Advancing anomaly detection in computational workflows with active learning
Not Available
Raghavan, Krishnan↗
Engineering topics
Kiran, Mariam
Publications and source records attributed to Kiran, Mariam.
FlowBench Raw Data Archive
The repo that provides data archive for DOE PoSeiDon project. It also contains scripts and instructions to parse the data.
George, Papadimitriou↗
Oak Ridge National Laboratory's Strategic Research and Development Insights for Digital Twins
Oak Ridge National Laboratory (ORNL) is pleased to provide our response to the NITRD RFI on Digital Twins Research and Development. Digital twins are virtual representations of physical systems, leveraging real-time data to simulate and predict behaviors. ORNL is advancing digital twin technology across various disciplines, including neutron scattering, networking, science ecosystems, supercomputing, secure facilities, mobility technologies, materials design and discovery, power systems, fusion reactors, biological sciences, and earth observation. These efforts aim to enhance scientific research, operational efficiency, and decision-making processes. ORNL facilities, such as the High Flux Isotope Reactor (HFIR), Grid-C, Spallation Neutron Source (SNS), and Oak Ridge Leadership Computing Facility (OLCF), provide the infrastructure to develop and demonstrate these digital twin technologies. In this document, we lay out key challenges, research gaps, and future opportunities based on our experience with digital twins that aim to serve as useful contributions towards a National Digital Twins R&D Strategic Plan. In the remaining document, we address nine of the thirteen topic areas specified in the RFI.
97 MATHEMATICS AND COMPUTING↗
A Simulation Study of Quantum Clock Synchronization Using Teleportation
An important requirement in implementing distributed computing and sensing application is the synchronization of clocks at various locations. The Internet relies on the Network Time Protocol (NTP), which synchronizes clocks with accuracy in the order of milliseconds. More recently an ensemble of atomic clocks is used for navigation based on GPS. These clocks are highly accurate and provide time with very low uncertainty. Even so, many physics experiments such as distributed LIGO-based systems may require more accurate clock synchronization that is achievable using quantum entanglement. This requires the deployment of a network of quantum clocks synchronized by exploiting entangled atomic clock qubits. In this paper, we carry out a simulation study of synchronizing a network of quantum clocks interconnected by a fiber plant that supports the ESnet; the latter is used to support the classical communication needed for teleportation. We consider an existing protocol for synchro-nizing the atomic clock qubits that relies on the GHZ states. To assess the performance of the protocol we developed a discrete-event simulation of the network using IBM Qiskit framework for underlying quantum gate operations and measurements. The simulation results shed light on the resources required in terms of the number entangled qubits and the time needed to achieve the synchronization of different number of nodes in ESnet.
Kiran, Mariam↗
Elephants Sharing the Highway: Studying TCP Fairness in Large Transfers over High Throughput Links
Escalating bandwidth demand strains high-performance data networks, posing potential performance risks. TCP congestion control algorithms enhance reliability and optimize bandwidth usage. Network performance is influenced by factors such as AQM algorithms and router buffer size. In the context of constrained network resources, understanding how TCP flows share networks and the resulting performance impact is essential. This paper introduces insights into TCP fairness and performance involving a comparison of TCP CUBIC, Reno, Hamilton, and BBR versions 1 and 2 across real-world networks supporting high bandwidths of up to 25 Gbps. The research explores TCP behaviors with AQM algorithms like FIFO, FQ_CODEL, and RED, alongside diverse buffer sizes. Notably, findings reveal that manipulating buffers and queuing methods yields contrasting outcomes based on bandwidth. BBRv2 emerges as a superior fair algorithm, pivotal for swift transfers, particularly in scientific data scenarios. These results provide crucial guidance for future network design, ensuring equitable performance optimization.
