2025
Bashyal, Atit; Alnahas, Hani; Boroukhian, Tina; Wicaksono, Hendro
Demand response based industrial energy management with focus on consumption of renewable energy: a deep reinforcement learning approach Journal Article
In: Procedia Computer Science, vol. 253, pp. 1442-1451, 2025.
Abstract | Links | BibTeX | Tags: artificial intelligence, demand response system, energy management, manufacturing, reinforcement learning
@article{nokey,
title = {Demand response based industrial energy management with focus on consumption of renewable energy: a deep reinforcement learning approach},
author = {Atit Bashyal and Hani Alnahas and Tina Boroukhian and Hendro Wicaksono},
url = {https://www.sciencedirect.com/science/article/pii/S1877050925002145},
doi = {https://doi.org/10.1016/j.procs.2025.01.206},
year = {2025},
date = {2025-02-25},
journal = {Procedia Computer Science},
volume = {253},
pages = {1442-1451},
abstract = {Integrating Renewable Energy Resources (RESs) into power grids requires effective Demand Response (DR) programs. Despite high DR potential in industrial sectors, adoption lags behind that of residential and commercial sectors due to diverse operations and production continuity requirements. This paper explores a reinforcement learning (RL)-based DR scheme for energy-intensive industries, promoting the consumption of distributed Renewable Energy (RE) generation. Our approach introduces modifications to the existing Markov Decision Process (MDP) framework. It proposes a flexible reward structure that provides flexibility in balancing production requirements and promotes the consumption of RE. This study addresses the gap in industrial DR literature, emphasizing tailored DR solutions for industrial settings. The key highlight of our RL-based DR solution is its ability to facilitate a price-based DR scheme while promoting the integration of RE into the smart grid.
},
keywords = {artificial intelligence, demand response system, energy management, manufacturing, reinforcement learning},
pubstate = {published},
tppubtype = {article}
}
Integrating Renewable Energy Resources (RESs) into power grids requires effective Demand Response (DR) programs. Despite high DR potential in industrial sectors, adoption lags behind that of residential and commercial sectors due to diverse operations and production continuity requirements. This paper explores a reinforcement learning (RL)-based DR scheme for energy-intensive industries, promoting the consumption of distributed Renewable Energy (RE) generation. Our approach introduces modifications to the existing Markov Decision Process (MDP) framework. It proposes a flexible reward structure that provides flexibility in balancing production requirements and promotes the consumption of RE. This study addresses the gap in industrial DR literature, emphasizing tailored DR solutions for industrial settings. The key highlight of our RL-based DR solution is its ability to facilitate a price-based DR scheme while promoting the integration of RE into the smart grid.
2024
Wicaksono, Hendro; Trat, Martin; Bashyal, Atit; Boroukhian, Tina; Felder, Mine; Ahrens, Mischa; Bender, Janek; Groß, Sebastian; Steiner, Daniel; July, Christoph; others,
Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes Journal Article
In: The International Journal of Advanced Manufacturing Technology, pp. 1–25, 2024.
Abstract | Links | BibTeX | Tags: artificial intelligence, demand response system, energy management, machine learning, manufacturing, ontologies, reinforcement learning
@article{wicaksono2024artificial,
title = {Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes},
author = {Hendro Wicaksono and Martin Trat and Atit Bashyal and Tina Boroukhian and Mine Felder and Mischa Ahrens and Janek Bender and Sebastian Groß and Daniel Steiner and Christoph July and others},
url = {https://link.springer.com/article/10.1007/s00170-024-13372-7},
doi = {https://doi.org/10.1007/s00170-024-13372-7},
year = {2024},
date = {2024-03-22},
urldate = {2024-01-01},
journal = {The International Journal of Advanced Manufacturing Technology},
pages = {1–25},
publisher = {Springer London},
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.
},
keywords = {artificial intelligence, demand response system, energy management, machine learning, manufacturing, ontologies, reinforcement learning},
pubstate = {published},
tppubtype = {article}
}
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.