce the energy footprint while retaining the system\u2019s utility. Our key insight is that many video-analytics applications do not need to be always operational, and we can design policies to activate video analytics only when necessary. We design two modes of operation for the reinforcement learning (RL) controller: (i) cloud-based mode and (ii) grid-isolated solar-powered mode. In the cloud-based mode, the controller runs on the cloud to control the cameras, whereas, in the solar-powered mode, the RL controller is constrained by the energy produced by solar. We evaluate our approach on a city-scale parking dataset having 76 streets spread across a city. Our analysis shows RL-CamSleep can learn an adaptive policy that reduces the average energy consumption by 76% and achieves an average accuracy of 98%. For the grid-isolated mode, RL-CamSleep outperforms other baseline techniques demonstrating the need for adaptive policy in energy-constrained environments.<\/jats:p>","DOI":"10.1145\/3584949","type":"journal-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T11:21:32Z","timestamp":1676978492000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Solar-powered Parking Analytics System Using Deep Reinforcement Learning"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6706-4517","authenticated-orcid":false,"given":"Yoones","family":"Rezaei","sequence":"first","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1552-2728","authenticated-orcid":false,"given":"Talha","family":"Khan","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9022-4259","authenticated-orcid":false,"given":"Stephen","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9508-9815","authenticated-orcid":false,"given":"Daniel","family":"Moss\u00e9","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,20]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Arlo. 2022. Arlo Pro 4 Wireless Security Camera. Retrieved from https:\/\/www.arlo.com\/en-us\/cameras\/VMC4050P-100NAS.html."},{"key":"e_1_3_2_3_2","unstructured":"Amazon. 2022. FUVISION Wireless Outdoor Security Camera Solar Battery. Retrieved from https:\/\/www.amazon.com\/Wireless-Security-FUVISION-Waterproof-10400mAh\/dp\/B07XYWD4MJ."},{"key":"e_1_3_2_4_2","unstructured":"Amazon. 2022. Ring Stick Up Cam Solar HD security camera. Retrieved from https:\/\/www.amazon.com\/All-new-Ring-Stick-Up-Cam-Solar-HD-security-camera-with-two-way-talk-Works-with-Alexa-\/dp\/B07W7G23ZG?tag=cnet-buy-button-20&ascsubtag=e41b80d785304ea8b660a7c39a92a18b%7C2360c684-ed2c-4105-afbb-5a7863c5ac93%7Cdtp."},{"key":"e_1_3_2_5_2","first-page":"33","volume-title":"Proceedings of the 5th Annual Research@Locate Conference","author":"Acharya Debaditya","year":"2018","unstructured":"Debaditya Acharya, Weilin Yan, and Kourosh Khoshelham. 2018. Real-time image-based parking occupancy detection using deep learning. In Proceedings of the 5th Annual Research@Locate Conference. 33\u201340."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.055"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.3641638"},{"issue":"3","key":"e_1_3_2_8_2","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.jue.2006.04.004","article-title":"An integrated model of downtown parking and traffic congestion","volume":"60","author":"Arnott Richard","year":"2006","unstructured":"Richard Arnott and Eren Inci. 2006. An integrated model of downtown parking and traffic congestion. J. Urban Econ. 60, 3 (2006), 418\u2013442.","journal-title":"J. Urban Econ."},{"key":"e_1_3_2_9_2","first-page":"1","volume-title":"Proceedings of the 15th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt\u201917)","author":"Atallah Ribal","year":"2017","unstructured":"Ribal Atallah, Chadi Assi, and Maurice Khabbaz. 2017. Deep reinforcement learning-based scheduling for roadside communication networks. In Proceedings of the 15th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt\u201917). IEEE, 1\u20138."},{"key":"e_1_3_2_10_2","first-page":"456","volume-title":"Proceedings of the IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems (MASS\u201919)","author":"Bashir Noman","year":"2019","unstructured":"Noman Bashir, Dong Chen, David Irwin, and Prashant Shenoy. 