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. |
Sarafanov Egor; Fatahi Valilai, Omid; Wicaksono Hendro Causal analysis of the adoption willingness of artificial intelligence in project management Conference Forthcoming Proceeding of Intelligent Systems Conference (IntelliSys) 2023 , Forthcoming. Abstract | BibTeX | Tags: artificial intelligence, causal analysis, causal inference, causal model, project management, structural equation modelling @conference{Sarafanov2023, title = {Causal analysis of the adoption willingness of artificial intelligence in project management}, author = {Sarafanov, Egor; Fatahi Valilai, Omid; Wicaksono, Hendro}, year = {2023}, date = {2023-09-07}, booktitle = {Proceeding of Intelligent Systems Conference (IntelliSys) 2023 }, abstract = {Artificial intelligence (AI) technologies have great potential to improve decision-making and automation processes in various sectors, including project management. AI technologies could significantly contribute to overcoming the complexity of project management through process automation, cognitive insight, and engagement. However, the adoption of AI technologies still faces many challenges due to technical, human resource-related, organizational, and legal issues. Our research identified the potential factors that lead to the willingness of people and organizations to adopt AI technologies in project management. This paper proposes a causal model describing multivariate causal relationships between the driving factors and the willingness to adopt AI. The causal model is a set of hypotheses evaluated through a survey and causal analysis using the structural equation modeling (SEM) technique. The analysis focused on six factors influencing the willingness to adopt AI in project management, i.e., performance effectiveness, price, previous experience, feedback, complexity, and complementary technologies. Our research found that the perception of the high effectiveness of AI technologies leading to higher profits and overall the state of the project is the main factor influencing the willingness to adopt AI technologies in project management.}, keywords = {artificial intelligence, causal analysis, causal inference, causal model, project management, structural equation modelling}, pubstate = {forthcoming}, tppubtype = {conference} } Artificial intelligence (AI) technologies have great potential to improve decision-making and automation processes in various sectors, including project management. AI technologies could significantly contribute to overcoming the complexity of project management through process automation, cognitive insight, and engagement. However, the adoption of AI technologies still faces many challenges due to technical, human resource-related, organizational, and legal issues. Our research identified the potential factors that lead to the willingness of people and organizations to adopt AI technologies in project management. This paper proposes a causal model describing multivariate causal relationships between the driving factors and the willingness to adopt AI. The causal model is a set of hypotheses evaluated through a survey and causal analysis using the structural equation modeling (SEM) technique. The analysis focused on six factors influencing the willingness to adopt AI in project management, i.e., performance effectiveness, price, previous experience, feedback, complexity, and complementary technologies. Our research found that the perception of the high effectiveness of AI technologies leading to higher profits and overall the state of the project is the main factor influencing the willingness to adopt AI technologies in project management. |
Agung Teguh Wibowo Almais Adi Susilo, Agus Naba Moechammad Sarosa Cahyo Crysdian Imam Tazi Mokhamad Amin Hariyadi Muhammad Aziz Muslim Puspa Miladin Nuraida Safitri Abdul Basid Yunifa Miftachul Arif Mohammad Singgih Purwanto Diyan Parwatiningtyas Hendro Wicaksono Principal Component Analysis-Based Data Clustering for Labeling of Level Damage Sector in Post-Natural Disasters Journal Article IEEE Access, 11 , pp. 74590 - 74601, 2023. Abstract | Links | BibTeX | Tags: artificial intelligence, machine learning, PCA @article{Almais2023, title = {Principal Component Analysis-Based Data Clustering for Labeling of Level Damage Sector in Post-Natural Disasters}, author = {Agung Teguh Wibowo Almais, Adi Susilo, Agus Naba, Moechammad Sarosa, Cahyo Crysdian, Imam Tazi, Mokhamad Amin Hariyadi, Muhammad Aziz Muslim, Puspa Miladin Nuraida Safitri Abdul Basid, Yunifa Miftachul Arif, Mohammad Singgih Purwanto, Diyan Parwatiningtyas, Hendro Wicaksono}, url = {https://ieeexplore.ieee.org/abstract/document/10123944}, doi = {10.1109/ACCESS.2023.3275852}, year = {2023}, date = {2023-05-12}, journal = {IEEE Access}, volume = {11}, pages = {74590 - 74601}, abstract = {Post-disaster sector damage data is data that has features or criteria in each case the level of damage to the post-natural disaster sector data. These criteria data are building conditions, building structures, building physicals, building functions, and other supporting conditions. Data on the level of damage to the post-natural disaster sector used in this study amounted to 216 data, each of which has 5 criteria for damage to the post-natural disaster sector. Then PCA is used to look for labels in each data. The results of these labels will be used to cluster data based on the value scale of the results of data normalization in the PCA process. In the data normalization process at PCA, the data is divided into 2 components, namely PC1 and PC2. Each component has a variance ratio and eigenvalue generated in the PCA process. For PC1 it has a variance ratio of 85.17% and an eigenvalue of 4.28%, while PC2 has a variance ratio of 9.36% and an eigenvalue of 0.47%. The results of data normalization are then made into a 2-dimensional graph to see the data visualization of the results of each main component (PC). The result is that there is 3 data cluster using a value scale based on the PCA results chart. The coordinate value (n) of each cluster is cluster 1 ( $\text{n} < 0$ ), cluster 2 ( $0\le \text{n} < 2$ ), and cluster 3 ( $\text{n}\ge 2$ ). To test these 3 groups of data, it is necessary to conduct trials by comparing the original target data, there are two experiments, namely testing the PC1 results based on the original target data, and the PC2 results based on the original target data. The result is that there are 2 updates, the first is that the distribution of PC1 data is very good when comparing the distribution of data with PC2 in grouping data, because the eigenvalue of PC1 is greater than that of PC2. While second, the results of testing the PC1 data with the original target data produce good data grouping, because the original target data which has a value of 1 (slightly damaged) occupies the coordinates of group 1 (n < 0), the original target data which has a value of 2 (moderately damaged) occupies group 2 coordinates ( $0\le \text{n} < 2$ ), and for the original target data the value 3 (heavily damaged) occupies group 3 coordinates ( $\text{n}\ge 2$ ). Therefore, it can be concluded that PCA, which so far has been used by many studies as feature reduction, this study uses PCA for labeling unsupervised data so that it has appropriate data labels for further processing.}, keywords = {artificial intelligence, machine learning, PCA}, pubstate = {published}, tppubtype = {article} } Post-disaster sector damage data is data that has features or criteria in each case the level of damage to the post-natural disaster sector data. These criteria data are building conditions, building structures, building physicals, building functions, and other supporting conditions. Data on the level of damage to the post-natural disaster sector used in this study amounted to 216 data, each of which has 5 criteria for damage to the post-natural disaster sector. Then PCA is used to look for labels in each data. The results of these labels will be used to cluster data based on the value scale of the results of data normalization in the PCA process. In the data normalization process at PCA, the data is divided into 2 components, namely PC1 and PC2. Each component has a variance ratio and eigenvalue generated in the PCA process. For PC1 it has a variance ratio of 85.17% and an eigenvalue of 4.28%, while PC2 has a variance ratio of 9.36% and an eigenvalue of 0.47%. The results of data normalization are then made into a 2-dimensional graph to see the data visualization of the results of each main component (PC). The result is that there is 3 data cluster using a value scale based on the PCA results chart. The coordinate value (n) of each cluster is cluster 1 ( $text{n} < 0$ ), cluster 2 ( $0le text{n} < 2$ ), and cluster 3 ( $text{n}ge 2$ ). To test these 3 groups of data, it is necessary to conduct trials by comparing the original target data, there are two experiments, namely testing the PC1 results based on the original target data, and the PC2 results based on the original target data. The result is that there are 2 updates, the first is that the distribution of PC1 data is very good when comparing the distribution of data with PC2 in grouping data, because the eigenvalue of PC1 is greater than that of PC2. While second, the results of testing the PC1 data with the original target data produce good data grouping, because the original target data which has a value of 1 (slightly damaged) occupies the coordinates of group 1 (n < 0), the original target data which has a value of 2 (moderately damaged) occupies group 2 coordinates ( $0le text{n} < 2$ ), and for the original target data the value 3 (heavily damaged) occupies group 3 coordinates ( $text{n}ge 2$ ). Therefore, it can be concluded that PCA, which so far has been used by many studies as feature reduction, this study uses PCA for labeling unsupervised data so that it has appropriate data labels for further processing. |