Kiran, Mariam↗
Graph neural networks for detecting anomalies in scientific workflows
Identifying and addressing anomalies in complex, distributed systems can be challenging for reliable execution of scientific workflows. We model these workflows as directed acyclic graphs (DAGs), where the nodes and edges of the DAGs represent jobs and their dependencies, respectively. We develop graph neural networks (GNNs) to learn patterns in the DAGs and to detect anomalies at the node (job) and graph (workflow) levels. We investigate workflow-specific GNN models that are trained on a particular workflow and workflow-agnostic GNN models that are trained across the workflows. Our GNN models, which incorporate both individual job features and topological information from the workflow, show improved accuracy and efficiency compared to conventional learning methods for detecting anomalies. While joint trained with multiple scientific workflows, our GNN models reached an accuracy more than 80% for workflow level and 75% for job level anomalies. In addition, we illustrate the importance of hyperparameter tuning method in our study that can significantly improve the metric(s) measure of evaluating the GNN models. Finally, we integrate explainable GNN methods to provide insights on job features in the workflow that cause an anomaly.
97 MATHEMATICS AND COMPUTING↗
Machine Learning Pattern Recognition Algorithm With Applications to Coherent Laser Combination
Herein we analyze a new kind of machine learning algorithm designed to feedback stabilize coherently combined lasers. This algorithm learns differential, rather than absolute, values of action in phase space, in order to facilitate learning on initially unstable systems. Experiments have shown that this approach can control small-scale spatial beam combination with high stability. In this paper we analyze the algorithm's performance and limitations in depth, showing that it can continuously learn during operation in order to track changes. Using simulation, we extend the application to temporal combination, and show that it scales to more complex instances by combining 81 beams.
97 MATHEMATICS AND COMPUTING↗
LBNL Superfacility Project Report
The Superfacility model is designed to leverage HPC for experimental science. It is more than simply a model of connected experiment, network, and HPC facilities; it encompasses the full ecosystem of infrastructure, software, tools, and expertise needed to make connected facilities easy to use. The three-year Lawrence Berkeley National Laboratory (LBNL) Superfacility project was initiated in 2019 to coordinate work being performed at LBNL to support this model, and to provide a coherent and comprehensive set of science requirements to drive existing and new work. A key component of the project was the in-depth engagements with eight science teams that represent challenging use cases across the DOE Office of Science.
97 MATHEMATICS AND COMPUTING↗
HPS-RL: Hyperparameter tuning for deep RL applications (HPS-RL) v1
Genetic Algorithms meets Deep RL for Hyperparameters Hyperparameter optimization and architecture search can easily become cumbersome and finding the right hyperparameters can seriously impact the robustness of the deep RL application being developed. We use genetic algorithms to evolve optimum deep RL architectures in a scalable manner. HPS-RL is designed to work with multiple gym enviornments, allow users to test their own optimization functions and tune multi-objective parameters in multiple deep RL algorithms. HPS-RL uses multi-threading and is being extended with mpipy for distributed processing on HPC. https://arxiv.org/abs/2201.11182
Kiran, Mariam↗
Experimental beam combining stabilization using machine learning trained while phases drift
An 8-beam, diffractive coherent beam combiner is phase controlled by a learning algorithm trained while optical phases drift, using a differential mapping technique. Combined output power is stable to 0.4% with 95% of theoretical maximum efficiency, limited by the diffractive element.
47 OTHER INSTRUMENTATION↗
Netostat: analyzing dynamic flow patterns in high-speed networks
Understanding flow traffic patterns in networks, such as the Internet or service provider networks, is crucial to improving their design and building them robustly. However, as networks grow and become more complex, it is increasingly cumbersome and challenging to study how the many flow patterns, sizes and the continually changing source-destination pairs in the network evolve with time. Here, we present Netostat, a visualization-based network analysis tool that uses visual representation and a mathematics framework to study and capture flow patterns, using graph theoretical methods such as clustering, similarity and difference measures. Netostat generates an interactive graph of all traffic patterns in the network, to isolate key elements that can provide insights for traffic engineering. We present results for U.S. and European research networks, ESnet and GEANT, demonstrating network state changes, to identify major flow trends, potential points of failure, and bottlenecks.
97 MATHEMATICS AND COMPUTING↗
NetGraf: An End-to-End Learning NetworkMonitoring Service (NetGraf) v1
NetGraf is a novel end-to-end learning monitoring system that utilizes current monitoring tools, merges multiple data sources into one dashboard for easy use, and provides machine learning libraries to analyze the data and perform real-time anomaly findings. Using a database backend, NetGraf can learn performance trends and show users if network performance has degraded. We demonstrate how NetGraf can easily be deployed through automation services and linked to multiple monitoring sources to collect data. Via the machine learning innovation and merging various data sources, NetGraf aims to fulfill the need for holistic learning network telemetry monitoring. To the best of our knowledge, this is the first-ever end-to-end learning monitoring service. We demonstrate its use on two network setups to showcase its impact.
