Hendro Wicaksono, Martin Trat, Atit Bashyal, Tina Boroukhian, Mine Felder, Mischa Ahrens, Janek Bender, Sebastian Groß, Daniel Steiner, Christoph July, Christoph Dorus, Thorsten Zoerner
{"title":"Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes","authors":"Hendro Wicaksono, Martin Trat, Atit Bashyal, Tina Boroukhian, Mine Felder, Mischa Ahrens, Janek Bender, Sebastian Groß, Daniel Steiner, Christoph July, Christoph Dorus, Thorsten Zoerner","doi":"10.1007/s00170-024-13372-7","DOIUrl":null,"url":null,"abstract":"<p>The transition towards renewable electricity provides opportunities for manufacturing companies to save electricity costs through participating in demand response programs. End-to-end implementation of demand response systems focusing on manufacturing power consumers is still challenging due to multiple stakeholders and subsystems that generate a heterogeneous and large amount of data. This work develops an approach utilizing artificial intelligence for a demand response system that optimizes industrial consumers’ and prosumers’ production-related electricity costs according to time-variable electricity tariffs. It also proposes a semantic middleware architecture that utilizes an ontology as the semantic integration model for handling heterogeneous data models between the system’s modules. This paper reports on developing and evaluating multiple machine learning models for power generation forecasting and load prediction, and also mixed-integer linear programming as well as reinforcement learning for production optimization considering dynamic electricity pricing represented as Green Electricity Index (GEI). The experiments show that the hybrid auto-regressive long-short-term-memory model performs best for solar and convolutional neural networks for wind power generation forecasting. Random forest, <i>k</i>-nearest neighbors, ridge, and gradient-boosting regression models perform best in load prediction in the considered use cases. Furthermore, this research found that the reinforcement-learning-based approach can provide generic and scalable solutions for complex and dynamic production environments. Additionally, this paper presents the validation of the developed system in the German industrial environment, involving a utility company and two small to medium-sized manufacturing companies. It shows that the developed system benefits the manufacturing company that implements fine-grained process scheduling most due to its flexible rescheduling capacities.</p>","PeriodicalId":50345,"journal":{"name":"International Journal of Advanced Manufacturing Technology","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Advanced Manufacturing Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s00170-024-13372-7","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
The transition towards renewable electricity provides opportunities for manufacturing companies to save electricity costs through participating in demand response programs. End-to-end implementation of demand response systems focusing on manufacturing power consumers is still challenging due to multiple stakeholders and subsystems that generate a heterogeneous and large amount of data. This work develops an approach utilizing artificial intelligence for a demand response system that optimizes industrial consumers’ and prosumers’ production-related electricity costs according to time-variable electricity tariffs. It also proposes a semantic middleware architecture that utilizes an ontology as the semantic integration model for handling heterogeneous data models between the system’s modules. This paper reports on developing and evaluating multiple machine learning models for power generation forecasting and load prediction, and also mixed-integer linear programming as well as reinforcement learning for production optimization considering dynamic electricity pricing represented as Green Electricity Index (GEI). The experiments show that the hybrid auto-regressive long-short-term-memory model performs best for solar and convolutional neural networks for wind power generation forecasting. Random forest, k-nearest neighbors, ridge, and gradient-boosting regression models perform best in load prediction in the considered use cases. Furthermore, this research found that the reinforcement-learning-based approach can provide generic and scalable solutions for complex and dynamic production environments. Additionally, this paper presents the validation of the developed system in the German industrial environment, involving a utility company and two small to medium-sized manufacturing companies. It shows that the developed system benefits the manufacturing company that implements fine-grained process scheduling most due to its flexible rescheduling capacities.
期刊介绍:
The International Journal of Advanced Manufacturing Technology bridges the gap between pure research journals and the more practical publications on advanced manufacturing and systems. It therefore provides an outstanding forum for papers covering applications-based research topics relevant to manufacturing processes, machines and process integration.