{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T06:40:01Z","timestamp":1746772801019,"version":"3.40.5"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10957-025-02658-9","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T04:48:48Z","timestamp":1744001328000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["(Online) Convex Optimization for Demand-Side Management: Application to Thermostatically Controlled Loads"],"prefix":"10.1007","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2456-6238","authenticated-orcid":false,"given":"Bianca M.","family":"Moreno","sequence":"first","affiliation":[]},{"given":"Margaux","family":"Br\u00e9g\u00e8re","sequence":"additional","affiliation":[]},{"given":"Pierre","family":"Gaillard","sequence":"additional","affiliation":[]},{"given":"Nadia","family":"Oudjane","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Albouys, J., Sabouret, N., Haradji, Y., Schumann, M., Inard, C.: SMACH: multi-agent simulation of human activity in the household. In: Advances in Practical Applications of Survivable Agents and Multi-Agent Systems: The PAAMS Collection, pp. 227\u2013231. Springer International Publishing, Cham (2019)","key":"2658_CR1","DOI":"10.1007\/978-3-030-24209-1_19"},{"key":"2658_CR2","doi-asserted-by":"publisher","first-page":"109899","DOI":"10.1016\/j.rser.2020.109899","volume":"130","author":"I Antonopoulos","year":"2020","unstructured":"Antonopoulos, I., Robu, V., Couraud, B., Kirli, D., Norbu, S., Kiprakis, A., Flynn, D., Elizondo-Gonzalez, S., Wattam, S.: Artificial intelligence and machine learning approaches to energy demand-side response: a systematic review. Renew. Sustain. Energy Rev. 130, 109899 (2020)","journal-title":"Renew. Sustain. Energy Rev."},{"key":"2658_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s42162-023-00262-7","volume":"6","author":"MS Bakare","year":"2023","unstructured":"Bakare, M.S., Abdulkarim, A., Zeeshan, M., Shuaibu, A.N.: A comprehensive overview on demand side energy management towards smart grids: challenges, solutions, and future direction. Energy Inf. 6, 4 (2023). https:\/\/doi.org\/10.1186\/s42162-023-00262-7","journal-title":"Energy Inf."},{"key":"2658_CR4","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s10107-023-01934-8","volume":"202","author":"JF Bonnans","year":"2023","unstructured":"Bonnans, J.F., Lavigne, P., Pfeiffer, L.: Discrete potential mean field games: duality and numerical resolution. Math. Program. 202, 241\u2013278 (2023). https:\/\/doi.org\/10.1007\/s10107-023-01934-8","journal-title":"Math. Program."},{"unstructured":"Br\u00e9g\u00e8re, M., Gaillard, P., Goude, Y., Stoltz, G.: Target tracking for contextual bandits: Application to demand side management. In: International Conference on Machine Learning (ICML) (2019)","key":"2658_CR5"},{"key":"2658_CR6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.epsr.2016.12.001","volume":"146","author":"EM Burger","year":"2017","unstructured":"Burger, E.M., Moura, S.J.: Generation following with thermostatically controlled loads via alternating direction method of multipliers sharing algorithm. Electric Power Syst. Res. 146, 141\u2013160 (2017). https:\/\/doi.org\/10.1016\/j.epsr.2016.12.001","journal-title":"Electric Power Syst. Res."},{"doi-asserted-by":"publisher","unstructured":"Bu\u0161i\u0107, A., Meyn, S.: Distributed randomized control for demand dispatch. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 6964\u20136971 (2016). https:\/\/doi.org\/10.1109\/CDC.2016.7799342","key":"2658_CR7","DOI":"10.1109\/CDC.2016.7799342"},{"doi-asserted-by":"publisher","unstructured":"Cammardella, N., Bu\u0161i\u0107, A., Ji, Y., Meyn, S.: Kullback-Leibler-quadratic optimal control of flexible power demand. In: 2019 IEEE 58th Conference on Decision and Control (CDC), pp. 4195\u20134201 (2019). https:\/\/doi.org\/10.1109\/CDC40024.2019.9029512","key":"2658_CR8","DOI":"10.1109\/CDC40024.2019.9029512"},{"doi-asserted-by":"publisher","unstructured":"Cammardella, N., Bu\u0161i\u0107, A., Meyn, S.: Kullback-Leibler-quadratic optimal control in a stochastic environment. In: 2021 60th IEEE Conference on Decision and Control (CDC), pp. 158\u2013165 (2021). https:\/\/doi.org\/10.1109\/CDC45484.2021.9682943","key":"2658_CR9","DOI":"10.1109\/CDC45484.2021.9682943"},{"key":"2658_CR10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, Learning, and Games","author":"N Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006). https:\/\/doi.org\/10.1017\/CBO9780511546921"},{"doi-asserted-by":"publisher","unstructured":"Chen, Y., Hashmi, M.U., Mathias, J., Bu\u0161i\u0107, A., Meyn, S.: Distributed control design for balancing the grid using flexible loads. In: S.