M. Mgt. Chandana Priya Nivarthi

Autonomous Energy Systems (AESy)

Fax: +49 561 804-6022
Email: chandana.nivarthi[at]uni-kassel[dot]de

Publications

[ 2022 ]
[ 2021 ]
[ 2020 ]

2022[ to top ]

Nivarthi, C.P., Vogt, S., Sick, B.: Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting In: International Conference on Machine Learning and Applications (ICMLA). bll 1530–1536. IEEE (2022). https://doi.org/10.1109/ICMLA55696.2022.00240.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
@inproceedings{nivarthi2022unified, abstract = {Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1530–1536}, publisher = {IEEE}, title = {Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting}, year = 2022 }
%0 Conference Paper %1 nivarthi2022unified %A Nivarthi, Chandana Priya %A Vogt, Stephan %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2022 %I IEEE %P 1530--1536 %R 10.1109/ICMLA55696.2022.00240 %T Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting %U https://ieeexplore.ieee.org/document/10068974 %X Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
Nivarthi, C.P.: Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems In: Tomforde, S. en Krupitzer, C. (reds) Organic Computing -- Doctoral Dissertation Colloquium 2021. bll 47–59. kassel university press (2022).
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.
@incollection{nivarthi2022transfer, abstract = {Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.}, author = {Nivarthi, Chandana Priya}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {47–59}, publisher = {kassel university press}, title = {Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems}, year = 2022 }
%0 Book Section %1 nivarthi2022transfer %A Nivarthi, Chandana Priya %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 47--59 %T Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems %X Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.

2021[ to top ]

Gruhl, C., Hannan, A., Huang, Z., Nivarthi, C., Vogt, S.: The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models In: Workshop on Self-Improving System Integration (SISSY), ACSOS. bll 204–209. IEEE (2021). https://doi.org/10.1109/acsos-c52956.2021.00055.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2021problem, author = {Gruhl, Christian and Hannan, Abdul and Huang, Zhixin and Nivarthi, Chandana and Vogt, Stephan}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {204–209}, publisher = {IEEE}, title = {The Problem with Real-World Novelty Detection – Issues in Multivariate Probabilistic Models}, year = 2021 }
%0 Conference Paper %1 gruhl2021problem %A Gruhl, Christian %A Hannan, Abdul %A Huang, Zhixin %A Nivarthi, Chandana %A Vogt, Stephan %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 204--209 %R 10.1109/acsos-c52956.2021.00055 %T The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models

2020[ to top ]

