Soumya Kundu

Soumya Kundu, Karanjit Kalsi, Scott Backhaus

With increasing availability of communication and control infrastructure at the distribution systems, it is expected that the distributed energy resources (DERs) will take an active part in future power systems operations. One of the main challenges associated with integration of DERs in grid planning and control is in estimating the available flexibility in a collection of (heterogeneous) DERs, each of which may have local constraints that vary over time. In this work, we present a geometric approach for approximating the flexibility of a DER in modulating its active and reactive power consumption. The proposed method is agnostic about the type and model of the DERs, thereby facilitating a plug-and-play approach, and allows scalable aggregation of the flexibility of a collection of (heterogeneous) DERs at the distributed system level. Simulation results are presented to demonstrate the performance of the proposed method.

Sai Pushpak Nandanoori, Indrasis Chakraborty, Thiagarajan Ramachandran et al.

The potential of distributed energy resources in providing grid services can be maximized with the recent advancements in demand side control. Effective utilization of this control strategy requires the knowledge of aggregate flexibility of the distributed energy resources (DERs). Recent works have shown that the aggregate flexibility of DERs can be modeled as a virtual battery (VB) whose state evolution is governed by a first order system including self-dissipation. The VB parameters (self-dissipation rate, energy capacity) are obtained by solving an optimization problem which minimizes the tracking performance of the ensemble and the proposed first-order model. For the identified first order model, time-varying power limits are calculated using binary search algorithms. Finally, this proposed framework is demonstrated for different homogeneous and heterogeneous ensembles consisting of air conditioners (ACs) and electric water heaters (EWHs).

Kaustav Bhattacharjee, Soumya Kundu, Indrasis Chakraborty et al.

Accurate net load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models.

Kaustav Bhattacharjee, Soumya Kundu, Indrasis Chakraborty et al.

Net load forecasting is crucial for energy planning and facilitating informed decision-making regarding trade and load distributions. However, evaluating forecasting models' performance against benchmark models remains challenging, thereby impeding experts' trust in the model's performance. In this context, there is a demand for technological interventions that allow scientists to compare models across various timeframes and solar penetration levels. This paper introduces a visual analytics-based application designed to compare the performance of deep-learning-based net load forecasting models with other models for probabilistic net load forecasting. This application employs carefully selected visual analytic interventions, enabling users to discern differences in model performance across different solar penetration levels, dataset resolutions, and hours of the day over multiple months. We also present observations made using our application through a case study, demonstrating the effectiveness of visualizations in aiding scientists in making informed decisions and enhancing trust in net load forecasting models.

Deepthi Sen, Indrasis Chakraborty, Soumya Kundu et al.

With the expected rise in behind-the-meter solar penetration within the distribution networks, there is a need to develop time-series forecasting methods that can reliably predict the net-load, accurately quantifying its uncertainty and variability. This paper presents a deep learning method to generate probabilistic forecasts of day-ahead net-load at 15-min resolution, at various solar penetration levels. Our proposed deep-learning based architecture utilizes the dimensional reduction, from a higher-dimensional input to a lower-dimensional latent space, via a convolutional Autoencoder (AE). The extracted features from AE are then utilized to generate probability distributions across the latent space, by passing the features through a kernel-embedded Perron-Frobenius (kPF) operator. Finally, long short-term memory (LSTM) layers are used to synthesize time-series probability distributions of the forecasted net-load, from the latent space distributions. The models are shown to deliver superior forecast performance (as per several metrics), as well as maintain superior training efficiency, in comparison to existing benchmark models. Detailed analysis is carried out to evaluate the model performance across various solar penetration levels (up to 50\%), prediction horizons (e.g., 15\,min and 24\,hr ahead), and aggregation level of houses, as well as its robustness against missing measurements.

Soumya Kundu, Saptarshi Bhattacharya, Himanshu Sharma et al.

This report documents recent technical work on developing and validating stochastic occupancy models in commercial buildings, performed by the Pacific Northwest National Laboratory (PNNL) as part of the Sensor Impact Evaluation and Verification project under the U.S. Department of Energy (DOE) Building Technologies Office (BTO). In this report, we present our work on developing and validating inhomogeneous semi-Markov chain models for generating sequences of zone-level occupancy presence and occupancy counts in a commercial building. Real datasets are used to learn and validate the generative occupancy models. Relevant metrics such as normalized Jensen-Shannon distance (NJSD) are used to demonstrate the ability of the models to express realistic occupancy behavioral patterns.

