Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep potential”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,513 records · Page 84

MEMS Applications in Aerodynamic Measurement Technology

Microelectromechanical systems (MEMS) embodies the integration of sensors, actuators, and electronics on a single substrate using integrated circuit fabrication techniques and compatible bulk and surface micromachining processes. Silicon and its derivatives form the material base for the MEMS technology. MEMS devices, including microsensors and microactuators, are attractive because they can be made small (characteristic dimension about 100 microns), be produced in large numbers with uniform performance, include electronics for high performance and sophisticated functionality, and be inexpensive. For aerodynamic measurements, it is preferred that sensors be small so as to approximate measurement at a point, and in fact, MEMS pressure sensors, wall shear-stress sensors, heat flux sensors and micromachined hot wires are nearing application. For the envisioned application to wind tunnel models, MEMS sensors can be placed on the surface or in very shallow grooves. MEMS devices have often been fabricated on stiff, flat silicon substrates, about 0.5 mm thick, and therefore were not easily mounted on curved surfaces. However, flexible substrates are now available and heat-flux sensor arrays have been wrapped around a curved turbine blade. Electrical leads can also be built into the flexible substrate. Thus MEMS instrumented wind tunnel models do not require deep spanwise grooves for tubes and leads that compromise the strength of conventionally instrumented models. With MEMS, even the electrical leads can potentially be eliminated if telemetry of the signals to an appropriate receiver can be implemented. While semiconductor silicon is well known for its electronic properties, it is also an excellent mechanical material for MEMS applications. However, silicon electronics are limited to operations below about 200 C, and silicon's mechanical properties start to diminish above 400 C. In recent years, silicon carbide (SiC) has emerged as the leading material candidate for applications in high temperature environments and can be used for high-temperature MEMS applications. With SiC, diodes and more complex electronics have been shown to operate to about 600 C, while the mechanical properties of SiC are maintained to much higher temperatures. Even when MEMS devices show benefits in the laboratory, there are many packaging challenges for any aeronautics application. Incorporating MEMS into these applications requires new approaches to packaging that goes beyond traditional integrated circuit (IC) packaging technologies. MEMS must interact mechanically, as well as electrically with their environment, making most traditional chip packaging and mounting techniques inadequate. Wind tunnels operate over wide temperature ranges in an environment that is far from being a 'clean-room.' In flight, aircraft are exposed to natural elements (e.g. rain, sun, ice, insects and dirt) and operational interferences(e.g. cleaning and deicing fluids, and maintenance crews). In propulsion systems applications, MEMS devices will have to operate in environments containing gases with very high temperatures, abrasive particles and combustion products. Hence deployment and packaging that maintains the integrity of the MEMS system is crucial. This paper presents an overview of MEMS fabrication and materials, descriptions of available sensors with more details on those being developed in our laboratories, and a discussion of sensor deployment options for wind tunnel and flight applications.

Reshotko, E.↗

Inertial-Electrostatic Confinement (IEC) Fusion For Space Propulsion

An Inertial-Electrostatic Confinement (IEC) device was assembled at the Marshall Space Flight Center (MSFC) Propulsion Research Center (PRC) to study the possibility of using IEC technology for deep space propulsion and power. Inertial-Electrostatic Confinement is capable of containing a nuclear fusion plasma in a series of virtual potential wells. These wells would substantially increase plasma confinement, possibly leading towards a high-gain, breakthrough fusion device. A one-foot in diameter IEC vessel was borrowed from the Fusion Studies Laboratory at the University of Illinois @ Urbana-Champaign for the summer. This device was used in initial parameterization studies in order to design a larger, actively cooled device for permanent use at the PRC.

Nadler, Jon↗

Inertial-Electrostatic Confinement (IEC) Fusion for Space Propulsion

An Inertial-Electrostatic Confinement (IEC) device was assembled at the Marshall Space Flight Center (MSFC) Propulsion Research Center (PRC) to study the possibility of using EEC technology for deep space propulsion and power. Inertial-Electrostatic Confinement is capable of containing a nuclear fusion plasma in a series of virtual potential wells. These wells would substantially increase plasma confinement, possibly leading towards a high-gain, breakthrough fusion device. A one-foot in diameter IEC vessel was borrowed from the Fusion Studies Laboratory at the University of Illinois@Urbana-Champaign for the summer. This device was used in initial parameterization studies in order to design a larger, actively cooled device for permanent use at the PRC.