Mohammed, Bashir↗
HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods, HYPPO uses adaptive surrogate models and directly accounts for uncertainty in model predictions to find accurate and reliable models that make robust predictions. Using asynchronous nested parallelism, we are able to significantly alleviate the computational burden of training complex architectures and quantifying the uncertainty. HYPPO is implemented in Python and can be used with both TensorFlow and PyTorch libraries. We demonstrate various software features on time-series prediction and image classification problems as well as a scientific application in computed tomography image reconstruction. Finally, we show that (1) we can reduce by an order of magnitude the number of evaluations necessary to find the most optimal region in the hyperparameter space and (2) we can reduce by two orders of magnitude the throughput for such HPO process to complete.
adaptation models↗
Machine learning-based analysis of COVID-19 pandemic impact on US research networks
Here in this study we explore how fallout from the changing public health policy around COVID-19 has changed how researchers access and process their science experiments. Using a combination of techniques from statistical analysis and machine learning, we conduct a retrospective analysis of historical network data for a period around the stay-at-home orders that took place in March 2020. Our analysis takes data from the entire ESnet infrastructure to explore DOE high-performance computing (HPC) resources at OLCF, ALCF, and NERSC, as well as User sites such as PNNL and JLAB. We look at detecting and quantifying changes in site activity using a combination of t-Distributed Stochastic Neighbor Embedding (t-SNE) and decision tree analysis. Our findings bring insights into the working patterns and impact on data volume movements, particularly during late-night hours and weekends.
97 MATHEMATICS AND COMPUTING↗
2019 Computing Sciences Strategic Plan
Computing has transformed nearly every aspect of scientific inquiry — across disciplines and across scales — from the behavior of subatomic particles to the formation of structures in the early universe, from the assembly of the human genome to the evolution of earth systems. Over the past two decades, computing has become an integral part of how Berkeley Lab is “Bringing Science Solutions to the World.” Advances in computing and mathematics have been key, with new mathematical models of complex physical phenomena, new methods for analyzing complex data, new algorithms for accuracy and scaling and sophisticated software systems that encapsulate these techniques into open, reusable tools. The performance of NERSC computers and the ESnet network have grown by several orders of magnitude, along with our understanding of how to map scientific computations and workflows onto these systems. From research to facility operations, the passion, talent and dedication of the Computing Sciences Area staff has been the cornerstone of our success. The plan outlined in this document describes the next step in a journey to expand the influence and impact of our efforts, building an increasingly connected global enterprise for science that places more powerful instruments in the hands of scientists, along with more powerful methods and tools for modeling, analysis and prediction.
97 MATHEMATICS AND COMPUTING↗
Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency
Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Levenberg–Marquardt multi-classification using hinge loss function
Incorporating higher-order optimization functions, such as Levenberg-Marquardt (LM) have revealed better generalizable solutions for deep learning problems. However, these higher-order optimization functions suffer from very large processing time and training complexity especially as training datasets become large, such as in multi-view classification problems, where finding global optima is a very costly problem. To solve this issue, we develop a solution for LM-enabled classification with, to the best of knowledge first-time implementation of hinge loss, for multiview classification. Hinge loss allows the neural network to converge faster and perform better than other loss functions such as logistic or square loss rates. Here we prove our method by experimenting with various multiclass classification challenges of varying complexity and training data size. The empirical results show the training time and accuracy rates achieved, highlighting how our method outperforms in all cases, especially when training time is limited. Our paper presents important results in the relationship between optimization and loss functions and how these can impact deep learning problems.
97 MATHEMATICS AND COMPUTING↗
FlexDRL v1.0
FlexDRL is a framework that can be used as a benchmarking tool to evaluate different Deep Reinforcement Learning algorithms in a building energy management setting. OpenAI Gym was used as wrapper to the co-simulation environment (EnergyPlus for envelope and HVAC and Modelica for battery and PV) to interface with DRL algorithms, which are developed in PyTorch. In order to facilitate the usage of FlexDRL, all the required dependencies have been packaged into a Docker container.
Touzani, Samir↗