arXiv subjects
Publications and source records attributed to Paritosh Ramanan.
We propose a collaborative meta-learning framework for distributed Bayesian optimization matching centralized performance without raw-data exchange. We show gradient sharing leaks client observations, with leakage worsening as the search converges and queries concentrate near the optimum. We evaluate a differentially private defense and characterize its privacy-utility trade-off.
Electrification of ethane cracking offers a promising pathway to industrial decarbonization, provided that the electricity is sourced from renewable energy. However, integrating electrified chemical plant microgrids with a decarbonized power grid requires joint operations planning between Independent System Operators and chemical plants, which is hindered by the highly confidential nature of plant operational data. In this paper, we propose a privacy-friendly decentralized framework based on data isolation that jointly optimizes the Unit Commitment problem in the power system and microgrid scheduling in electrified ethane cracker plants. The framework employs the Alternating Direction Method of Multipliers, augmented with an auxiliary system-level penalty that accelerates convergence, allowing each subsystem to solve its local subproblem and share only minimal coordination signals. To reflect real-world conditions, numerical experiments are conducted on the ACTIVSg2000 test case, a synthetic model of the Texas transmission network, with 26 chemical plants identified from Texas mapped to their nearest grid connection points. In doing so, we characterize the cost of privacy-friendly decomposition on joint power and chemical system decisions, showing that data isolation results in consistently small optimality gaps, and that its emissions consequences are load-dependent and non-monotone.
The electrification of chemical process heating is essential to industrial decarbonization and sustainable manufacturing of chemical products. Joint optimization of electrified chemical process heating units and electric power systems is needed to achieve decarbonized operation of both sectors. In this work, we introduce a joint optimization model that identifies the optimal unit commitment of power systems and optimal operation of electrified steam cracking microgrids for olefins production. A mixed-integer linear programming (MILP) model is developed to optimize the hourly operational plan of 26 ethylene plants and the main power system in Texas. We propose a two-stage solution method to solve the resulting large-scale MILP problem efficiently. In the first stage, we apply Benders decomposition with LP-relaxed subproblems to decouple microgrid operations from the main power system. In the second stage, we use the first-stage optimal solution as a warm-starting point for the MILP. This two-stage approach reduces the average solution time by 93.5% compared to direct solution of the MILP. Results show that the largest overall greenhouse gas (GHG) emission reduction for both power systems and microgrids is achieved when the electrification level of steam cracking units is at 30%. Above 30% electrification level, a higher electrification level leads to higher overall GHG emissions and steady increase in operating costs, particularly on the microgrid side. Increasing renewables contributions in the electric power system helps debottleneck the electrification efforts and facilitate holistic decarbonization. We also remark that the optimal operational plan of electrified steam cracking microgrids also exhibit strong spatiotemporal patterns.
Root cause analysis (RCA) in networked industrial systems, such as supply chains and power networks, is notoriously difficult due to unknown and dynamically evolving interdependencies among geographically distributed clients. These clients represent heterogeneous physical processes and industrial assets equipped with sensors that generate large volumes of nonlinear, high-dimensional, and heterogeneous IoT data. Classical RCA methods require partial or full knowledge of the system's dependency graph, which is rarely available in these complex networks. While federated learning (FL) offers a natural framework for decentralized settings, most existing FL methods assume homogeneous feature spaces and retrainable client models. These assumptions are not compatible with our problem setting. Different clients have different data features and often run fixed, proprietary models that cannot be modified. This paper presents a federated cross-client interdependency learning methodology for feature-partitioned, nonlinear time-series data, without requiring access to raw sensor streams or modifying proprietary client models. Each proprietary local client model is augmented with a Machine Learning (ML) model that encodes cross-client interdependencies. These ML models are coordinated via a global server that enforces representation consistency while preserving privacy through calibrated differential privacy noise. RCA is performed using model residuals and anomaly flags. We establish theoretical convergence guarantees and validate our approach on extensive simulations and a real-world industrial cybersecurity dataset.