Nadler, Jon↗

Effects of Deep Convection on Atmospheric Chemistry

This presentation will trace the important research developments of the last 20+ years in defining the roles of deep convection in tropospheric chemistry. The role of deep convection in vertically redistributing trace gases was first verified through field experiments conducted in 1985. The consequences of deep convection have been noted in many other field programs conducted in subsequent years. Modeling efforts predicted that deep convection occurring over polluted continental regions would cause downstream enhancements in photochemical ozone production in the middle and upper troposphere due to the vertical redistribution of ozone precursors. Particularly large post-convective enhancements of ozone production were estimated for convection occurring over regions of pollution from biomass burning and urban areas. These estimates were verified by measurements taken downstream of biomass burning regions of South America. Models also indicate that convective transport of pristine marine boundary layer air causes decreases in ozone production rates in the upper troposphere and that convective downdrafts bring ozone into the boundary layer where it can be destroyed more rapidly. Additional consequences of deep convection are perturbation of photolysis rates, effective wet scavenging of soluble species, nucleation of new particles in convective outflow, and the potential fix stratosphere-troposphere exchange in thunderstorm anvils. The remainder of the talk will focus on production of NO by lightning, its subsequent transport within convective clouds . and its effects on downwind ozone production. Recent applications of cloud/chemistry model simulations combined with anvil NO and lightning flash observations in estimating NO Introduction per flash will be described. These cloud-resolving case-study simulations of convective transport and lightning NO production in different environments have yielded results which are directly applicable to the design of lightning parameterizations for global chemical transport models. The range of mean values (factor of 3) of NO production per flash (or per meter of lightning channel length) that have been deduced from the model will be shown and compared with values of production in the literature that have been deduced using other methods, Results show that on a per flash basis, IC flashes are nearly as productive of NO as CG flashes. When combined with the global flash rate of 44 flashes per second from NASA's Optical Transient Detector (OTD) measurements, these estimates and the results from other techniques yield global NO production rates of 2-9 TgN/year. Vertical profiles of lightning NOx mass at the end of the 3-D storm simulations have been summarized to yield suggested profiles for use in global models. Simulations of the photochemistry over the 24 hours following a storm have been performed to determine the additional ozone production which can be attributed to lightning NO.

Pickering, Kenneth E.↗

NASA’s In-Space Manufacturing Project: Update on Manufacturing Technologies and Materials to Enable More Sustainable and Safer Exploration

NASA’s In-Space Manufacturing (ISM) project seeks to develop the materials, processes, and manufacturing technologies needed to provide an on-demand manufacturing capability for deep space exploration missions. The ability to manufacture and recycle some parts on demand rather than launch them from earth has the potential to reduce logistics requirements on long duration missions and enhance crew safety. With the launch of the first 3D printer (built and operated by Made in Space through a Small Business Innovative Research – SBIR -- contract) to the International Space Station (ISS) in 2014, the ISM project demonstrated the feasibility of operating an on-demand manufacturing system in a microgravity environment. This paper will provide an update on recent advancements in ISM under three key technology areas: manufacturing, recycling, and development of a design database. ISM continues to pursue development of manufacturing technologies for space applications and use the ISS as a critical test bed to prove out these technologies before deploying them on next generation exploration systems. Activities under this focus area include: characterization of materials manufactured using the Additive Manufacturing Facility (AMF), the second generation commercial 3D-printer on ISS, also owned and operated by Made in Space; development of prototype payloads for metal manufacturing through phase II SBIR contracts with Tethers Unlimited, Made in Space, and Ultra Tech Machinery; development of a multi-material fabrication laboratory capable of processing metals and providing inspection of manufactured parts through a Broad Agency Announcement (Techshot, Interlog, and Tethers Unlimited); an in-line sensing system for ISM platforms; and development of higher strength feedstocks for 3D polymer printers. In the area of recycling, the Tethers Unlimited Refabricator payload (an integrated 3D printer and recycler for ULTEM 9085) launched to ISS in November 2018 and began operating in early 2019. This payload represents the first demonstration of on-orbit recycling; down massed specimens will assess material degradation in the polymer over multiple recycling cycles to define limits on material re-use. Other work in the recycling area includes development of common use materials intended to be reused and recycled on space missions (Tethers Unlimited and Cornerstone Research Group) and a sterilization capability for multiple-use materials (ERASMUS from Tethers Unlimited). Concurrent with manufacturing technology and materials development work is creation of a design database, a curated list of parts that can be manufactured using the suite of In-Space Manufacturing capabilities.