Singh, A., Nivarthi, C.P., Akhilesh, K.B.: Implementing IoT in India---A Look at Macro Issues and a Framework for Recommendations In: Akhilesh, K.B. en Möller, D.P.F. (reds) Smart Technologies : Scope and Applications. bll 35–52. Springer (2020). https://doi.org/10.1007/978-981-13-7139-4_3.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
IoT is the latest technology on the block, promising to be a panacea for multiple maladies. India, too, is looking at IoT with palpable interest. In this paper, we look the four major stakeholders in India, at the forefront of adoption and use of IoT, namely the academia, startups, large manufacturers, and the government. A representative of each class of the stakeholders is studied in depth, and the problems that they are facing with respect to implementation are identified. It turns out that a substantial chunk of the macrolevel implementation issues faced by all stakeholders are situated on the threads of one-to-one interactions of these stakeholders, with collaboration and standardization issues enveloping these one-to-one interactions. We propose a framework for formulating solution recommendations for these macroissues and give an example of its use.
@inbook{singh2020implementing, abstract = {IoT is the latest technology on the block, promising to be a panacea for multiple maladies. India, too, is looking at IoT with palpable interest. In this paper, we look the four major stakeholders in India, at the forefront of adoption and use of IoT, namely the academia, startups, large manufacturers, and the government. A representative of each class of the stakeholders is studied in depth, and the problems that they are facing with respect to implementation are identified. It turns out that a substantial chunk of the macrolevel implementation issues faced by all stakeholders are situated on the threads of one-to-one interactions of these stakeholders, with collaboration and standardization issues enveloping these one-to-one interactions. We propose a framework for formulating solution recommendations for these macroissues and give an example of its use.}, author = {Singh, Apoorvaa and Nivarthi, Chandana Priya and Akhilesh, K. B.}, booktitle = {Smart Technologies : Scope and Applications}, chapter = 3, editor = {Akhilesh, K. B. and M{\"o}ller, Dietmar P. F.}, keywords = {not_ies}, pages = {35–52}, publisher = {Springer}, title = {Implementing IoT in India—A Look at Macro Issues and a Framework for Recommendations}, year = 2020 }
%0 Book Section %1 singh2020implementing %A Singh, Apoorvaa %A Nivarthi, Chandana Priya %A Akhilesh, K. B. %B Smart Technologies : Scope and Applications %D 2020 %E Akhilesh, K. B. %E Möller, Dietmar P. F. %I Springer %P 35--52 %R 10.1007/978-981-13-7139-4_3 %T Implementing IoT in India---A Look at Macro Issues and a Framework for Recommendations %X IoT is the latest technology on the block, promising to be a panacea for multiple maladies. India, too, is looking at IoT with palpable interest. In this paper, we look the four major stakeholders in India, at the forefront of adoption and use of IoT, namely the academia, startups, large manufacturers, and the government. A representative of each class of the stakeholders is studied in depth, and the problems that they are facing with respect to implementation are identified. It turns out that a substantial chunk of the macrolevel implementation issues faced by all stakeholders are situated on the threads of one-to-one interactions of these stakeholders, with collaboration and standardization issues enveloping these one-to-one interactions. We propose a framework for formulating solution recommendations for these macroissues and give an example of its use. %& 3 %@ 978-981-13-7139-4
Nivarthi, C.P., Akhilesh, K.B.: Cybercare---Role of Cyber Security in Healthcare Industry In: Akhilesh, K.B. en Möller, D.P.F. (reds) Smart Technologies : Scope and Applications. bll 291–304. Springer (2020). https://doi.org/10.1007/978-981-13-7139-4_22.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
The Internet of Things (IoT) is the trend that designs the next generation technologies with the capability to impact the entire spectrum of business. It conceptualizes connection with anyone at any time with anything through any network at anyplace to serve any service. It can be defined as the interconnection of unique smart devices, services and systems. With IoT at play, automation is achievable in any field. The IoT offers wide range of `smart' solutions such as smart cities, smart homes, smart retail, smart banking, smart manufacturing and smart health care. This paper gives an overview on healthcare industry, identifies the primary stakeholders of the ecosystem, discusses the current challenges faced by the industry because of digitization and IoT devices and also suggests preventive measures.
@inbook{nivarthi2020cybercare, abstract = {The Internet of Things (IoT) is the trend that designs the next generation technologies with the capability to impact the entire spectrum of business. It conceptualizes connection with anyone at any time with anything through any network at anyplace to serve any service. It can be defined as the interconnection of unique smart devices, services and systems. With IoT at play, automation is achievable in any field. The IoT offers wide range of `smart' solutions such as smart cities, smart homes, smart retail, smart banking, smart manufacturing and smart health care. This paper gives an overview on healthcare industry, identifies the primary stakeholders of the ecosystem, discusses the current challenges faced by the industry because of digitization and IoT devices and also suggests preventive measures.}, author = {Nivarthi, Chandana Priya and Akhilesh, K. B.}, booktitle = {Smart Technologies : Scope and Applications}, chapter = 22, editor = {Akhilesh, K. B. and M{\"o}ller, Dietmar P. F.}, keywords = {not_ies}, pages = {291–304}, publisher = {Springer}, title = {Cybercare—Role of Cyber Security in Healthcare Industry}, year = 2020 }
%0 Book Section %1 nivarthi2020cybercare %A Nivarthi, Chandana Priya %A Akhilesh, K. B. %B Smart Technologies : Scope and Applications %D 2020 %E Akhilesh, K. B. %E Möller, Dietmar P. F. %I Springer %P 291--304 %R 10.1007/978-981-13-7139-4_22 %T Cybercare---Role of Cyber Security in Healthcare Industry %X The Internet of Things (IoT) is the trend that designs the next generation technologies with the capability to impact the entire spectrum of business. It conceptualizes connection with anyone at any time with anything through any network at anyplace to serve any service. It can be defined as the interconnection of unique smart devices, services and systems. With IoT at play, automation is achievable in any field. The IoT offers wide range of `smart' solutions such as smart cities, smart homes, smart retail, smart banking, smart manufacturing and smart health care. This paper gives an overview on healthcare industry, identifies the primary stakeholders of the ecosystem, discusses the current challenges faced by the industry because of digitization and IoT devices and also suggests preventive measures. %& 22 %@ 978-981-13-7139-4