Analysis of clinical data is a cornerstone of biomedical research with applications in areas such as genomic testing and response characterization of therapeutic drugs. Maintaining strict privacy controls is essential because such data typically contains personally identifiable health information of patients. At the same time, regulatory compliance often requires study managers to demonstrate the integrity and authenticity of participant data used in analyses. Balancing these competing requirements of privacy preservation and verifiable accountability remains a critical challenge. In this paper, we present CoSMeTIC, a zero-knowledge computational framework that proposes computational Sparse Merkle Trees (SMTs) as a means to generate verifiable inclusion and exclusion proofs for individual participants' data in clinical studies. We formally analyze the zero-knowledge properties of CoSMeTIC and evaluate its computational efficiency through extensive experiments. We demonstrate the framework on Huntington's disease and HIV-1 case studies, using simulated CAG-repeat cohorts derived from published summary statistics and published de-identified clinical lab measurements of virus samples. Using two-sample Kolmogorov-Smirnov and likelihood-ratio hypothesis tests, along with logistic-regression-based genomic analyses on the de-identified datasets, we show that CoSMeTIC achieves strong privacy guarantees while maintaining statistical fidelity. Our results suggest that CoSMeTIC provides a scalable and practical alternative for achieving regulatory compliance with rigorous privacy protection in large-scale clinical research.
Ethylene is one of the most ubiquitous chemicals and is predominantly produced through steam cracking. However, steam cracking is highly energy- and carbon-intensive, making its decarbonization a priority. Electrifying the steam cracking process is a promising pathway to reduce carbon emissions. However, this is challenged by the intrinsic conflict between the continuous operational nature of ethylene plants and the intermittent nature of renewable energy sources in modern power systems. A viable solution is to pursue a gradual electrification pathway and operate an ethylene plant as a microgrid that adopts diverse energy sources. To optimize the operational strategy of such a microgrid considering uncertainties in renewable energy generation and market prices, in this work, we propose a novel superstructure for electrified steam cracking systems and introduce a stochastic optimization framework for minimizing the operating costs. Results from a case study show that, given the current status of the power grid and renewable energy generation technologies, the process economics and sustainability of electrified steam cracking do not always favor higher decarbonization levels. To overcome this barrier, electricity from the main grid must be cleaner and cheaper, and energy storage costs per unit stored must decrease. Furthermore, it is important for both chemical and power systems stakeholders must seamlessly coordinate with each other to pursue joint optimization in operation.
Industrial control systems (ICS) form the operational backbone of critical infrastructure networks (CIN) such as power grids, water supply systems, and gas pipelines. As cyber threats to these systems escalate, regulatory agencies are imposing stricter compliance requirements to ensure system-wide security and reliability. A central challenge, however, is enabling regulators to verify the effectiveness of detection mechanisms without requiring utilities to disclose sensitive operational data. In this paper, we introduce zkSTAR, a zero-knowledge based cyberattack detection framework that leverages zk-SNARKs to enable regulatory compliance while delivering provable detection guarantees with complete data privacy. Our approach builds on established residual-based statistical hypothesis testing methods applied to state-space detection models. Specifically, we design a two-pronged zk-SNARK architecture that enforces (i) temporal consistency of the state-space dynamics and (ii) statistical consistency of the detection tests, enabling regulators to verify correctness and prevent suppression of alarms without visibility into utility-level data. We formally analyze the soundness and zero-knowledge properties of our framework and validate its practical feasibility through computational experiments on real-world ICS datasets. Our work demonstrates that zkSNARKs can provide a compliant, scalable, privacy-preserving alternative for detecting data-driven cyberattacks on ICS driven critical infrastructure networks.