Tracie Prater↗

CO2-Based Manufacturing System for Recombinant Protein Production

Space biomanufacturing is a potential In Situ Resource Utilization (ISRU) strategy to provide critical consumables and products while minimizing the launched mass for long-duration, deep space missions. On Earth, the primary biological conversion of CO 2 to biomass is through photosynthesis, and sugars from photosynthetic organisms are used as feedstocks for microbial biomanufacturing. The efficiency of non-biological reduction of CO 2 to organic molecules, such as acetate or ethanol, has greatly increased in recent years. We are designing a biomanufacturing system to rely on electrochemical CO 2 conversion products for carbon substrates to support microbial growth and production of recombinant proteins. The preliminary design includes a gas-permeable membrane bioreactor with dry salts that are rehydrated and mixed with the carbon source to support growth of bacteria or yeast. The system architecture has a partially automated bioprocessing system to concentrate biomass and purify recombinant protein. This system is designed to operate semi-autonomously with minimal crew intervention. The specific use-case scenario is to produce a thermal stable carbonic anhydrase to increase the efficiency of a proposed liquid amine CO 2 removal subsystem of an environmental control and life-support system (ECLSS) on Mars.

Biomanufacturing↗

Development of a Space Compatible Biomanufacturing System

Space biomanufacturing is a potential In Situ Resource Utilization (ISRU) strategy to provide critical consumables and products while minimizing the launched mass for long-duration, deep space missions. On Earth, the primary biological conversion of CO 2 to biomass is through photosynthesis, and sugars from photosynthetic organisms are used as feedstocks for microbial biomanufacturing. The efficiency of non-biological reduction of CO 2 to organic molecules, such as acetate or ethanol, has greatly increased in recent years. We are designing a biomanufacturing system to rely on electrochemical CO 2 conversion products for carbon substrates to support microbial growth and production of recombinant proteins. The preliminary design includes a gas-permeable membrane bioreactor with dry salts that are rehydrated and mixed with the carbon source to support growth of bacteria or yeast. The system architecture has a partially automated bioprocessing system to concentrate biomass and purify recombinant protein. This system is designed to operate semi-autonomously with minimal crew intervention. The specific use-case scenario is to produce a thermal stable carbonic anhydrase to increase the efficiency of a proposed liquid amine CO 2 removal subsystem of an environmental control and life-support system (ECLSS) on Mars.

Recombinant↗

PFLOTRAN Integrated Performance Assessment at Waste Isolation Pilot Plant

The Waste Isolation Pilot Plant (WIPP) is developed by the U.S. Department of Energy (DOE) for the deep geologic disposal of transuranic (TRU) waste in southeast New Mexico. The purpose of performance assessment (PA) is to estimate probability of potential radionuclide releases from the repository to the environment for a regulatory period of 10,000 years after its closure. The use of PFLOTRAN has been proposed to enhance PA with more physically realistic flow and transport models in 3D. PFLOTRAN is a state-of-art massively parallel subsurface flow and reactive transport code. This paper introduces the progress of implementation of PFLOTRAN in the PA and the preliminary results for undisturbed repository conditions. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Neurovascular Outcomes of Ionizing Radiation in Human Blood-Brain Barrier Models

