An official website of the United States government
Processing large amounts of data, especially in learning algorithms, poses a challenge for current embedded computing systems. Hyperdimensional (HD) computing (HDC) is a brain-inspired computing paradigm that works with high-dimensional vectors called hypervectors . HDC replaces several complex learning computations with bitwise and simpler arithmetic operations at the expense of an increased amount of data due to mapping the data into high-dimensional space. These hypervectors, more often than not, cannot be stored in memory, resulting in long data transfers from storage. In this article, we propose Store-n-Learn, an in-storage computing solution that performs HDC classification and clustering by implementing encoding, training, retraining, and inference across the flash hierarchy. To hide the latency of training and enable efficient computation, we introduce the concept of batching in HDC. We also present on-chip acceleration for HDC encoding in flash planes. This enables us to exploit the high parallelism provided by the flash hierarchy and encode multiple data points in parallel in both batched and non-batched fashion. Store-n-Learn also implements a single top-level FPGA accelerator with novel implementations for HDC classification training, retraining, inference, and clustering on the encoded data. Our evaluation over 10 popular datasets shows that Store-n-Learn is on average 222× (543×) faster than CPU and 10.6× (7.3×) faster than the state-of-the-art in-storage computing solution, INSIDER for HDC classification (clustering).
more »
« less
Windfarm Forced Oscillation Detection Using Hyperdimensional Computing
Convolutional Neural Networks (CNNs) have been explored to detect forced oscillations in windfarm systems in the past. However, these CNNs require a significant amount of data samples between inference queries and a significant amount of computational power and time. This leads to systems that have a large delay between a forced oscillation occurring and detecting the forced oscillation. This paper presents a novel approach applying Hyperdimensional Computing (HDC) as an effective solution for the first time in forced oscillation detection to overcome the problems of CNNs. HDC is able to reduce the time to detect forced oscillations in two ways: First, by reducing the time needed to collect data to create a new inference sample by reducing the number of data points required. Second, by providing a significantly smaller, more energy efficient, and faster model for detection than current state-of-the-art. Our results show that HDC, with an FPGA implementation, is able to achieve 55× faster detection of forced oscillations in windfarms while achieving the same accuracy as the best current CNN models using software solutions.
more »
« less
- Award ID(s):
- 2334256
- PAR ID:
- 10553535
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-2445-7
- Page Range / eLocation ID:
- 3965 to 3972
- Format(s):
- Medium: X
- Location:
- Sorrento, Italy
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper presents a new methodology to detect low-frequency oscillations in power grids by use of timesynchronized data from phasor measurement units (PMUs). Principal component analysis (PCA) is first applied to the massive PMU data to extract the low-dimensional features, i.e., the principal components (PCs). Then, based on persistent homology, a cyclicity response function is proposed to detect low-frequency oscillations through the use of PCs. Whenever the cyclicity response exceeds a numerically robust threshold, a low-frequency oscillation can be detected instantly. Such swift detection can then be followed by modal analysis tools for more detailed information about the oscillation. Numerical examples using real data illustrate the effectiveness of the proposed methodology for quick detection of oscillations during operations.more » « less
-
Past research argues for an internal multidecadal (40- to 60-year) oscillation distinct from climate noise. Recent studies have claimed that this so-termed Atlantic Multidecadal Oscillation is instead a manifestation of competing time-varying effects of anthropogenic greenhouse gases and sulfate aerosols. That conclusion is bolstered by the absence of robust multidecadal climate oscillations in control simulations of current-generation models. Paleoclimate data, however, do demonstrate multidecadal oscillatory behavior during the preindustrial era. By comparing control and forced “Last Millennium” simulations, we show that these apparent multidecadal oscillations are an artifact of pulses of volcanic activity during the preindustrial era that project markedly onto the multidecadal (50- to 70-year) frequency band. We conclude that there is no compelling evidence for internal multidecadal oscillations in the climate system.more » « less
-
In recent years, the frequency of forced oscillation events due to control system malfunctions or improper parameter settings has increased. Tuning the parameters of exciters and governor models is crucial for maintaining power system stability. Traditional simulation studies typically involve small transient disturbances or step changes to find optimal parameter sets, but existing optimization algorithms often fall short in fine-tuning for forced oscillations. Identifying the sensitive parameters within these control models is essential for ensuring stability during large, sustained disturbances. This study focuses on identifying these critical exciter and governor model parameters by analyzing their influence on sustained forced oscillations. Using Kundur’s two-area system, we analyze common exciter models such as SCRX, ESST1A, and AC7B, along with governor models like GAST, HYGOV, and GGOV1, utilizing PSS®E software version 34. Sustained forced oscillations are injected at generator-1 of area-1, with individual parameter changes dynamically simulated. By considering a local oscillation frequency of 1.4 Hz and an inter-area oscillation mode of 0.25 Hz, we analyze the impact of each parameter change on the magnitude and frequency of forced oscillations as well as on active and reactive power outputs. This novel approach highlights the most influential parameters of each tested model—such as exciter, governor, and turbine gains, as well as time constant parameters—on the impact of forced oscillations. Based on our findings, the sensitive parameters of each tested model are ranked. These would provide valuable insights for industry operators to fine-tune control settings during oscillation events, ultimately enhancing system stability.more » « less
-
Abstract Although the connectivity offered by industrial internet of things (IIoT) enables enhanced operational capabilities, the exposure of systems to significant cybersecurity risks poses critical challenges. Recently, machine learning (ML) algorithms such as feature-based support vector machines and logistic regression, together with end-to-end deep neural networks, have been implemented to detect intrusions, including command injection, denial of service, reconnaissance, and backdoor attacks, by capturing anomalous patterns. However, ML algorithms not only fall short in agile identification of intrusion with few samples, but also fail in adapting to new data or environments. This paper introduces hyperdimensional computing (HDC) as a new cognitive computing paradigm that mimics brain functionality to detect intrusions in IIoT systems. HDC encodes real-time data into a high-dimensional representation, allowing for ultra-efficient learning and analysis with limited samples and a few passes. Additionally, we incorporate the concept of regenerating brain cells into hyperdimensional computing to further improve learning capability and reduce the required memory. Experimental results on the WUSTL-IIOT-2021 dataset show that HDC detects intrusion with the accuracy of 92.6%, which is superior to multi-layer perceptron (40.2%), support vector machine (72.9%), logistic regression (84.2%), and Gaussian process classification (89.1%) while requires only 300 data and 5 iterations for training.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/BigData59044.2023.10386628