2019. Solar-TK: A data-driven toolkit for solar PV performance modeling and forecasting. In Proceedings of the IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems (MASS\u201919). IEEE, 456\u2013466."},{"key":"e_1_3_2_11_2","first-page":"79","volume-title":"Proceedings of the IEEE\/ACM Fifth International Conference on Internet-of-Things Design and Implementation (IoTDI\u201920)","author":"Bovornkeeratiroj Phuthipong","year":"2020","unstructured":"Phuthipong Bovornkeeratiroj, Srinivasan Iyengar, Stephen Lee, David Irwin, and Prashant Shenoy. 2020. RepEL: A utility-preserving privacy system for IoT-based energy meters. In Proceedings of the IEEE\/ACM Fifth International Conference on Internet-of-Things Design and Implementation (IoTDI\u201920). IEEE, 79\u201391."},{"key":"e_1_3_2_12_2","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. Retrieved from arXiv:arXiv:1606.01540"},{"issue":"8","key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"2763","DOI":"10.1109\/JSEN.2016.2517084","article-title":"A reinforcement learning-based sleep scheduling algorithm for desired area coverage in solar-powered wireless sensor networks","volume":"16","author":"Chen Hongbin","year":"2016","unstructured":"Hongbin Chen, Xueyan Li, and Feng Zhao. 2016. A reinforcement learning-based sleep scheduling algorithm for desired area coverage in solar-powered wireless sensor networks. IEEE Sensors J. 16, 8 (2016), 2763\u20132774.","journal-title":"IEEE Sensors J."},{"key":"e_1_3_2_14_2","unstructured":"IHS Markit. 2018. Consumer Video Surveillance Market to Top $1 Billion in 2018 IHS Markit Says. Retrieved from https:\/\/bit.ly\/30XBt5C."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","DOI":"10.1145\/3404191","article-title":"Aces: Automatic configuration of energy harvesting sensors with reinforcement learning","author":"Fraternali Francesco","year":"2020","unstructured":"Francesco Fraternali, Bharathan Balaji, Yuvraj Agarwal, and Rajesh K. Gupta. 2020. Aces: Automatic configuration of energy harvesting sensors with reinforcement learning. ACM Trans. Sensor Netw. 16, 4 (2020), 1\u201331.","journal-title":"ACM Trans. Sensor Netw."},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1145\/3384419.3430734","volume-title":"Proceedings of the 18th Conference on Embedded Networked Sensor Systems","author":"Fraternali Francesco","year":"2020","unstructured":"Francesco Fraternali, Bharathan Balaji, Dhiman Sengupta, Dezhi Hong, and Rajesh K. Gupta. 2020. Ember: Energy management of batteryless event detection sensors with deep reinforcement learning. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems. 503\u2013516."},{"key":"e_1_3_2_18_2","article-title":"Energy efficiency of the Internet of Things","author":"Friedli Martin","year":"2016","unstructured":"Martin Friedli, Lukas Kaufmann, Francesco Paganini, and Rainer Kyburz. 2016. Energy efficiency of the Internet of Things. Technology and Energy Assessment Report prepared for IEA 4E EDNA. Lucerne University of Applied Sciences, Switzerland.","journal-title":"Technology and Energy Assessment Report prepared for IEA 4E EDNA. Lucerne University of Applied Sciences, Switzerland"},{"issue":"77","key":"e_1_3_2_19_2","first-page":"1","article-title":"ChainerRL: A deep reinforcement learning library","volume":"22","author":"Fujita Yasuhiro","year":"2021","unstructured":"Yasuhiro Fujita, Prabhat Nagarajan, Toshiki Kataoka, and Takahiro Ishikawa. 2021. ChainerRL: A deep reinforcement learning library. J. Mach. Learn. Res. 22, 77 (2021), 1\u201314. Retrieved from http:\/\/jmlr.org\/papers\/v22\/20-376.html.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_20_2","volume-title":"Encyclopedia of Electrochemical Power Sources","author":"Garche Jurgen","year":"2013","unstructured":"Jurgen Garche, Ch Dyer, Patrick T. Moseley, Zempachi Ogumi, David A. J. Rand, and Bruno Scrosati. 2013. Encyclopedia of Electrochemical Power Sources. Newnes."},{"key":"e_1_3_2_21_2","unstructured":"Google. 2020. Google Nest. Retrieved from https:\/\/nest.com\/."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/2674061.2674071","volume-title":"Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings","author":"Iyengar Srinivasan","year":"2014","unstructured":"Srinivasan Iyengar, Navin Sharma, David Irwin, Prashant Shenoy, and Krithi Ramamritham. 