artificial intelligence blockchain building energy management building information modelling data analytics data mining energy efficiency Energy efficient building energy management energy performance indicator flexibility measurement industry 4.0 industry 4.0 maturity assessment Internet of Things knowledge management linked data machine learning manufacturing Ontology ontology engineering ontology population product configuration product lifecycle management production planning and control requirement engineering resource efficient manufacturing smart cities Supply Chain 4.0 sustainability virtual engineering
2023 |
Wicaksono Hendro; Trat, Martin.; Bashyal Atit; Boroukhian Tina; Felder Mine; Ahrens Mischa; Bender Janek; Groß Sebastian; Steiner Daniel; July Christoph; Dorus Christoph; Zoerner Thorsten Artificial Intelligence Enabled Dynamic Demand Response System for Maximizing the Use of Green Electricity in Production Processes, Robotics and Computer-Integrated Manufacturing Journal Article Forthcoming Robotics and Computer-Integrated Manufacturing, Forthcoming. Abstract | BibTeX | Tags: artificial intelligence, Artificial neural network, machine learning, Ontology, production scheduling, reinforcement learning @article{Wicaksono2023, title = {Artificial Intelligence Enabled Dynamic Demand Response System for Maximizing the Use of Green Electricity in Production Processes, Robotics and Computer-Integrated Manufacturing}, author = {Wicaksono, Hendro; Trat, Martin.; Bashyal, Atit; Boroukhian, Tina; Felder, Mine; Ahrens, Mischa; Bender, Janek; Groß, Sebastian; Steiner, Daniel; July, Christoph; Dorus, Christoph; Zoerner, Thorsten}, year = {2023}, date = {2023-12-30}, journal = {Robotics and Computer-Integrated Manufacturing}, 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, Artificial neural network, machine learning, Ontology, production scheduling, reinforcement learning}, pubstate = {forthcoming}, 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. |
Krstevski Stefan; Fatahi Valilai, Omid; Wicaksono Hendro In Proceedings of the 2023 10th International Conference on Industrial Engineering and Applications (ICIEAEU '23), pp. 98–106, Association for Computing Machinery, New York, NY, USA, 2023. Abstract | Links | BibTeX | Tags: energy efficiency, manufacturing, operation research, production planning and control, production scheduling, sustainability @inproceedings{Krstevski2023, title = {Integrating Real-Time Dynamic Electricity Price Forecast into Job Shop Production Scheduling Model with Multiple Machine Environments}, author = {Krstevski, Stefan; Fatahi Valilai, Omid; Wicaksono, Hendro }, url = {https://doi.org/10.1145/3587889.3587905}, doi = {10.1145/3587889.3587905}, year = {2023}, date = {2023-06-09}, booktitle = {In Proceedings of the 2023 10th International Conference on Industrial Engineering and Applications (ICIEAEU '23)}, pages = {98–106}, publisher = {Association for Computing Machinery, New York, NY, USA}, abstract = {One of the challenges in the transition towards green electricity is the intermittence of power generated by renewable sources. Thus, power consumers, including the manufacturing industry, must adapt their activities and processes to green electricity supply. Real-time dynamic pricing is an approach to encourage electricity consumers to change their consumption patterns by lowering prices when the availability of green electricity in the grid is high. Due to the introduction of real-time electricity pricing, manufacturing companies must adapt their production planning by integrating dynamic price information into their production scheduling. Our research focuses on extending the basic production scheduling mathematical model by introducing real-time power pricing in the model. The prices are built based on the current proportion of green electricity in the grid represented in the green electricity index (GEI) with one-hour intervals. This paper also illustrates a scenario of how to use the model. Our future research will further extend the model addressing the flexibility of manufacturing shop floors (e.g. adding buffer, retooling, and setup time) and validate the model in two small and medium manufacturing enterprises.