The exponential growth of computational workloads is surpassing the capabilities of conventional architectures, which are constrained by fundamental limits. In-memory computing (IMC) with RRAM provides a promising alternative by providing analog computations with significant gains in latency and energy use. However, existing algorithms developed for conventional architectures do not translate to IMC, particularly for constrained optimization problems where frequent matrix reprogramming remains cost-prohibitive for IMC applications. Here we present a distributed in-memory primal-dual hybrid gradient (PDHG) method, specifically co-designed for arrays of RRAM devices. Our approach minimizes costly write cycles, incorporates robustness against device non-idealities, and leverages a symmetric block-matrix formulation to unify operations across distributed crossbars. We integrate a physics-based simulation framework called MELISO+ to evaluate performance under realistic device conditions. Benchmarking against GPU-accelerated solvers on large-scale linear programs demonstrates that our RRAM-based solver achieves comparable accuracy with up to three orders of magnitude reductions in energy consumption and latency. These results demonstrate the first PDHG-based LP solver implemented on RRAMs, showcasing the transformative potential of algorithm-hardware co-design for solving large-scale optimization through distributed in-memory computing.
Exponential growth in global computing demand is exacerbated due to the higher-energy requirements of conventional architectures, primarily due to energy-intensive data movement. In-memory computing with Resistive Random Access Memory (RRAM) addresses this by co-integrating memory and processing, but faces significant hurdles related to device-level non-idealities and poor scalability for large computing tasks. Here, we introduce MELISO+ (In-Memory Linear Solver), a full-stack, distributed framework for energy-efficient in-memory computing. MELISO+ proposes a novel two-tier error correction mechanism to mitigate device non-idealities and develops a distributed RRAM computing framework to enable matrix computations exceeding dimensions of $65,000\times65,000$. This approach reduces first- and second-order arithmetic errors due to device non-idealities by over $90\%$, enhances energy efficiency by three to five orders of magnitude, and decreases latency 100-fold. Hence, MELISO+ allows lower-precision RRAM devices to outperform high-precision device alternatives in accuracy, energy and latency metrics. By unifying algorithm-hardware co-design with scalable architecture, MELISO+ significantly advances sustainable, high-dimensional computing suitable for applications like large language models and generative AI.
Industrial control systems are a fundamental component of critical infrastructure networks (CIN) such as gas, water, and power. With the growing risk of cyberattacks, regulatory compliance requirements are also increasing for large scale critical infrastructure systems comprising multiple utility stakeholders. The primary goal of regulators is to ensure overall system stability with recourse to trustworthy stakeholder attack detection. However, adhering to compliance requirements requires stakeholders to also disclose sensor and control data to regulators, raising privacy concerns. In this paper, we present a cyberattack detection framework PRECISE, that utilizes differentially private (DP) hypothesis tests geared towards enhancing regulatory confidence while alleviating privacy concerns of CIN stakeholders. The hallmark of our approach is a two phase privacy scheme applying Laplacian DP to covariance matrix disclosures and Gaussian Differential Privacy (GDP) to state-space residuals derived from a Non-Linear Kalman Filter LSTM model. We formally characterize the GDP-induced test statistic via the non-central chi-squared distribution and derive tight bounds on misclassification rates and equivalent DP levels of significance. Theoretically, we show that our method induces a misclassification error rate comparable to the non-DP cases while delivering robust privacy guarantees. Using real-world HAI and ORNL-PS datasets, we demonstrate that under strong differential privacy guarantees on both covariance and residual disclosures, PRECISE matches non-DP detection outcomes in over 88% of cases within 600 seconds of attack onset for the HAI dataset and over 92% for the ORNL-PS dataset, while maintaining false alarm rates below 9% across all tested DP parameter configurations.