2014. SolarCast: A cloud-based black box solar predictor for smart homes. In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings. 40\u201349."},{"issue":"12","key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"3520","DOI":"10.3390\/en14123520","article-title":"Optimal sizing of rooftop PV and battery storage for grid-connected houses considering flat and time-of-use electricity rates","volume":"14","author":"Javeed Iflah","year":"2021","unstructured":"Iflah Javeed, Rahmat Khezri, Amin Mahmoudi, Amirmehdi Yazdani, and G. M. Shafiullah. 2021. Optimal sizing of rooftop PV and battery storage for grid-connected houses considering flat and time-of-use electricity rates. Energies 14, 12 (2021), 3520.","journal-title":"Energies"},{"key":"e_1_3_2_24_2","volume-title":"Proceedings of the Conference of the ACM Special Interest Group on Data Communication","author":"Jiang Junchen","year":"2018","unstructured":"Junchen Jiang, Ganesh Ananthanarayanan, Peter Bodik, Siddhartha Sen, and Ion Stoica. 2018. Chameleon: Scalable adaptation of video analytics. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication."},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Daniel Kang John Emmons Firas Abuzaid Peter Bailis and Matei Zaharia. 2017. Noscope: Optimizing neural network queries over video at scale. Retrieved from https:\/\/arXiv:1703.02529.","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"e_1_3_2_27_2","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Adv. Neural Info. Process. Syst. 25 (2012).","journal-title":"Adv. Neural Info. Process. Syst."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2013.2285921"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2462456.2464448"},{"key":"e_1_3_2_30_2","article-title":"Spoton: Just-in-time active event detection on energy autonomous sensing systems","volume":"9","author":"Luo Yubo","year":"2019","unstructured":"Yubo Luo and Shahriar Nirjon. 2019. Spoton: Just-in-time active event detection on energy autonomous sensing systems. In Proceedings of the 25th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS\u201919) 9 (2019).","journal-title":"Proceedings of the 25th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS\u201919)"},{"key":"e_1_3_2_31_2","unstructured":"Kevin McCoy. 2017. Drivers spend an average of 17 hours a year searching for parking spots. Retrieved from https:\/\/bit.ly\/36Y2VlU."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"4","key":"e_1_3_2_33_2","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TC.2009.158","article-title":"Adaptive power management for environmentally powered systems","volume":"59","author":"Moser Clemens","year":"2009","unstructured":"Clemens Moser, Lothar Thiele, Davide Brunelli, and Luca Benini. 2009. Adaptive power management for environmentally powered systems. IEEE Trans. Comput. 59, 4 (2009), 478\u2013491.","journal-title":"IEEE Trans. Comput."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"issue":"8","key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1080\/14786451.2015.1100196","article-title":"Residential load and rooftop PV generation: An Australian distribution network dataset","volume":"36","author":"Ratnam Elizabeth L.","year":"2017","unstructured":"Elizabeth L. Ratnam, Steven R. Weller, Christopher M. Kellett, and Alan T. Murray. 2017. Residential load and rooftop PV generation: An Australian distribution network dataset. Int. J. Sustain. Energy 36, 8 (2017), 787\u2013806.","journal-title":"Int. J. Sustain. Energy"},{"key":"e_1_3_2_36_2","unstructured":"Tom Schaul John Quan Ioannis Antonoglou and David Silver. 2015. Prioritized experience replay. Retrieved from https:\/\/arXiv:1511.05952."},{"key":"e_1_3_2_37_2","article-title":"Green AI","author":"Schwartz Roy","year":"2019","unstructured":"Roy Schwartz, Jesse Dodge, Noah A. Smith, and Oren Etzioni. 2019. Green AI. Retrieved from https:\/\/arXiv:1907.10597.","journal-title":"Retrieved from https:\/\/arXiv:1907.10597"},{"key":"e_1_3_2_38_2","first-page":"528","volume-title":"Proceedings of the IEEE International Conference on Smart Grid Communications (SmartGridComm\u201911)","author":"Sharma Navin","year":"2011","unstructured":"Navin Sharma, Pranshu Sharma, David Irwin, and Prashant Shenoy. 