Energieeffiziente Steuerung von Kältemaschinen durch KI

Literaturverzeichnis

Datengetriebene und KI-basierte Methoden

[1] Rumelhart, D. E, Hinton, G. E, Williams, R. J.: Learning representations by back-propagating errors. In: Nature. Vol. 323, 1986, S. 533–536.

[2] LeCun, Y. et al.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE. Vol. 86, Nr. 11, 1998, S. 2278–2324.

[3] Breiman, L.: Random Forests. In: Machine Learning. Vol. 45, Nr. 1, 2001, S. 5–32.

[4] Hinton, G. E, Osindero, S, Teh, Y. W.: A fast learning algorithm for deep belief nets. In: Neural Computation. Vol. 18, Nr. 7, 2006, S. 1527–1554.

[5] Mnih, V. et al.: Playing Atari with Deep Reinforcement Learning. In: arXiv preprint arXiv:1312.5602, 2013.

[6] Silver, D. et al.: Mastering the game of Go with deep neural networks and tree search. In: Nature. Vol. 529, 2016, S. 484–489.

[7] Schulman, J. et al.: Proximal Policy Optimization Algorithms. In: arXiv preprint arXiv:1707.06347, 2017.

[8] Vaswani, A. et al.: Attention Is All You Need. In: Advances in Neural Information Processing Systems (NeurIPS). 2017.

[9] LeCun, Y, Bengio, Y, Hinton, G.: Deep learning. In: Nature. Vol. 521, 2015, S. 436–444.

[10] Ng, A.: Machine Learning Yearning. Mountain View (CA): deeplearning.ai, 2018. Online verfügbar unter: https://www.deeplearning.ai/

Digitale Zwillinge

[11] Grieves, M, Vickers, J.: Origins of the Digital Twin Concept. ResearchGate, Aug. 2016. Online verfügbar unter: https://www.researchgate.net/publication/307509727_Origins_of_the_Digital_Twin_Concept

[12] Diginomica: Grieves and Vickers – The history of digital twins. 13. Sep. 2023. Online verfügbar unter: https://diginomica.com/grieves-and-vickers-history-digital-twins

Cloud & Rechenkapazitäten

[13] Armbrust, M. et al.: A View of Cloud Computing. In: Communications of the ACM. Vol. 53, Nr. 4, 2010, S. 50–58.

[14] Hill, M. D, Marty, M. R.: Amdahl’s Law in the Multicore Era. In: Computer. Vol. 41, Nr. 7, 2008, S. 33–38.

[15] OpenAI: AI and Compute. San Francisco, 2018. Online verfügbar unter: https://openai.com/research/ai-and-compute

[16] Sun, Y. et al.: Summarizing CPU and GPU Design Trends with Product Data. In: arXiv preprint arXiv:1911.11313, 2019. Online verfügbar unter: https://arxiv.org/pdf/1911.11313

[17] Ward, J. S, Barker, A.: Undefined By Data: A Survey of Big Data Definitions. In: arXiv preprint arXiv:1309.5821, 2013

Internet of Things (IoT)

[18] Ashton, K.: That ‘Internet of Things’ Thing. In: RFID Journal. 2009. Online verfügbar unter: https://www.rfidjournal.com/articles/view?4986

[19] Atzori, L, Iera, A, Morabito, G.: The Internet of Things: A Survey. In: Computer Networks. Vol. 54, Nr. 15, 2010, S. 2787–2805.

[20] Lee, I, Lee, K.: The Internet of Things (IoT): Applications, investments, and challenges for enterprises. In: Business Horizons. Vol. 58, Nr. 4, 2015, S. 431–440.

Realtime Computing

[21] Buttazzo, G. C.: Hard Real-Time Computing Systems: Predictable Scheduling Algorithms and Applications. 4th ed. New York: Springer, 2020. ISBN 978-3-030-46956-9.

Edge Computing

[22] Elbamby, M. S. et al.: Wireless Edge Computing with Latency and Reliability Guarantees. In: IEEE Network. Vol. 33, Nr. 3, 2019, S. 70–78.

[23] Sánchez, J. M. G. et al.: Edge computing for cyber-physical systems: A systematic mapping study emphasizing trustworthiness. In: Journal of Systems Architecture. Vol. 128, 2022, Art. 102645.

Zugang zu Industriedaten, SCADA, BACNet

[24] Boyer, S. A.: SCADA: Supervisory Control and Data Acquisition. 4. Aufl. Research Triangle Park, NC: ISA – The International Society of Automation, 2010.

[25] International Organization for Standardization (ISO): ISO 9506: Industrial automation systems – Manufacturing Message Specification (MMS). Genf: ISO, 2003.

[26] Bushby, S. T.: BACnet Today: A Supplement to ASHRAE Journal. BACnet International, 2002. Online verfügbar unter: https://bacnet.org/wp-content/uploads/sites/4/2022/06/AJ-4-91.pdf

[27] Fraunhofer IPA: Big Data in der Produktion – Studie zur Datennutzung in der Industrie. Stuttgart, 2014. Online verfügbar unter: https://zenodo.org/record/803099

Moderne Optimierungsverfahren

[28] Schweidtmann, A. M., Zhang, D., von Stosch, M.: A review and perspective on hybrid modeling methodologies. In: Digital Chemical Engineering. Vol. 10, 2024, Art. 100136.

