arXiv subjects

Ratnesh Sharma

Publications and source records attributed to Ratnesh Sharma.

7 recordsLinked to original sources

arXiv2024

Taking Second-life Batteries from Exhausted to Empowered using Experiments, Data Analysis, and Health Estimation

The reuse of retired electric vehicle batteries in grid energy storage offers environmental and economic benefits. This study concentrates on health monitoring algorithms for retired batteries deployed in grid storage. Over 15 months of testing, we collect, analyze, and publicize a dataset of second-life batteries, implementing a cycling protocol simulating grid energy storage load profiles within a 3-4 V voltage window. Four machine-learning-based health estimation models, relying on online-accessible features and initial capacity, are compared, with the selected model achieving a mean absolute percentage error below 2.3% on test data. Additionally, an adaptive online health estimation algorithm is proposed by integrating a clustering-based method, thus limiting estimation errors during online deployment. These results showcase the feasibility of repurposing retired batteries for second-life applications. Based on obtained data and power demand, these second-life batteries exhibit potential for over a decade of grid energy storage use.

cs.LG↗

arXiv2024

Towards a BMS2 Design Framework: Adaptive Data-driven State-of-health Estimation for Second-Life Batteries with BIBO Stability Guarantees

A key challenge that is currently hindering the widespread use of retired electric vehicle (EV) batteries for second-life (SL) applications is the ability to accurately estimate and monitor their state of health (SOH). Second-life battery systems can be sourced from different battery packs with lack of knowledge of their historical usage. To tackle the in-the-field use of SL batteries, this paper introduces an online adaptive health estimation approach with guaranteed bounded-input-bounded-output (BIBO) stability. This method relies exclusively on operational data that can be accessed in real time from SL batteries. The effectiveness of the proposed approach is shown on a laboratory aged experimental data set of retired EV batteries. The estimator gains are dynamically adapted to accommodate the distinct characteristics of each individual cell, making it a promising candidate for future SL battery management systems (BMS2).

eess.SY↗

arXiv2020

Adaptive Traffic Control with Deep Reinforcement Learning: Towards State-of-the-art and Beyond

In this work, we study adaptive data-guided traffic planning and control using Reinforcement Learning (RL). We shift from the plain use of classic methods towards state-of-the-art in deep RL community. We embed several recent techniques in our algorithm that improve the original Deep Q-Networks (DQN) for discrete control and discuss the traffic-related interpretations that follow. We propose a novel DQN-based algorithm for Traffic Control (called TC-DQN+) as a tool for fast and more reliable traffic decision-making. We introduce a new form of reward function which is further discussed using illustrative examples with comparisons to traditional traffic control methods.

cs.LG↗

arXiv2020

Stochastic Decision-Making Model for Aggregation of Residential Units with PV-Systems and Storages

Many residential energy consumers have installed photovoltaic (PV) panels and energy storage systems. These residential users can aggregate and participate in the energy markets. A stochastic decision making model for an aggregation of these residential units for participation in two-settlement markets is proposed in this paper. Scenarios are generated using Seasonal Autoregressive Integrated Moving Average (SARIMA) model and joint probability distribution function of the forecast errors to model the uncertainties of the real-time prices, PV generations and demands. The proposed scenario generation model of this paper treats forecast errors as random variable, which allows to reflect new information observed in the real-time market into scenario generation process without retraining SARIMA or re-fitting probability distribution functions over the forecast errors. This approach significantly improves the computational time of the proposed model. A simulation study is conducted for an aggregation of 6 residential units, and the results highlights the benefits of aggregation as well as the proposed stochastic decision-making model.

math.OC↗

arXiv2019

Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation

Increasing adoption of solar photovoltaic (PV) presents new challenges to modern power grid due to its variable and intermittent nature. Fluctuating outputs from PV generation can cause the grid violating voltage operation limits. PV smart inverters (SIs) provide a fast-response method to regulate voltage by modulating real and/or reactive power at the connection point. Yet existing local autonomous control scheme of SIs is based on local information without coordination, which can lead to suboptimal performance. In this paper, a deep reinforcement learning (DRL) based algorithm is developed and implemented for coordinating multiple SIs. The reward scheme of the DRL is carefully designed to ensure voltage operation limits of the grid are met with more effective utilization of SI reactive power. The proposed DRL agent for voltage control can learn its policy through interaction with massive offline simulations, and adapts to load and solar variations. The performance of the DRL agent is compared against the local autonomous control on the IEEE 37 node system with thousands of scenarios. The results show a properly trained DRL agent can intelligently coordinate different SIs for maintaining grid voltage within allowable ranges, achieving reduction of PV production curtailment, and decreasing system losses.

eess.SY↗

arXiv2019

Energy Predictive Models with Limited Data using Transfer Learning

In this paper, we consider the problem of developing predictive models with limited data for energy assets such as electricity loads, PV power generations, etc. We specifically investigate the cases where the amount of historical data is not sufficient to effectively train the prediction model. We first develop an energy predictive model based on convolutional neural network (CNN) which is well suited to capture the interaday, daily, and weekly cyclostationary patterns, trends and seasonalities in energy assets time series. A transfer learning strategy is then proposed to address the challenge of limited training data. We demonstrate our approach on a usecase of daily electricity demand forecasting. we show practicing the transfer learning strategy on the CNN model results in significant improvement to existing forecasting methods.

cs.LG↗

arXiv2015

SDP-based State Estimation of Multi-phase Active Distribution Networks using micro-PMUs

Distribution system state estimation (DSSE) is an essential tool for operation of distribution networks, the results of which enables the operator to have a thorough observation of the system. Thus, most distribution management systems (DMS) include a single-phase state estimator. Due to non-convexity of the SE problem, heuristic and Newton methods do not guarantee the global solution. In contrast, SDP based SE is more promising to guarantee the globally optimal solution since it represents and solves the problem in a convex format. However, the observability of the power system is highly vulnerable to the set of measurements while employing the SDP-based SE, which is addressed in this report. An algorithm is proposed to generate additional measurements using the measurement data already gathered. The SDP-based SE is very sensitive to the level of noise in large power networks. Also, bad data detection algorithms proposed for Newton methods do not work for the SDP-based SE method due to larger number of state variables in SDP representation of power network. In this report, an algorithm is proposed to generate additional measurements using the measurement data already gathered in order to solve the observability issue. A network separation algorithm is developed to solve the entire problem for smaller sub-networks which include micro-PMUs to mitigate the adverse effects of noise for huge networks. An algorithm based on redundancy test is also developed for bad data detection. The algorithms are tested on single phase and multiphase test systems. The algorithms are applied EPRI Circuit 5 (2998-bus) test feeder to demonstrate the flexibility of the algorithms developed.

eess.SY↗