2021 |
Wicaksono Hendro; Boroukhian, Tina; Bashyal Atit A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning Book Chapter Freitag, Michael ; Kotzab, Herbert ; Megow, Nicole (Ed.): pp. 155-181, Springer, 2021, ISBN: 978-3-030-88662-2. Abstract | Links | BibTeX | Tags: artificial intelligence, causal analysis, causal inference, causal model, energy transition, linked data, machine learning, Ontology, project management, structural equation modelling, sustainability @inbook{Wicaksono2021, title = {A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning}, author = {Wicaksono, Hendro; Boroukhian, Tina; Bashyal, Atit }, editor = {Freitag, Michael and Kotzab, Herbert and Megow, Nicole}, doi = {10.1007/978-3-030-88662-2_8}, isbn = {978-3-030-88662-2}, year = {2021}, date = {2021-12-31}, pages = {155-181}, publisher = {Springer}, abstract = {The spread of demand-response (DR) programs in Europe is a slow but steady process to optimize the use of renewable energy in different sectors including manufacturing. A demand-response program promotes changes of electricity consumption patterns at the end consumer side to match the availability of renewable energy sources through price changes or incentives. This research develops a system that aims to engage manufacturing power consumers through price- and incentive-based DR programs. The system works on data from heterogeneous systems at both supply and demand sides, which are linked through a semantic middleware, instead of centralized data integration. An ontology is used as the integration information model of the semantic middleware. This chapter explains the concept of constructing the ontology by utilizing relational database to ontology mapping techniques, reusing existing ontologies such as OpenADR, SSN, SAREF, etc., and applying ontology alignment methods. Machine learning approaches are developed to forecast both the power generated from renewable energy sources and the power demanded by manufacturing consumers based on their processes. The forecasts are the groundworks to calculate the dynamic electricity price introduced for the DR program. This chapter presents different neural network architectures and compares the experiment results. We compare the results of Deep Neural Network (DNN), Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), and Hybrid architectures. This chapter focuses on the initial phase of the research where we focus on the ontology development method and machine learning experiments using power generation datasets.}, keywords = {artificial intelligence, causal analysis, causal inference, causal model, energy transition, linked data, machine learning, Ontology, project management, structural equation modelling, sustainability}, pubstate = {published}, tppubtype = {inbook} } The spread of demand-response (DR) programs in Europe is a slow but steady process to optimize the use of renewable energy in different sectors including manufacturing. A demand-response program promotes changes of electricity consumption patterns at the end consumer side to match the availability of renewable energy sources through price changes or incentives. This research develops a system that aims to engage manufacturing power consumers through price- and incentive-based DR programs. The system works on data from heterogeneous systems at both supply and demand sides, which are linked through a semantic middleware, instead of centralized data integration. An ontology is used as the integration information model of the semantic middleware. This chapter explains the concept of constructing the ontology by utilizing relational database to ontology mapping techniques, reusing existing ontologies such as OpenADR, SSN, SAREF, etc., and applying ontology alignment methods. Machine learning approaches are developed to forecast both the power generated from renewable energy sources and the power demanded by manufacturing consumers based on their processes. The forecasts are the groundworks to calculate the dynamic electricity price introduced for the DR program. This chapter presents different neural network architectures and compares the experiment results. We compare the results of Deep Neural Network (DNN), Long Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), and Hybrid architectures. This chapter focuses on the initial phase of the research where we focus on the ontology development method and machine learning experiments using power generation datasets. |