[29] Wu, Z., Christofides, P. D., Wu, W., Wang, Y., Abdullah, F., Alnajdi, A., Kadakia, Y.: A tutorial review of machine learning-based model predictive control methods. In: Reviews in Chemical Engineering. Vol. 41, No. 4, 2025, S. 359–400.

[30] Dogru, O., Xie, J., Prakash, O., Chiplunkar, R., Soesanto, J., Chen, H., Velswamy, K., Ibrahim, F., Huang, B.: Reinforcement learning in process industries: Review and perspective. In: IEEE/CAA Journal of Automatica Sinica. Vol. 11, No. 2, 2024, S. 283–300.

[31] McKinsey & Company: Digital twins: The next frontier of factory optimization. 2024. Online verfügbar unter: https://www.mckinsey.com/capabilities/operations/our-insights/digital-twins-the-next-frontier-of-factory-optimization

[32] Karkaria, V., Tsai, Y., Chen, Y., Chen, W.: An optimization-centric review on integrating artificial intelligence and digital twin technologies in manufacturing. In: Engineering Optimization. Vol. 57, No. 1, 2025, S. 161–207.

[33] Rahman, M. A., Shahrior, M. F., Iqbal, K., Abushaiba, A. A.: Enabling Intelligent Industrial Automation: A Review of Machine Learning Applications with Digital Twin and Edge AI Integration. In: Automation. Vol. 6, No. 3, 2025, Art. 37.

Forschungsvorhaben

[34] Bundesministerium für Umwelt, Naturschutz und nukleare Sicherheit. Klimaschutzplan 2050: Klimaschutzpolitische Grundsätze und Ziele der Bundesregierung. Berlin: BMU, Arbeitsgruppe IK III 1, November 2016.

[35] Preuß, G. Energiebedarf für Kältetechnik in Deutschland. Im Auftrag des Forschungsrats Kältetechnik e. V. Hrsg. vom VDMA. Frankfurt am Main: VDMA, 2011.

[36] VDMA. VDMA 24247-1: Energieeffizienz von Kälteanlagen. Teil 1: Klimaschutzbeitrag von Kälte- und Klimaanlagen – Verbesserung der Energieeffizienz – Verminderung von treibhausrelevanten Emissionen. Frankfurt am Main: Verband Deutscher Maschinen- und Anlagenbau e. V., November 2011.

Anwendungsfall

[37] VDMA 24247-7. Energieeffizienz von Kälteanlagen – Teil 7: Regelung, Energiemanagement und effiziente Betriebsführung. Frankfurt am Main: Verband Deutscher Maschinen- und Anlagenbau e. V. (VDMA), 2021.

Model-Based Reinforcement Learning

[38] Wikipedia. Markov decision process. [online]. 2024 [Zugriff am: 03.11.2025]. Verfügbar unter: https://en.wikipedia.org/wiki/Markov_decision_process

[39] Moerland, T. M.; Broekens, J.; Plaat, A.; Jonker, C. M. Model-based Reinforcement Learning: A Survey. Foundations and Trends® in Machine Learning. 2023. Bd. 16, Nr. 1. DOI: 10.1561/2200000086.

[40] Polydoros, A. S.; Nalpantidis, L. Survey of Model-Based Reinforcement Learning: Applications on Robotics. Journal of Intelligent & Robotic Systems. 2017.

[41] Unit8 SA. Multiple Time Series, Pre-trained Models and Covariates — Darts Documentation. Online verfügbar unter: https://unit8co.github.io/darts/examples/01-multi-time-series-and-covariates.html

Prognosemodell

[42] Lim, B., Arık, S. Ö., Loeff, N. und Pfister, T. Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting. In: International Journal of Forecasting, 37(4), 2021, S. 1748–1764.

[43] Unit8 Co: Temporal Fusion Transformer (TFTModel). In: Darts Models – Forecasting. Online verfügbar unter https://unit8co.github.io/darts/generated_api/darts.models.forecasting.tft_model.html (letzter Zugriff: [Datum]), 2024.

[44] Unit8 Co.: Metrics — Darts Models – Forecasting. Online verfügbar unter https://unit8co.github.io/darts/generated_api/darts.metrics.metrics.html (letzter Zugriff: [Datum]), 2024.

Optimierungsverfahren

[45] Schulman, J., Levine, S., Moritz, P., Jordan, M., & Abbeel, P.: Trust Region Policy Optimization. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015, S. 1889–1897.

[46] SB3 Contrib: Trust Region Policy Optimization (TRPO). In: Stable Baselines3 Contrib – RL Algorithms. Online verfügbar unter https://sb3-contrib.readthedocs.io/en/master/modules/trpo.html (letzter Zugriff: [Datum]), 2024.