One of the main health risks in human deep space exploration is central nervous system (CNS) damage by ionizing radiation due to exposure to galactic cosmic rays (GCRs). In animal models, irradiation with simulated GCRs or their components has been shown to cause neurodegeneration and neuroinflammation associated with cognitive and behavioral dysfunction. The extent of CNS damage is partially mediated by the blood-brain barrier (BBB), which regulates the interaction between CNS and systemic responses to stressors in the rest of the body. The main cellular regulators of BBB permeability are astrocytes, which also modulate neuronal death, neuroinflammation and oxidative stress. However, studies on BBB and astrocyte functions in regulating CNS responses to ionizing radiation have been limited, especially in human tissue/organ analogs. Therefore, we developed a high-throughput 3D organ-on-a-chip system to study human CNS and BBB impairments caused by deep space radiation. We investigated both immediate and delayed CNS responses to major GCR components: 0.15-0.5Gy 250MeV/n 4He and 0.3-0.8Gy 600MeV/n 56Fe; as well as to 0.5-1Gy X-rays. We observed ionizing radiation-mediated increases in BBB permeability that was exacerbated by astrocyte presence and accompanied by damage to endothelial cells and tight junctions, altered cytokine expression including TNFalpha upregulation, and increased oxidative stress. In particular, 600MeV/n 56Fe particle irradiation selectively induced astrocyte damage and blood-brain barrier permeability only in models that contained astrocytes in addition to endothelial cells, indicating astrocytes as a particularly radiosensitive component of the CNS that could therefore be a suitable a target for neuroprotection. Future studies will compare human and mouse CNS model responses to simulated GCRs and evaluate the induction of an anti-inflammatory phenotype in astrocytes as a potential countermeasure. Ultimately, we aim to expand upon these results to uncover novel cellular and mechanistic targets for countermeasure development to mitigate human CNS damage in deep space exploration.

space radiation↗

Neurovascular Outcomes of Space Radiation in Human Blood-Brain Barrier Models

One of the main health risks in human deep space exploration is central nervous system (CNS) damage by ionizing radiation due to exposure to galactic cosmic rays (GCRs). In animal models, irradiation with simulated GCRs or their components has been shown to cause neurodegeneration and neuroinflammation associated with cognitive and behavioral dysfunction. The extent of CNS damage is partially mediated by the blood-brain barrier (BBB), which regulates the interaction between CNS and systemic responses to stressors in the rest of the body. The main cellular regulators of BBB permeability are astrocytes, which also modulate neuronal death, neuroinflammation and oxidative stress. However, studies on BBB and astrocyte functions in regulating CNS responses to ionizing radiation have been limited, especially in human tissue/organ analogs. Therefore, we developed a high-throughput 3D organ-on-a-chip system to study human CNS and BBB impairments caused by deep space radiation. We investigated both immediate and delayed CNS responses to major GCR components: 0.15-0.5Gy 250MeV/n 4He and 0.3-0.8Gy 600MeV/n 56Fe; as well as to 0.5-1Gy X-rays. We observed ionizing radiation-mediated increases in BBB permeability that was exacerbated by astrocyte presence and accompanied by damage to endothelial cells and tight junctions, altered cytokine expression including TNFalpha upregulation, and increased oxidative stress. In particular, 600MeV/n 56Fe particle irradiation selectively induced astrocyte damage and increased blood-brain barrier permeability only in models that contained astrocytes in addition to endothelial cells, indicating astrocytes as a particularly radiosensitive component of the CNS that could therefore be a suitable a target for neuroprotection. Future studies will compare human and mouse CNS model responses to simulated GCRs and evaluate the induction of an anti-inflammatory phenotype in astrocytes as a potential countermeasure. Ultimately, we aim to expand upon these results to uncover novel cellular and mechanistic targets for countermeasure development to mitigate human CNS damage in deep space exploration.

centrat nervous system↗

Doing the impossible: Why neural networks can be trained at all

As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A common naive question arises: if we have a system with billions of degrees of freedom, don't we also need billions of samples to train it? Of course, the success of deep learning indicates that reliable models can be learned with reasonable amounts of data. Similar questions arise in protein folding, spin glasses and biological neural networks. With effectively infinite potential folding/spin/wiring configurations, how does the system find the precise arrangement that leads to useful and robust results? Simple sampling of the possible configurations until an optimal one is reached is not a viable option even if one waited for the age of the universe. On the contrary, there appears to be a mechanism in the above phenomena that forces them to achieve configurations that live on a low-dimensional manifold, avoiding the curse of dimensionality. In the current work we use the concept of mutual information between successive layers of a deep neural network to elucidate this mechanism and suggest possible ways of exploiting it to accelerate training.

