Energy Sciences Network

This paper explores the quantification and forecasting of reserve capacity from electric trains for participation in power system ancillary service markets. We first map train electricity consumption – traction and non-traction – to suitable reserve products, considering operational and regulatory constraints. Using historical data from the Danish railway operator DSB, we estimate the available flexibility for frequency containment reserves, focusing on controllable non-traction loads such as heating and air conditioning. To support market participation, we develop a low-resolution stochastic forecasting model based on conformal prediction, capable of estimating reserve availability for both day-ahead and hour-ahead horizons. Results show that a fleet of approximately 60 active trains can provide up to 10 MW of downward regulation and 1.5 MW of upward regulation from non-traction loads. Additionally, traction power from 25 trains can provide up to 5 MW of upward reserve in certain time periods. The findings demonstrate a viable pathway for integrating electric trains into flexibility markets, offering new revenue opportunities for operators and enhancing grid stability. • Demonstrates the feasibility of using electric trains to provide Frequency Containment Reserve. (FCR-D). • Introduces a forecasting framework using conformal prediction to meet regulatory P90 compliance. • Quantifies reserve capacity from real-world Danish railway data under operational constraints. (data specificity). • Shows minimal impact on schedules and comfort when participating in ancillary service markets. (market readiness). • Advances sector coupling by integrating railway operations into future energy flexibility systems.

The escalating demands of scientific collaborations necessitate advanced networking for deterministic, secure, and orchestrated services across multiple administrative domains. The Software-Defined Network for End-to-end Networked Science at the Exascale (SENSE) paradigm addresses these needs through intent-based networking and multi-domain orchestration. This paper evaluates SENSE’s performance on a comprehensive multi-domain testbed, including GNA-G AutoGOLE, the National Research Platform (NRP), FABRIC, and production LHC CMS infrastructure. Our results demonstrate that intent-based service requests are successfully translated into network configurations, with average provisioning times of 183 seconds for simple services and 290 seconds for complex multi-domain workflows. Performance monitoring confirms that SENSE maintains guaranteed bandwidth allocations, enabling higher-priority data flows to complete significantly faster than in best-effort scenarios. This capability transforms the network into a first-class schedulable resource, optimizing scientific workflows by prioritizing data criticality and moving beyond best-effort limitations to achieve predictable and efficient data movement for data-intensive scientific endeavors.

In February 2025, the DOE user facility Energy Sciences Network (ESnet) held a three-day Data and AI Workshop in Berkeley, California. The objective of the workshop was to identify challenges within ESnet that could be addressed through data-driven methods, to help define ESnet’s data-analysis requirements, and to shape its AI strategy, guiding data-stewardship efforts and the direction of AI research and AIOps exploration for ESnet7, the next iteration of ESnet’s network. This report summarizes the multi-faceted discussions and findings and presents a set of recommendations for next steps.

DIII-D research is being accelerated by leveraging high performance computing (HPC) and data resources available through the National Energy Research Scientific Computing Center (NERSC) Superfacility initiative. As part of this initiative, a high-resolution, fully automated, whole discharge kinetic equilibrium reconstruction workflow was developed that runs at the NERSC for most DIII-D shots in under 20 min. This has eliminated a long-standing research barrier and opened the door to more sophisticated analyses, including plasma transport and stability. These capabilities would benefit from being automated and executed within the larger Department of Energy Advanced Scientific Computing Research program’s Integrated Research Infrastructure (IRI) framework. The goal of IRI is to empower researchers to meld DOE’s world-class research tools, infrastructure, and user facilities seamlessly and securely in novel ways to radically accelerate discovery and innovation. For transport, we are looking at producing flux matched profiles and also using particle tracing to predict fast ion heat deposition from neutral beam injection before a shot takes place. Our starting point for evaluating plasma stability focuses on the pedestal limits that must be navigated to achieve better confinement. This information is meant to help operators run more effective experiments, so it needs to be available rapidly inside the DIII-D control room. So far this has been achieved by ensuring the data is available with existing tools, but as more novel results are produced new visualization tools must be developed. In addition, all of the high-quality data we have generated has been collected into databases that can unlock even deeper insights. This has already been leveraged for model and code validation studies as well as for developing AI/ML surrogates. The workflows developed for this project are intended to serve as prototypes that can be replicated on other experiments and can be run to provide timely and essential information for ITER, as well as next stage fusion power plants.