Thiagarajan Ramachandran, Andrew Reiman, Sai Pushpak Nandanoori et al.

Low-to-medium voltage distribution networks are experiencing rising levels of distributed energy resources, including renewable generation, along with improved sensing, communication, and automation infrastructure. As such, state estimation methods for distribution systems are becoming increasingly relevant as a means to enable better control strategies that can both leverage the benefits and mitigate the risks associated with high penetration of variable and uncertain distributed generation resources. The primary challenges of this problem include modeling complexities (nonlinear, non-convex power-flow equations), limited availability of sensor measurements, and high penetration of uncertain renewable generation. This paper formulates the distribution system state estimation as a nonlinear, weighted, least squares problem, based on sensor measurements as well as forecast data (both load and generation). We investigate the sensitivity of state estimator accuracy to (load/generation) forecast uncertainties, sensor accuracy, and sensor coverage levels.

Gianluca Bianchin, Fabio Pasqualetti, Soumya Kundu

This paper investigates the use of Infrastructure-To-Vehicle (I2V) communication to generate routing suggestions for drivers in transportation systems, with the goal of optimizing a measure of overall network congestion. We define link-wise levels of trust to tolerate the non-cooperative behavior of part of the driver population, and we propose a real-time optimization mechanism that adapts to the instantaneous network conditions and to sudden changes in the levels of trust. Our framework allows us to quantify the improvement in travel time in relation to the degree at which drivers follow the routing suggestions. We then study the resilience of the system, measured as the smallest change in routing choices that results in roads reaching their maximum capacity. Interestingly, our findings suggest that fluctuations in the extent to which drivers follow the provided routing suggestions can cause failures of certain links. These results imply that the benefits of using Infrastructure-To-Vehicle communication come at the cost of new fragilities, that should be appropriately addressed in order to guarantee the reliable operation of the infrastructure.

Indrasis Chakraborty, Sai Pushpak Nandanoori, Soumya Kundu

Recent studies have shown that the aggregated dynamic flexibility of an ensemble of thermostatic loads can be modeled in the form of a virtual battery. The existing methods for computing the virtual battery parameters require the knowledge of the first-principle models and parameter values of the loads in the ensemble. In real-world applications, however, it is likely that the only available information are end-use measurements such as power consumption, room temperature, device on/off status, etc., while very little about the individual load models and parameters are known. We propose a transfer learning based deep network framework for calculating virtual battery state of a given ensemble of flexible thermostatic loads, from the available end-use measurements. This proposed framework extracts first order virtual battery model parameters for the given ensemble. We illustrate the effectiveness of this novel framework on different ensembles of ACs and WHs.

Zhiyuan Liu, Soumya Kundu, Lijun Chen et al.

In this paper we propose a new Koopman operator approach to the decomposition of nonlinear dynamical systems using Koopman Gramians. We introduce the notion of an input-Koopman operator, and show how input-Koopman operators can be used to cast a nonlinear system into the classical state-space form, and identify conditions under which input and state observable functions are well separated. We then extend an existing method of dynamic mode decomposition for learning Koopman operators from data known as deep dynamic mode decomposition to systems with controls or disturbances. We illustrate the accuracy of the method in learning an input-state separable Koopman operator for an example system, even when the underlying system exhibits mixed state-input terms. We next introduce a nonlinear decomposition algorithm, based on Koopman Gramians, that maximizes internal subsystem observability and disturbance rejection from unwanted noise from other subsystems. We derive a relaxation based on Koopman Gramians and multi-way partitioning for the resulting NP-hard decomposition problem. We lastly illustrate the proposed algorithm with the swing dynamics for an IEEE 39-bus system.

Enoch Yeung, Soumya Kundu, Nathan Hodas

The Koopman operator has recently garnered much attention for its value in dynamical systems analysis and data-driven model discovery. However, its application has been hindered by the computational complexity of extended dynamic mode decomposition; this requires a combinatorially large basis set to adequately describe many nonlinear systems of interest, e.g. cyber-physical infrastructure systems, biological networks, social systems, and fluid dynamics. Often the dictionaries generated for these problems are manually curated, requiring domain-specific knowledge and painstaking tuning. In this paper we introduce a deep learning framework for learning Koopman operators of nonlinear dynamical systems. We show that this novel method automatically selects efficient deep dictionaries, outperforming state-of-the-art methods. We benchmark this method on partially observed nonlinear systems, including the glycolytic oscillator and show it is able to predict quantitatively 100 steps into the future, using only a single timepoint, and qualitative oscillatory behavior 400 steps into the future.