deep learning, training, curse of dimensionality, ↗

Ultrafast processing of pixel detector data with machine learning frameworks

Modern photon science performed at high repetition rate free-electron laser (FEL) facilities and beyond relies on 2D pixel detectors operating at increasing frequencies (towards 100 kHz at LCLS-II) and producing rapidly increasing amounts of data (towards TB/s). This data must be rapidly stored for offline analysis and summarized in real time for online feedback to the scientists. While at LCLS all raw data has been stored, at LCLS-II this would lead to a prohibitive cost; instead, enabling real time processing of pixel detector data (dark, gain, common mode, background, charge summing, subpixel position, photon counting, data summarization) allows reducing the size and cost of online processing, offline processing and storage by orders of magnitude while preserving full photon information. This could be achieved by taking advantage of the compressibility of sparse data typical for LCLS-II applications. Faced with a similar big data challenge a decade ago, computer vision stimulated revolutionary advances in machine learning hardware and software. We investigated if these developments are useful in the field of data processing for high speed pixel detectors and found that typical deep learning models and autoencoder architectures failed to yield useful noise reduction while preserving full photon information, presumably because of the very different statistics and feature sets in computer vision and radiation imaging. However, the raw performance of modern frameworks like Tensorflow inspired us to redesign in Tensorflow mathematically equivalent versions of the state-of-the-art, “classical” algorithms used at LCLS. The novel Tensorflow models resulted in elegant, compact and hardware agnostic code, gaining 1 to 2 orders of magnitude faster processing on an inexpensive consumer GPU, reducing by 3 orders of magnitude the projected cost of online analysis and compression without photon loss at LCLS-II. The novel Tensorflow models also enabled ongoing development of a pipelined hardware system expected to yield an additional 3 to 4 orders of magnitude speedup, necessary for meeting the data acquisition and storage requirements at LCLS-II, potentially enabling acquiring every single FEL pulse at full speed. Computer vision a decade ago was dominated by hand-crafted filters; their structure inspired the deep learning revolution resulting in modern deep convolutional networks; similarly, our novel Tensorflow filters provide inspiration for designing future deep learning models for ultrafast and efficient processing and classification of pixel detector images at FEL facilities.

47 OTHER INSTRUMENTATION↗

Physics-Guided Deep Learning for Complex System Health Management and Decision Making

The landscape of complex engineered systems is rapidly evolving, from smart manufacturing facilities to next-generation transportation vehicles. As these systems become increasingly sophisticated and interconnected, the need for advanced health management systems grows ever more critical. These systems must go beyond simple monitoring, actively predicting potential failures before they occur. This paradigm shift from fixed maintenance schedules to condition-based predictions is key to optimizing system performance, enhancing safety, and paving the way for autonomous decision-making across various industries. Whether in industrial processes, energy systems, or advanced transportation, the ability to anticipate and prevent failures is becoming a cornerstone of operational excellence. To accurately predict the future health of any complex system, knowledge of its current health state and future operational conditions is essential. Recent advancements in data-driven algorithms have generated growing interest in artificial intelligence for industrial applications. However, the limitations of pure data-driven methods, particularly in industries where data acquisition is costly and limited, have become apparent. This has led to a focus on blending physics with data-driven algorithms, mitigating the drawbacks of both approaches while emphasizing their respective advantages. This research proposes a novel framework for integrating physics-based performance models with deep learning algorithms for the prognostics of complex safety-critical systems. In this approach, physics-based models serve as a blueprint, capturing fundamental system behaviors, while deep learning algorithms, leveraging real-world sensor data, fill in gaps and identify subtle patterns indicative of potential problems. This hybrid methodology, utilizing techniques such as Physics-Informed Neural Networks (PINNs), offers a powerful solution for predicting system health. By fusing domain knowledge with data-driven insights, this approach promises more accurate, adaptable, and reliable models for health prediction. The resulting framework is versatile, applicable across various sectors including aerospace, manufacturing, and energy systems, ultimately contributing to safer, more efficient operations in our increasingly complex technological landscape.