\u00a0Meyn, T.\u00a0Samad, I.\u00a0Hiskens, J.\u00a0Stoustrup (eds.) Energy Markets and Responsive Grids: Modeling, Control, and Optimization, pp. 383\u2013411. Springer New York, New York, NY (2018). https:\/\/doi.org\/10.1007\/978-1-4939-7822-9_16","key":"2658_CR11","DOI":"10.1007\/978-1-4939-7822-9_16"},{"key":"2658_CR12","doi-asserted-by":"publisher","first-page":"111,002","DOI":"10.1016\/j.automatica.2023.111002","volume":"152","author":"A Coffman","year":"2023","unstructured":"Coffman, A., Bu\u0161i\u0107, A., Barooah, P.: A unified framework for coordination of thermostatically controlled loads. Automatica 152, 111,002 (2023). https:\/\/doi.org\/10.1016\/j.automatica.2023.111002","journal-title":"Automatica"},{"issue":"2","key":"2658_CR13","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/TCST.2020.2974181","volume":"29","author":"M Franceschelli","year":"2021","unstructured":"Franceschelli, M., Pilloni, A., Gasparri, A.: Multi-agent coordination of thermostatically controlled loads by smart power sockets for electric demand side management. IEEE Trans. Control Syst. Technol. 29(2), 731\u2013743 (2021). https:\/\/doi.org\/10.1109\/TCST.2020.2974181","journal-title":"IEEE Trans. Control Syst. Technol."},{"unstructured":"Geist, M., P\u00e9rolat, J., Lauri\u00e8re, M., Elie, R., Perrin, S., Bachem, O., Munos, R., Pietquin, O.: Concave utility reinforcement learning: The mean-field game viewpoint. In: International Conference on Autonomous Agents and Multiagent Systems, p. 489-497. Richland, SC (2022)","key":"2658_CR14"},{"unstructured":"Hazan, E.: Introduction to Online Convex Optimization, 2nd edn. MIT Press, Adaptive Computation and Machine Learning series (2022)","key":"2658_CR15"},{"unstructured":"Hazan, E., Kakade, S., Singh, K., Van\u00a0Soest, A.: Provably efficient maximum entropy exploration. In: International Conference on Machine Learning (ICML), vol.\u00a097, pp. 2681\u20132691. PMLR (2019)","key":"2658_CR16"},{"doi-asserted-by":"publisher","unstructured":"Huang, M., Malhame, R., Caines, P.: Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle. Commun. Inf. Syst. 6(3), 221\u20132252 (2006). https:\/\/doi.org\/10.4310\/CIS.2006.v6.n3.a5","key":"2658_CR17","DOI":"10.4310\/CIS.2006.v6.n3.a5"},{"issue":"9","key":"2658_CR18","doi-asserted-by":"publisher","first-page":"4142","DOI":"10.1109\/TPAS.1981.316965","volume":"PAS\u2013100","author":"S Ihara","year":"1981","unstructured":"Ihara, S., Schweppe, F.C.: Physically based modeling of cold load pickup. IEEE Trans. Power Appar. Syst. PAS\u2013100(9), 4142\u20134150 (1981). https:\/\/doi.org\/10.1109\/TPAS.1981.316965","journal-title":"IEEE Trans. Power Appar. Syst."},{"issue":"4","key":"2658_CR19","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1109\/TSG.2013.2257893","volume":"4","author":"SJ Kim","year":"2013","unstructured":"Kim, S.J., Giannakis, G.B.: Scalable and robust demand response with mixed-integer constraints. IEEE Trans. Smart Grid 4(4), 2089\u20132099 (2013). https:\/\/doi.org\/10.1109\/TSG.2013.2257893","journal-title":"IEEE Trans. Smart Grid"},{"doi-asserted-by":"publisher","unstructured":"Kizilkale, A., Malhame, R.: Mean field based control of power system dispersed energy storage devices for peak load relief. In: Proceedings of the IEEE Conference on Decision and Control, pp. 4971\u20134976 (2013). https:\/\/doi.org\/10.1109\/CDC.2013.6760669","key":"2658_CR20","DOI":"10.1109\/CDC.2013.6760669"},{"issue":"3","key":"2658_CR21","doi-asserted-by":"publisher","first-page":"1867","DOI":"10.3182\/20140824-6-ZA-1003.00630","volume":"47","author":"AC Kizilkale","year":"2014","unstructured":"Kizilkale, A.C., Malhame, R.P.: Collective target tracking mean field control for Markovian jump-driven models of electric water heating loads. IFAC Proc. Vol. 47(3), 1867\u20131872 (2014). https:\/\/doi.org\/10.3182\/20140824-6-ZA-1003.00630","journal-title":"IFAC Proc. Vol."},{"unstructured":"Koch, S., Mathieu, J.L., Callaway, D.S.: Modeling and control of aggregated heterogeneous thermostatically controlled loads for ancillary services. In: 17th Power Systems Computation Conference (PSCC\u201911) (2011)","key":"2658_CR22"},{"key":"2658_CR23","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s11537-007-0657-8","volume":"2","author":"JM Lasry","year":"2007","unstructured":"Lasry, J.M., Lions, P.L.: Mean field games. Japan. J. Math. 2, 229\u2013260 (2007)","journal-title":"Japan. J. Math."