}, keywords = {energy efficiency, manufacturing, operation research, production planning and control, production scheduling, sustainability}, pubstate = {published}, tppubtype = {inproceedings} } One of the challenges in the transition towards green electricity is the intermittence of power generated by renewable sources. Thus, power consumers, including the manufacturing industry, must adapt their activities and processes to green electricity supply. Real-time dynamic pricing is an approach to encourage electricity consumers to change their consumption patterns by lowering prices when the availability of green electricity in the grid is high. Due to the introduction of real-time electricity pricing, manufacturing companies must adapt their production planning by integrating dynamic price information into their production scheduling. Our research focuses on extending the basic production scheduling mathematical model by introducing real-time power pricing in the model. The prices are built based on the current proportion of green electricity in the grid represented in the green electricity index (GEI) with one-hour intervals. This paper also illustrates a scenario of how to use the model. Our future research will further extend the model addressing the flexibility of manufacturing shop floors (e.g. adding buffer, retooling, and setup time) and validate the model in two small and medium manufacturing enterprises. |
2013 |
Wicaksono, Hendro; Prohl, Enrst Victor; Ovtcharova, Jivka Hyper heuristc based production process scheduling to improve productivity in sustainable manufacturing Inproceedings Proceeding the 22nd International Conference on Production Research, Brazil, 28 July – 1 August, 2013, 2013. Abstract | BibTeX | Tags: energy efficiency, hyper heuristics, manufacturing, production scheduling @inproceedings{Wicaksono2013d, title = {Hyper heuristc based production process scheduling to improve productivity in sustainable manufacturing}, author = {Hendro Wicaksono and Enrst Victor Prohl and Jivka Ovtcharova}, year = {2013}, date = {2013-08-01}, booktitle = {Proceeding the 22nd International Conference on Production Research, Brazil, 28 July – 1 August, 2013}, abstract = {In recent years, increased customer-demand in individualized and timely products has changed the playing field for manufacturing industries. The production process is perpetually gaining complexity whereas its life-cycle is shortening. Additionally, a growing ecological conscience enforces the consideration of energy effi-ciency. Intelligent production process scheduling is a core instrument to increase efficiency of the value-added chain whilst acknowledging existing constraints. This paper introduces a hyper-heuristic based framework for production scheduling that incorporates economic and ecological aspects. In contrast to meta heuristics that aim for easily reusable solution-methods to NP-Hard scheduling problems, hyper-heuristics try to automate the search for the best solution methods. Thus a hyper-heuristic does not seek for the best solution, but for a heuristic that solves the problem best. Other than conventional scheduling described in lit-erature, the proposed approach in this paper copes with many aspects (constraints and objectives) at once, such as retooling activities, energy efficiency, energy peak load avoidance, product lot size, operation multi-plicity, and shift work. Furthermore, this paper will introduce the incorporation possibilities of prior knowledge coming from both human and machine learning (data mining) into the hyper-heuristic framework. }, keywords = {energy efficiency, hyper heuristics, manufacturing, production scheduling}, pubstate = {published}, tppubtype = {inproceedings} } In recent years, increased customer-demand in individualized and timely products has changed the playing field for manufacturing industries. The production process is perpetually gaining complexity whereas its life-cycle is shortening. Additionally, a growing ecological conscience enforces the consideration of energy effi-ciency. Intelligent production process scheduling is a core instrument to increase efficiency of the value-added chain whilst acknowledging existing constraints. This paper introduces a hyper-heuristic based framework for production scheduling that incorporates economic and ecological aspects. In contrast to meta heuristics that aim for easily reusable solution-methods to NP-Hard scheduling problems, hyper-heuristics try to automate the search for the best solution methods. Thus a hyper-heuristic does not seek for the best solution, but for a heuristic that solves the problem best. Other than conventional scheduling described in lit-erature, the proposed approach in this paper copes with many aspects (constraints and objectives) at once, such as retooling activities, energy efficiency, energy peak load avoidance, product lot size, operation multi-plicity, and shift work. Furthermore, this paper will introduce the incorporation possibilities of prior knowledge coming from both human and machine learning (data mining) into the hyper-heuristic framework. |