Publications
New software helps users build resilient, cost-effective energy architectures
July 2, 2019
Journal Article
Published in:
Lincoln Laboratory News
Summary
The Energy Resilience Analysis tool lets mission owners and energy managers balance the needs of critical missions on military installations with affordability when they design energy resilience solutions.
Summary
The Energy Resilience Analysis tool lets mission owners and energy managers balance the needs of critical missions on military installations with affordability when they design energy resilience solutions.
READ MORE
A Framework for Evaluating Electric Power Grid Improvements in Puerto Rico(2.58 MB)
July 1, 2019
Project Report
Summary
This report is motivated by the recognition that serving highly distributed electric power load in Puerto Rico during extreme events requires innovative methods. To do this, we must determine the type and locations of the most critical equipment, innovative methods, and software for operating the electrical system most effectively. It is well recognized that the existing system needs to be both hardened and further enhanced by deploying Distributed Energy Resources (DERs), solar photovoltaics (PV) in particular, and local reconfigurable microgrids to manage these newly deployed DERs. While deployment of microgrids and DERs has been advocated by many, there is little fundamental understanding how to operate Puerto Rico’s electrical system in a way that effectively uses DERs during both normal operations and grid failures. Utility companies’ traditional reliability requirements and operational risk management practices rely on excessive amounts of centralized reserve generation to anticipate failures, which increases the cost of normal operations and nullifies the potential of DERs to meet loads during grid failures. At present, no electric power utility has a ready-to-use framework that overcomes these limitations. This report seeks to fill this void.
Summary
This report is motivated by the recognition that serving highly distributed electric power load in Puerto Rico during extreme events requires innovative methods. To do this, we must determine the type and locations of the most critical equipment, innovative methods, and software for operating the electrical system most effectively. It...
READ MORE
A framework for evaluating electric power grid improvements in Puerto Rico
July 1, 2019
Project Report
Published in:
MIT Lincoln Laboratory Report 127164
Topic:
R&D area:
R&D group:
Summary
This report is motivated by the recognition that serving highly distributed electric power load in Puerto Rico during extreme events requires innovative methods. To do this, we must determine the type and locations of the most critical equipment, innovative methods, and software for operating the electrical system most effectively. It is well recognized that the existing system needs to be both hardened and further enhanced by deploying Distributed Energy Resources (DERs), solar photovoltaics (PV) in particular, and local reconfigurable microgrids to manage these newly deployed DERs. While deployment of microgrids and DERs has been advocated by many, there is little fundamental understanding how to operate Puerto Rico's electrical system in a way that effectively uses DERs during both normal operations and grid failures. Utility companies' traditional reliability requirements and operational risk management practices rely on excessive amounts of centralized reserve generation to anticipate failures, which increases the cost of normal operations and nullifies the potential of DERs to meet loads during grid failures. At present, no electric power utility has a ready-to-use framework that overcomes these limitations. This report seeks to fill this void.
Summary
This report is motivated by the recognition that serving highly distributed electric power load in Puerto Rico during extreme events requires innovative methods. To do this, we must determine the type and locations of the most critical equipment, innovative methods, and software for operating the electrical system most effectively. It...
READ MORE
Feature forwarding for efficient single image dehazing
June 17, 2019
Conference Paper
Published in:
IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops, CVPRW, 16-17 June 2019.
Topic:
R&D area:
Summary
Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to run on edge graphical processing units (GPUs). We utilize three variants of our architecture to explore the dependency of dehazed image quality on parameter count and model design. The first two variants presented, a small and big version, make use of a single efficient encoder–decoder convolutional feature extractor. The final variant utilizes a pair of encoder-decoders for atmospheric light and transmission map estimation. Each variant ends with an image refinement pyramid pooling network to form the final dehazed image. For the big variant of the single-encoder network, we demonstrate state-of-the-art performance on the NYU Depth dataset. For the small variant, we maintain competitive performance on the superresolution O/I-HAZE datasets without the need for image cropping. Finally, we examine some challenges presented by the Dense-Haze dataset when leveraging CNN architectures for dehazing of dense haze imagery and examine the impact of loss function selection on image quality. Benchmarks are included to show the feasibility of introducing this approach into real-time systems.
Summary
Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to run on edge graphical processing units (GPUs). We utilize three variants of our architecture to explore...