},{"unstructured":"Lauri\u00e8re, M., Perrin, S., Geist, M., Pietquin, O.: Learning mean field games: a survey. arXiv:2205.12944 (2022)","key":"2658_CR24"},{"issue":"3","key":"2658_CR25","doi-asserted-by":"publisher","first-page":"2683","DOI":"10.1109\/TSG.2018.2808247","volume":"10","author":"KL L\u00f3pez","year":"2019","unstructured":"L\u00f3pez, K.L., Gagn\u00e9, C., Gardner, M.A.: Demand-side management using deep learning for smart charging of electric vehicles. IEEE Trans. Smart Grid 10(3), 2683\u20132691 (2019). https:\/\/doi.org\/10.1109\/TSG.2018.2808247","journal-title":"IEEE Trans. Smart Grid"},{"issue":"9","key":"2658_CR26","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1109\/TAC.1985.1104071","volume":"30","author":"R Malhame","year":"1985","unstructured":"Malhame, R., Chong, C.Y.: Electric load model synthesis by diffusion approximation of a high-order hybrid-state stochastic system. IEEE Trans. Autom. Control 30(9), 854\u2013860 (1985). https:\/\/doi.org\/10.1109\/TAC.1985.1104071","journal-title":"IEEE Trans. Autom. Control"},{"unstructured":"Marin\u00a0Moreno, B., Gaillard, P., Oudjane, N., Br\u00e9g\u00e8re, M.: Efficient model-based concave utility reinforcement learning through greedy mirror descent. In: International Conference on Artificial Intelligence and Statistics (AISTATS) (2024)","key":"2658_CR27"},{"issue":"3","key":"2658_CR28","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1109\/59.14584","volume":"3","author":"R Mortensen","year":"1988","unstructured":"Mortensen, R., Haggerty, K.: A stochastic computer model for heating and cooling loads. IEEE Trans. Power Syst. 3(3), 1213\u20131219 (1988). https:\/\/doi.org\/10.1109\/59.14584","journal-title":"IEEE Trans. Power Syst."},{"unstructured":"Pasztor, B., Bogunovic, I., Krause, A.: Efficient model-based multi-agent mean-field reinforcement learning. Trans. Mach. Learn. Res. 2023, (2021)","key":"2658_CR29"},{"unstructured":"Perrin, S., Perolat, J., Lauriere, M., Geist, M., Elie, R., Pietquin, O.: Fictitious play for mean field games: continuous time analysis and applications. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)","key":"2658_CR30"},{"key":"2658_CR31","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. Wiley, Hoboken (1994)","edition":"1"},{"unstructured":"Rakhlin, A., Sridharan, K.: Online learning with predictable sequences. In: Proceedings of the 26th Annual Conference on Learning Theory (COLT) (2013)","key":"2658_CR32"},{"unstructured":"Rakhlin, A., Sridharan, K.: Optimization, learning, and games with predictable sequences. In: Proceedings of the 26th International Conference on Neural Information Processing Systems (NeurIPS) (2013)","key":"2658_CR33"},{"unstructured":"Rosenberg, A.A., Mansour, Y.: Online convex optimization in adversarial markov decision processes. In: International Conference on Machine Learning (ICML) (2019)","key":"2658_CR34"},{"doi-asserted-by":"publisher","unstructured":"Seguret, A., Oudjane, N., Le\u00a0Corre, T.: A decentralized algorithm for a mean field control problem of piecewise deterministic Markov processes. pp. 22\u201345 (2023). https:\/\/doi.org\/10.1051\/ps\/2023021","key":"2658_CR35","DOI":"10.1051\/ps\/2023021"},{"key":"2658_CR36","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"unstructured":"Zhang, J., Koppel, A., Bedi, A.S., Szepesvari, C., Wang, M.: Variational policy gradient method for reinforcement learning with general utilities. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)","key":"2658_CR37"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02658-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-025-02658-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-025-02658-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T06:02:21Z","timestamp":1746770541000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-025-02658-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,7]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2658"],"URL":"https:\/\/doi.org\/10.1007\/s10957-025-02658-9","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"type":"print","value":"0022-3239"},{"type":"electronic","value":"1573-2878"}],"subject":[],"published":{"date-parts":[[2025,4,7]]},"assertion":[{"value":"13 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"43"}}