Data engineering pipelines are essential - albeit costly - components of predictive analytics frameworks requiring significant engineering time and domain expertise for carrying out tasks such as data ingestion, preprocessing, feature extraction, and feature engineering. In this paper, we propose ADEPT, an automated data engineering pipeline via text embeddings. At the core of the ADEPT framework is a simple yet powerful idea that the entropy of embeddings corresponding to textually dense raw format representation of time series can be intuitively viewed as equivalent (or in many cases superior) to that of numerically dense vector representations obtained by data engineering pipelines. Consequently, ADEPT uses a two step approach that (i) leverages text embeddings to represent the diverse data sources, and (ii) constructs a variational information bottleneck criteria to mitigate entropy variance in text embeddings of time series data. ADEPT provides an end-to-end automated implementation of predictive models that offers superior predictive performance despite issues such as missing data, ill-formed records, improper or corrupted data formats and irregular timestamps. Through exhaustive experiments, we show that the ADEPT outperforms the best existing benchmarks in a diverse set of datasets from large-scale applications across healthcare, finance, science and industrial internet of things. Our results show that ADEPT can potentially leapfrog many conventional data pipeline steps thereby paving the way for efficient and scalable automation pathways for diverse data science applications.
Operations and maintenance (O&M) scheduling is a critical problem in leased manufacturing systems, with significant implications for operational efficiency, cost optimization, and machine reliability. Solving this problem involves navigating complex trade-offs between machine-level degradation risks, production throughput, and maintenance team logistics across multi-site manufacturing networks. Conventional approaches rely on large-scale Mixed Integer Programming (MIP) models, which, while capable of yielding optimal solutions, suffer from prolonged computational times and scalability limitations. To overcome these challenges, we propose AttenMfg, a novel decision-making framework that leverages multi-head attention (MHA), tailored for complex optimization problems. The proposed framework incorporates several key innovations, including constraint-aware masking procedures and novel reward functions that explicitly embed mathematical programming formulations into the MHA structure. The resulting attention-based model (i) reduces solution times from hours to seconds, (ii) ensures feasibility of the generated schedules under operational and logistical constraints, (iii) achieves solution quality on par with exact MIP formulations, and (iv) demonstrates strong generalizability across diverse problem settings. These results highlight the potential of attention-based learning to revolutionize O&M scheduling in leased manufacturing systems.
Stochastic optimization problems in large-scale multi-stakeholder networked systems (e.g., power grids and supply chains) rely on data-driven scenarios to encapsulate complex spatiotemporal interdependencies. However, centralized aggregation of stakeholder data is challenging due to the existence of data silos resulting from computational and logistical bottlenecks. In this paper, we present SplitVAEs, a decentralized scenario generation framework that leverages variational autoencoders to generate high-quality scenarios without moving stakeholder data. With the help of experiments on distributed memory systems, we demonstrate the broad applicability of SplitVAEs in a variety of domain areas that are dominated by a large number of stakeholders. Our experiments indicate that SplitVAEs can learn spatial and temporal interdependencies in large-scale networks to generate scenarios that match the joint historical distribution of stakeholder data in a decentralized manner. Our experiments show that SplitVAEs deliver robust performance compared to centralized, state-of-the-art benchmark methods while significantly reducing data transmission costs, leading to a scalable, privacy-enhancing alternative to scenario generation.
Advanced sensors and IoT devices have improved the monitoring and control of complex industrial enterprises. They have also created an interdependent fabric of geographically distributed process operations (clients) across these enterprises. Granger causality is an effective approach to detect and quantify interdependencies by examining how one client's state affects others over time. Understanding these interdependencies captures how localized events, such as faults and disruptions, can propagate throughout the system, possibly causing widespread operational impacts. However, the large volume and complexity of industrial data pose challenges in modeling these interdependencies. This paper develops a federated approach to learning Granger causality. We utilize a linear state space system framework that leverages low-dimensional state estimates to analyze interdependencies. This addresses bandwidth limitations and the computational burden commonly associated with centralized data processing. We propose augmenting the client models with the Granger causality information learned by the server through a Machine Learning (ML) function. We examine the co-dependence between the augmented client and server models and reformulate the framework as a standalone ML algorithm providing conditions for its sublinear and linear convergence rates. We also study the convergence of the framework to a centralized oracle model. Moreover, we include a differential privacy analysis to ensure data security while preserving causal insights. Using synthetic data, we conduct comprehensive experiments to demonstrate the robustness of our approach to perturbations in causality, the scalability to the size of communication, number of clients, and the dimensions of raw data. We also evaluate the performance on two real-world industrial control system datasets by reporting the volume of data saved by decentralization.