2011. Predicting solar generation from weather forecasts using machine learning. In Proceedings of the IEEE International Conference on Smart Grid Communications (SmartGridComm\u201911). IEEE, 528\u2013533."},{"key":"e_1_3_2_39_2","unstructured":"Donald Shoup. 2011. The High Cost of Free Parking . American Planning Association."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126495"},{"key":"e_1_3_2_41_2","volume-title":"Proceedings of the 3rd International Conference on Mobile Systems, Applications, and Services","author":"Sorber Jacob","year":"2005","unstructured":"Jacob Sorber, Nilanjan Banerjee, Mark D. Corner, and Sami Rollins. 2005. Turducken: Hierarchical power management for mobile devices. In Proceedings of the 3rd International Conference on Mobile Systems, Applications, and Services."},{"key":"e_1_3_2_42_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. MIT press."},{"key":"e_1_3_2_43_2","unstructured":"The city of Melbourne Parking dataset. 2019. Retrieved from https:\/\/bit.ly\/3ESojsi."},{"key":"e_1_3_2_44_2","volume-title":"Proceedings of the IEEE 3rd World Forum on Internet of Things (WF-IoT\u201916)","author":"Valipour Sepehr","year":"2016","unstructured":"Sepehr Valipour, Mennatullah Siam, Eleni Stroulia, and Martin Jagersand. 2016. Parking-stall vacancy indicator system, based on deep convolutional neural networks. In Proceedings of the IEEE 3rd World Forum on Internet of Things (WF-IoT\u201916). IEEE."},{"key":"e_1_3_2_45_2","volume-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence","author":"Hasselt Hado Van","year":"2016","unstructured":"Hado Van Hasselt, Arthur Guez, and David Silver. 2016. Deep reinforcement learning with double q-learning. In Proceedings of the 30th AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_46_2","first-page":"164","volume-title":"Proceedings of the IEEE\/ACM 5th International Conference on Internet-of-Things Design and Implementation (IoTDI)","author":"Wang Wenpeng","year":"2020","unstructured":"Wenpeng Wang, Jianyu Su, Zackary Hicks, and Bradford Campbell. 2020. The standby energy of smart devices: Problems, progress, & potential. In Proceedings of the IEEE\/ACM 5th International Conference on Internet-of-Things Design and Implementation (IoTDI). IEEE, 164\u2013175."},{"key":"e_1_3_2_47_2","first-page":"1995","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In Proceedings of the International Conference on Machine Learning. 1995\u20132003."},{"key":"e_1_3_2_48_2","first-page":"485","volume-title":"Proceedings of the International Conference on Wireless Algorithms, Systems, and Applications","author":"Wei Zhenchun","year":"2018","unstructured":"Zhenchun Wei, Fei Liu, Zengwei Lyu, Xu Ding, Lei Shi, and Chengkai Xia. 2018. Reinforcement learning for a novel mobile charging strategy in wireless rechargeable sensor networks. In Proceedings of the International Conference on Wireless Algorithms, Systems, and Applications. Springer, 485\u2013496."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388948"},{"issue":"51","key":"e_1_3_2_51_2","doi-asserted-by":"crossref","first-page":"1802188","DOI":"10.1002\/smll.201802188","article-title":"Highly compact artificial memristive neuron with low energy consumption","volume":"14","author":"Zhang Yishu","year":"2018","unstructured":"Yishu Zhang, Wei He, Yujie Wu, Kejie Huang, Yangshu Shen, Jiasheng Su, Yaoyuan Wang, Ziyang Zhang, Xinglong Ji, Guoqi Li et\u00a0al. 2018. Highly compact artificial memristive neuron with low energy consumption. Small 14, 51 (2018), 1802188.","journal-title":"Small"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3584949","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3584949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:07Z","timestamp":1750178227000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3584949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,11,30]]}},"alternative-id":["10.1145\/3584949"],"URL":"https:\/\/doi.org\/10.1145\/3584949","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"type":"print","value":"1550-4859"},{"type":"electronic","value":"1550-4867"}],"subject":[],"published":{"date-parts":[[2023,4,20]]},"assertion":[{"value":"2022-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}