READ MORE
Collaborative and passive channel gain estimation in fading environments
June 12, 2019
Journal Article
Published in:
IEEE Trans. Cognitive Commun. and Netw., Vol. 5, No. 4, December 2019, pp. 863-72.
Summary
Dynamic spectrum access techniques are typically aided by knowledge of the wireless channel gains among participating radios, as this knowledge allows the potential interference impact of any radio's transmissions on its neighbors to be quantified. We present a technique for collaborative inference of the channel gains which relies solely on the radios monitoring their aggregate transmitted and received energies as they transmit their data packets. We demonstrate that through low data-rate exchange of these energy metrics among bursty networks, the gains can be jointly estimated within a dB and with low latency on the order of seconds. In particular, we derive the best linear unbiased estimator (BLUE) for the gains. While this estimator relies on knowledge of fading parameters not known in practice, we propose a practical variant which achieves performance comparable to the BLUE in the realistic fading setting used in our simulations.
Summary
Dynamic spectrum access techniques are typically aided by knowledge of the wireless channel gains among participating radios, as this knowledge allows the potential interference impact of any radio's transmissions on its neighbors to be quantified. We present a technique for collaborative inference of the channel gains which relies solely on...
READ MORE
Discriminative PLDA for speaker verification with X-vectors
May 12, 2019
Conference Paper
Published in:
International Conference on Acoustics, Speech, and Signal Processing, May 2019 [submitted]
Topic:
R&D area:
Summary
This paper proposes a novel approach to discriminative training ofprobabilistic linear discriminant analysis (PLDA) for speaker veri-fication with x-vectors. The Newton Method is used to discrimi-natively train the PLDA model by minimizing the log loss of ver-ification trials. By diagonalizing the across-class and within-classcovariance matrices as a pre-processing step, the PLDA model canbe trained without relying on approximations, and while maintain-ing important properties of the underlying covariance matrices. Thetraining procedure is extended to allow for efficient domain adapta-tion. When applied to the Speakers in the Wild and SRE16 tasks, theproposed approach provides significant performance improvementsrelative to conventional PLDA.
Summary
This paper proposes a novel approach to discriminative training ofprobabilistic linear discriminant analysis (PLDA) for speaker veri-fication with x-vectors. The Newton Method is used to discrimi-natively train the PLDA model by minimizing the log loss of ver-ification trials. By diagonalizing the across-class and within-classcovariance matrices as a pre-processing step, the...
READ MORE
AI enabling technologies: a survey
May 8, 2019
Journal Article
Published in:
https://arxiv.org/abs/1905.03592
Summary
Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together in order to provide capabilities that can be used by decision makers, warfighters and analysts. These pieces include data collection, data conditioning, algorithms, computing, robust artificial intelligence, and human-machine teaming. While much of the popular press today surrounds advances in algorithms and computing, most modern AI systems leverage advances across numerous different fields. Further, while certain components may not be as visible to end-users as others, our experience has shown that each of these interrelated components play a major role in the success or failure of an AI system. This article is meant to highlight many of these technologies that are involved in an end-to-end AI system. The goal of this article is to provide readers with an overview of terminology, technical details and recent highlights from academia, industry and government. Where possible, we indicate relevant resources that can be used for further reading and understanding.
Summary
Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together...
READ MORE
Banshee distribution network benchmark and prototyping platform for hardware-in-the-loop integration of microgrid and device controllers
April 29, 2019
Journal Article
Published in:
J. Eng., Vol. 2019, No. 8, pp. 5365-73.
Topic:
R&D area:
Summary
This article provides a unique benchmark to integrate and systematically evaluate advanced functionalities of microgrid and downstream device controllers. The article describes Banshee, a real-life power distribution network. It also details a real-time controller hardware-in-the-loop (HIL) prototyping platform to test the responses of the controllers and verify decision-making algorithms. The benchmark aims to address power industry needs for a common basis to integrate and evaluate controllers for the overall microgrid, distributed energy resources (DERs), and protective devices. The test platform will accelerate microgrid deployment, enable standard compliance verification, and further develop and test controllers' functionalities. These contributions will facilitate safe and economical demonstrations of the state-of-the-possible while verifying minimal impact to existing electrical infrastructure. All aspects of the benchmark and platform development including models, configuration files, and documentation are publicly available via the electric power HIL controls collaborative (EPHCC).
