Chandana Priya Nivarthi

Ms. Chandana Priya Nivarthi


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
CNChandana Priya Nivarthi
Chandana Priya Nivarthi
SVStephan Vogt
Stephan Vogt
BSBernhard Sick
Bernhard Sick
Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.

19 December 2025 in Energy and AI
Verified
Journal Article
Open access
CNChandana Priya Nivarthi
Chandana Priya Nivarthi
ZHZhixin Huang
Zhixin Huang
CGChristian Gruhl
Christian Gruhl
BSBernhard Sick
Bernhard Sick


23 March 2026
Verified
Conference Paper
Open access
CNChandana Priya Nivarthi
Chandana Priya Nivarthi
Scalable zero-shot anomaly detection in photovoltaic inverter fleets is critical for minimizing downtime and ensuring renewable energy stability, yet labeled faults remain scarce and models often fail to generalize across devices. We propose TRACE, a self-supervised contrastive learning framework for scalable and label-free fault monitoring across photovoltaic (PV) inverter fleets. TRACE learns transferable embeddings from unlabeled multivariate sensor data by coupling a Transformer autoencoder with a Siamese contrastive network trained using reconstruction-aware positive augmentations and hard negative mining. The pretrained TRACE network generalizes across inverters, deriving latent representations that enable plug-and-play zero-shot anomaly detection without retraining. On a real PV dataset (12 inverters, 137 sensors, two weeks of data), TRACE achieves F1=0.993 on unseen inverters versus 0.777 for source-trained baselines, reducing deployment overhead by over 90% and outperforming state-of-the-art time-series AD methods by up to 17%. TRACE demonstrates a scalable path toward AI-enabled, self-supervised monitoring in renewable energy systems.