Operations and maintenance (O&M) is a fundamental problem in wind energy systems with far reaching implications for reliability and profitability. Optimizing O&M is a multi-faceted decision optimization problem that requires a careful balancing act across turbine level failure risks, operational revenues, and maintenance crew logistics. The resulting O&M problems are typically solved using large-scale mixed integer programming (MIP) models, which yield computationally challenging problems that require either long-solution times, or heuristics to reach a solution. To address this problem, we introduce a novel decision-making framework for wind farm O&M that builds on a multi-head attention (MHA) models, an emerging artificial intelligence methods that are specifically designed to learn in rich and complex problem settings. The development of proposed MHA framework incorporates a number of modeling innovations that allows explicit embedding of MIP models within an MHA structure. The proposed MHA model (i) significantly reduces the solution time from hours to seconds, (ii) guarantees feasibility of the proposed solutions considering complex constraints that are omnipresent in wind farm O&M, (iii) results in significant solution quality compared to the conventional MIP formulations, and (iv) exhibits significant transfer learning capability across different problem settings.
The Von Neumann bottleneck, a fundamental challenge in conventional computer architecture, arises from the inability to execute fetch and data operations simultaneously due to a shared bus linking processing and memory units. This bottleneck significantly limits system performance, increases energy consumption, and exacerbates computational complexity. Emerging technologies such as Resistive Random Access Memories (RRAMs), leveraging crossbar arrays, offer promising alternatives for addressing the demands of data-intensive computational tasks through in-memory computing of analog vector-matrix multiplication (VMM) operations. However, the propagation of errors due to device and circuit-level imperfections remains a significant challenge. In this study, we introduce MELISO (In-Memory Linear Solver), a comprehensive end-to-end VMM benchmarking framework tailored for RRAM-based systems. MELISO evaluates the error propagation in VMM operations, analyzing the impact of RRAM device metrics on error magnitude and distribution. This paper introduces the MELISO framework and demonstrates its utility in characterizing and mitigating VMM error propagation using state-of-the-art RRAM device metrics.
Battery diagnosis, prognosis and health management models play a critical role in the integration of battery systems in energy and mobility fields. However, large-scale deployment of these models is hindered by a myriad of challenges centered around data ownership, privacy, communication, and processing. State-of-the-art battery diagnosis and prognosis methods require centralized collection of data, which further aggravates these challenges. Here we propose a federated battery prognosis model, which distributes the processing of battery standard current-voltage-time-usage data in a privacy-preserving manner. Instead of exchanging raw standard current-voltage-time-usage data, our model communicates only the model parameters, thus reducing communication load and preserving data confidentiality. The proposed model offers a paradigm shift in battery health management through privacy-preserving distributed methods for battery data processing and remaining lifetime prediction.
Cybersecurity of Industrial Cyber-Physical Systems is drawing significant concerns as data communication increasingly leverages wireless networks. A lot of data-driven methods were develope for detecting cyberattacks, but few are focused on distinguishing them from equipment faults. In this paper, we develop a data-driven framework that can be used to detect, diagnose, and localize a type of cyberattack called covert attacks on networked industrial control systems. The framework has a hybrid design that combines a variational autoencoder (VAE), a recurrent neural network (RNN), and a Deep Neural Network (DNN). This data-driven framework considers the temporal behavior of a generic physical system that extracts features from the time series of the sensor measurements that can be used for detecting covert attacks, distinguishing them from equipment faults, as well as localize the attack/fault. We evaluate the performance of the proposed method through a realistic simulation study on a networked power transmission system as a typical example of ICS. We compare the performance of the proposed method with the traditional model-based method to show its applicability and efficacy.