Summary
This article provides a unique benchmark to integrate and systematically evaluate advanced functionalities of microgrid and downstream device controllers. The article describes Banshee, a real-life power distribution network. It also details a real-time controller hardware-in-the-loop (HIL) prototyping platform to test the responses of the controllers and verify decision-making algorithms. The...
READ MORE
A neural network approach for waveform generation and selection with multi-mission radar
April 22, 2019
Conference Paper
Published in:
2019 IEEE Radar Conf., 22-26 April 2019.
R&D area:
R&D group:
Summary
Nonlinear frequency modulated (NLFM) pulse compression waveforms have become a mainstream methodology for radars across multiple sectors and missions, including weather observation, target tracking, and target detection. NLFM affords the ability to generate a low-sidelobe autocorrelation function and matched filter while avoiding aggressive amplitude modulation, resulting in more power incident on the target. This capability can lead to significantly lower system design costs due to the possibility of sensitivity gains on the order of 3 dB or more compared with traditional, amplitude-modulated linear frequency modulated (LFM) waveforms. Generation of an optimal NLFM waveform, however, can be an arduous task, and may involve complex optimization and non-closed-form solutions. For a multimission or cognitive radar, which may utilize a wide combination of frequencies, pulse lengths, and amplitude modulations (among other factors), this could lead to an extremely large waveform table for selection. This paper takes a neural network approach to this problem by optimizing a set of over 100 waveforms spanning a wide space and using the results to interpolate the waveform possibilities to a higher resolution. A modified form of a previous NLFM method is combined with a four-hidden-layer neural network to show the integrated and peak range sidelobes of the generated waveforms across the model training space. The results are applicable to multi-mission and cognitive radars that need precise waveform specifications in rapid succession. The expected waveform generation times are addressed and quantified, and the potential applicability to multi-mission and cognitive radars is discussed.
Summary
Nonlinear frequency modulated (NLFM) pulse compression waveforms have become a mainstream methodology for radars across multiple sectors and missions, including weather observation, target tracking, and target detection. NLFM affords the ability to generate a low-sidelobe autocorrelation function and matched filter while avoiding aggressive amplitude modulation, resulting in more power incident...
READ MORE
Modular Aid and Power Pallet (MAPP): FY18 Energy Technical Investment Program
April 19, 2019
Project Report
Published in:
MIT Lincoln Laboratory Report TIP-93
Topic:
R&D area:
R&D group:
Summary
Electric power is a critical element of rapid response disaster relief efforts. Generators currently used have high failure rates and require fuel supply chains, and standardized renewable power systems are not yet available. In addition, none of these systems are designed for easy adaptation or repairs in the field to accommodate changing power needs as the relief effort progresses. To address this, the Modular Aid and Power Pallet, or MAPP, was designed to be a temporary, scalable, self-contained, user-focused power system. While some commercial systems are advertised for disaster relief systems, most are limited by mobility, custom battery assemblies (with challenges for air transport, ground mobility, or both), and the ability to power AC loads. While the first year system focused on an open architecture design with distributed DC units that could be combined to serve larger AC loads, the second year succeeded in minimizing or eliminating batteries while providing AC power for both the distributed and centralized systems. Therefore, individual modules can be distributed to power small AC loads such as laptop charging, or combined in series for larger loads such as water purification. Each module is powered by a small photovoltaic (PV) array connected to a prototype off-grid Enphase microinverter that can be used with or without energy storage. In addition, an output box for larger loads is included to provide a ground fault interrupt, under/over voltage relay, and the ability to change the system grounding to fit the needs of a more complicated system. The second year MAPP effort was divided into two phases: Phase 1 from October 2017 to March 20181 focused on refining requirements and vendor selection, and Phase 2 from March 2018 to October 20182 focusing on power electronics, working with the new Enphase microinverter, and ruggedizing the system. The end result is the Phase 2 effort has been designed, tested, and proven to form a robust AC power source that is flexible and configurable by the end user. Our testing has shown that operators can easily set up the system and adapt it to changing needs in the field.
Summary
Electric power is a critical element of rapid response disaster relief efforts. Generators currently used have high failure rates and require fuel supply chains, and standardized renewable power systems are not yet available. In addition, none of these systems are designed for easy adaptation or repairs in the field to...
READ MORE