Efficient data transfer across scientific computing facilities is critical for enabling timely scientific discoveries. In this work, we explore the options of anticipating extremely slow data transfers to enable preventive actions. However, the dynamic nature of the large distributed scientific workflows driving these data transfers presents significant challenges for predicting network throughput. This study introduces a Conditional Recurrent Neural Network (CondRNN) model, specifically utilizing Conditional Long Short-Term Memory (CondLSTM), to integrate both static and dynamic features for enhanced throughput prediction. By leveraging historical transfers as proxy features, more than 60% of predictions achieved an absolute percentage error (APE) of less than 20%, and slow transfers were detected with a precision of 91.7% and recall of 100%, outperforming traditional RNN models. Implementing CondLSTM in scientific computing environments can optimize network resource utilization, ensuring efficient data transmission, thereby supporting the continuous progression of scientific research.

EPOC uses the Deep Dive process to discuss and analyze current and planned science, research, or education activities and the anticipated data output of a particular use case, site, or project to help inform the strategic planning of a campus or regional networking environment. This includes understanding future needs related to network operations, network capacity upgrades, and other technological service investments. A Deep Dive comprehensively surveys major research stakeholders’ plans and processes in order to investigate data management requirements over the next 5–10 years. Between February and June 2024, staff members from the Engagement and Performance Operations Center (EPOC) met with researchers and staff from New York-Presbyterian (NYP), Columbia University Irving Medical Center (CUIMC), and NYSERNet for the purpose of a Deep Dive into scientific and research drivers. The goal of this activity was to help characterize the requirements for a number of campus use cases, and to enable cyberinfrastructure support staff to better understand the needs of the researchers within the community. Material for this event included the written documentation from each of the profiled research areas, documentation about the current state of technology support, and a write-up of the discussion that took place via e-mail and video conferencing. The case studies highlighted the ongoing challenges and opportunities that NYP and CUIMC have in supporting a cross-section of established and emerging research use cases. Each case study mentioned unique challenges which were summarized into common needs.

The Thomas Jefferson National Accelerator Facility collaborates with Lawrence Berkeley National Lab to implement a dynamic UDP load balancer (LB) for high-throughput scientific data processing. This study employs a simulation to compare the efficacy of Proportional, Integrative, Derivative (PID) controllers and Q-Learning based controllers for configuring the load balancer. Two cluster configurations, homogeneous and heterogeneous, were examined. The simulation results indicate that PID control is superior in both configurations. In homogeneous clusters, PID achieved a 50% reduction in aggregate queue levels and maintained an even distribution across computational nodes (CNs). In contrast, Q-Learning was less effective in heterogeneous environments, exacerbating queue levels compared to the no-control case and failing to achieve balance across the cluster. Our findings suggest that PID control should be used for the ESnet-JLab FPGA Accelerated Transport (EJFAT) system.

Data caches of various forms have been widely deployed in the context of commercial and research and education networks, but their common positioning at the Edge limits their utility from a network operator perspective. When deployed outside the network core, providers lack visibility to make decisions or apply traffic engineering based on data access patterns and caching node location. As an alternative, in-network caching provides a different type of content delivery network for scientific data infrastructure, supporting on-demand temporary caching service. We will describe the status of in-network caching nodes deployed within ESnet in support of the US CMS data federation. We will describe the container and networking architecture used to deploy data caches within ESnet, and update on the evolving tooling around service management lifecycle. An analysis of cache usage will also be provided along with an outlook for expanding the in-network cache footprint.

Large scientific collaborations often have multiple scientists accessing the same set of files while doing different analyses, which create repeated accesses to the large amounts of shared data located far away. These data accesses have long latency due to distance and occupy the limited bandwidth available over the wide-area network. To reduce the wide-area network traffic and the data access latency, regional data storage caches have been installed as a new networking service. To study the effectiveness of such a cache system in scientific applications, we examine the Southern California Petabyte Scale Cache for a high-energy physics experiment. By examining about 3TB of operational logs, we show that this cache removed 67.6% of file requests from the wide-area network and reduced the traffic volume on wide-area network by 12. 3TB (or 35.4%) an average day. The reduction in the traffic volume (35.4%) is less than the reduction in file counts (67.6%) because the larger files are less likely to be reused. Due to this difference in data access patterns, the cache system has implemented a policy to avoid evicting smaller files when processing larger files. We also build a machine learning model to study the predictability of the cache behavior. Tests show that this model is able to accurately predict the cache accesses, cache misses, and network throughput, making the model useful for future studies on resource provisioning and planning.