Wicaksono, Hendro Accelerating Energy Transition to Green Electricity through Artificial Intelligence Presentation 24.08.2021. Abstract | Links | BibTeX | Tags: artificial intelligence, data analytics, energy transition, machine learning @misc{Wicaksono2021c, title = {Accelerating Energy Transition to Green Electricity through Artificial Intelligence}, author = {Wicaksono, Hendro }, doi = {10.31219/osf.io/tcrkh}, year = {2021}, date = {2021-08-24}, abstract = {The presentation focuses on the role of artificial intelligence in accelerating the transition to green electricity in Germany. It discusses the challenges in the transition towards green electricity in Germany and the role of digitalization through smart metering. One of the methods to adopt and disseminate the use of green electricity is demand response. The presentation explains the definition of demand response concept and gives an example of projects that applies neural network to forecast power generation and consumption to enable calculation of dynamic electricity price. Finally, the presentation explores the adoption of green electricity in broader contexts, e.g., cities and districts, through a data-driven smart energy platform.}, keywords = {artificial intelligence, data analytics, energy transition, machine learning}, pubstate = {published}, tppubtype = {presentation} } The presentation focuses on the role of artificial intelligence in accelerating the transition to green electricity in Germany. It discusses the challenges in the transition towards green electricity in Germany and the role of digitalization through smart metering. One of the methods to adopt and disseminate the use of green electricity is demand response. The presentation explains the definition of demand response concept and gives an example of projects that applies neural network to forecast power generation and consumption to enable calculation of dynamic electricity price. Finally, the presentation explores the adoption of green electricity in broader contexts, e.g., cities and districts, through a data-driven smart energy platform. |
2019 |
Kusumawardana Arya; Habibi, Muhammad Afnan; Wibawanto Slamet; Wicaksono Hendro; Prasetya Yoga; Nurrahman Rizqi Coordination Power Control Of DC Water Pump System using Dual-loop Control and Consensus Algorithm Inproceedings 2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE), pp. 37-42, IEEE, 2019. Links | BibTeX | Tags: algorithm, artificial intelligence, energy efficiency, Energy efficient building @inproceedings{Kusumawardana2020, title = {Coordination Power Control Of DC Water Pump System using Dual-loop Control and Consensus Algorithm}, author = {Kusumawardana, Arya; Habibi, Muhammad Afnan; Wibawanto,Slamet; Wicaksono, Hendro; Prasetya, Yoga; Nurrahman, Rizqi }, url = {https://ieeexplore.ieee.org/document/8981473}, doi = {10.1109/ICEEIE47180.2019.8981473}, year = {2019}, date = {2019-02-01}, booktitle = {2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE)}, pages = {37-42}, publisher = {IEEE}, keywords = {algorithm, artificial intelligence, energy efficiency, Energy efficient building}, pubstate = {published}, tppubtype = {inproceedings} } |
Publications and Talks
2023 |
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. |
Causal analysis of the adoption willingness of artificial intelligence in project management Conference Forthcoming Proceeding of Intelligent Systems Conference (IntelliSys) 2023 , Forthcoming. |
Principal Component Analysis-Based Data Clustering for Labeling of Level Damage Sector in Post-Natural Disasters Journal Article IEEE Access, 11 , pp. 74590 - 74601, 2023. |
2021 |
A Demand-Response System for Sustainable Manufacturing Using Linked Data and Machine Learning Book Chapter Freitag, Michael ; Kotzab, Herbert ; Megow, Nicole (Ed.): pp. 155-181, Springer, 2021, ISBN: 978-3-030-88662-2. |
Accelerating Energy Transition to Green Electricity through Artificial Intelligence Presentation 24.08.2021. |
2019 |
Coordination Power Control Of DC Water Pump System using Dual-loop Control and Consensus Algorithm Inproceedings 2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE), pp. 37-42, IEEE, 2019. |