Diagnostics↗

The age and potential causes of the giant Green Lake Landslide, Fiordland, New Zealand

Abstract Landslide deposits preserved in the geological record afford opportunities to better inform hillslope and seismic hazard and risk models, particularly in regions where observational records are short. In the Southern Alps of New Zealand, small coseismic landslides are frequent, but the geological record preserves several instances of more substantial (> 1 km 3 ) but infrequent mass failures. With an estimated volume of 27 km 3 , the giant Green Lake Landslide represents one of the largest subaerial landslides on Earth. Previous work has suggested this deep-seated mass movement was most likely triggered by high-intensity seismic shaking, but that local structural weakness and/or glacial debuttressing may help to explain the anomalously large failure volume. Resolving the potential contribution of the latter is important given predictions concerning alpine deglaciation in the coming decades to centuries. Key to resolution are secure chronologies of landslide emplacement and past glacier change. Here we present in situ cosmogenic 10 Be exposure ages from the Green Lake Landslide that suggest an emplacement age of 15.5 ± 0.7 ka. Recent work shows that glacial retreat in the region was underway by 19 ka, indicating that the Green Lake Landslide was emplaced 3–4 kyr after the onset of glacier retreat. Given the geometry of the former confining valley glacier, we expect that the deglaciation-landslide age gap is closer to the upper end of this estimate. If correct, this conclusion places greater weight on the roles of local geological structure and/or a great earthquake as factors contributing to the exceptionally large volume of this event.

58 GEOSCIENCES↗

Assessment of MON-25/MMH Propellant System for Deep-Space Engines

Hypergolic propellant system of oxidizer MON-25 and fuel MMH has been considered in propulsion trade studies for NASA science mission concepts. A propulsion system using this bi-propellant combination will be capable of operating at a lower temperature as compared to traditional MON-3/MMH for heater power reduction. Operation robustness can also be realized since such a propellant system is utilized under a wide range of temperatures. Propulsion system designs and engine test programs for MON-25/MMH have been carried out since 2008. Several engine development programs have been conducted. The thrust classes of 22-Newton [5-lb(sub f)] and 445-Newton [100-lb(sub f)] were tested with the capability of a pulse mode operation for a wide range of duty cycles. Additional engine development tests are followed. Outcomes of the development efforts suggest that there is a balance of mission benefits and potential engine design and operation challenges, although the propellants can handle a low temperature. This paper will report an assessment of using the MON-25/MMH system for deep- space application.

Trinh, Huu P.↗

Assessment of Deep Burnup HALEU Fuel Impact and Requirements

This report explores advancements in nuclear fuel technology, focusing on once-through high-assay low-enriched uranium (HALEU) fuels. It examines the potential for increased fuel residence time in reactors and the fuel cost implications. The study highlights the differences between fast and thermal reactors in terms of fuel enrichment and burnup, emphasizing the complex relationship in fast reactors in which increased core size and fuel density can lead to lower enrichment requirements. Various advances in fuel technologies for light-water reactors (LWR) and sodium-cooled fast reactors (SFR) are presented in this report to provide more comprehensive analysis.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Chapter 7: Predictive Analytics in Future Power Systems: A Panorama and State-of-the-Art of Deep Learning Applications

The challenges surrounding the optimal operation of power systems are growing in various dimensions, due in part to increasingly distributed energy resources and a progression towards large-scale transportation electrification. Currently, the increasing uncertainties associated with both renewable energy generation and demand are largely being managed by increasing operational reserves - potentially at the cost of suboptimal economic conditions - in order to maintain the reliability of the system. This chapter looks at the big picture role of forecasting in power systems from generation to consumption and provides a comprehensive review of traditional approaches for forecasting generation and load in various contexts. This chapter then takes a deep dive into the state-of-the-art machine learning and deep learning approaches for power systems forecasting. Furthermore, a case study of multi-time-horizon solar irradiance forecasting using deep learning is discussed in detail. Smart grids form the backbone of the future interdependent networks. For addressing the challenges associated with the operations of smart grid, development and wide adoption of machine learning and deep learning algorithms capable of producing better forecasting accuracies is urgently needed. Along with exploring the implementation and benefits of these approaches, this chapter also considers the strengths and limitations of deep learning algorithms for power systems forecasting applications. This chapter, thus, provides a panoramic view of state-of-the-art of predictive analytics in power systems in the context of future smart grid operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