WO2021194820A1 - Systèmes de détection et d'atténuation de défaillance de réseau électrique local - Google Patents

Systèmes de détection et d'atténuation de défaillance de réseau électrique local Download PDF

Info

Publication number
WO2021194820A1
WO2021194820A1 PCT/US2021/022717 US2021022717W WO2021194820A1 WO 2021194820 A1 WO2021194820 A1 WO 2021194820A1 US 2021022717 W US2021022717 W US 2021022717W WO 2021194820 A1 WO2021194820 A1 WO 2021194820A1
Authority
WO
WIPO (PCT)
Prior art keywords
facility
sensor
data
grid
model
Prior art date
Application number
PCT/US2021/022717
Other languages
English (en)
Inventor
Steve Chan
Original Assignee
Vit Tall Llc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vit Tall Llc filed Critical Vit Tall Llc
Publication of WO2021194820A1 publication Critical patent/WO2021194820A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
    • H02J3/0012—Contingency detection
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/30—State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Definitions

  • Power distribution systems also known as electrical power grids
  • electrical power grids are used to transmit power from power generators to consumers.
  • power distribution systems have become increasingly complex and more difficult to govern, resulting in increased monitoring needs.
  • the present disclosure deals with systems and methods for monitoring and controlling the nodes in an electrical grid.
  • certain institutional consumers such as healthcare facilities, may account for a significant portion of the overall load on the grid, and faults near or in such large consumer sites may have significant effects on the overall distribution system.
  • the influence of these fault events are further complicated when the facility has dual roles as both a producer and consumer, i.e., large institutional consumers may function as significant power generators in the grid due to use of on-site renewable resources such as solar arrays. Accordingly, there is a need for advanced self-monitoring systems at key nodes in an electrical grid.
  • Severe Acute Respiratory Syndrome Coronavirus-2 (SARS- CoV-2) is the name given to the 2019 novel coronavirus. (COVID-19 is the name given to the disease associated with the virus.)
  • SARS- CoV-2 Severe Acute Respiratory Syndrome Coronavirus-2
  • COVID-19 is the name given to the disease associated with the virus.
  • the 2019 novel coronavirus is genetically closely related to the SARS-CoV-1 virus.
  • heat at 56°C kills the SARS coronavirus at around 10,000 units per 15 min (quick reduction).
  • the 2019 novel coronavirus can be killed in water at 56°C or higher after 30 minutes.
  • the London School of Hygiene and Tropical Medicine “to actively kill the virus you need temperatures of around 60 degrees [Celsius].”
  • Hospitals stand out in their convergence of workers (e.g. nurses, aides, paramedics, doctors, orderlies/maids, janitors, garbage collectors, security, police, etc.), who face the greatest coronavirus risk. It is anticipated that patient linens and towels as well as staff uniforms will go through the laundry cycle at higher frequency and volume at 60°C so as to kill viruses in the fabric.
  • the hospital itself is fairly porous as members of the community will go in and out of certain areas, so this type of mitigation (similar to hand sanitizer) may be crucial.
  • hospitals are expected to operate their washing and drying facilities above normal loads around the clock. Given the extra load, the risk of a power outage is higher.
  • HVAC Heating, Ventilation, and Air Conditioning
  • a distribution utility might utilize load management techniques, also known as demand-side management, to balance the supply of electricity on the network with the electrical load by using special tariffs to influence consumer behavior (e.g. raise rates during certain times to reduce demand), but these techniques might not be effective amidst these coronavirus times.
  • load management techniques also known as demand-side management
  • these techniques might not be effective amidst these coronavirus times.
  • the inventories have been depleted. Accordingly, higher electricity prices will likely not deter electricity consumption.
  • distribution systems have been developed to service daily demand throughout the physical grid under typical behavior conditions. But the pandemic has displaced millions of workers from commercial districts to their residences, which is expected to alter the geographic distribution of daily power demands.
  • the hospital is not forecasting/granularly assessing their power requirements in real time; in some cases, hospitals are also independent power producers and even sell energy back to the utility. Prior to making these decisions, hospitals can make certain assessments in real-time regarding their needs. Hospitals can significantly increase operational efficiency with real time data and around-the-clock monitoring.
  • the monitoring of key power distribution equipment (servicing the facility) for aberrations and the monitoring of the incoming current and voltage channels for aberrations can help increase energy resiliency, improve efficiency, and enable greater self-sufficiency for the facility.
  • the disclosure relates to local facility power grid monitoring systems and methods.
  • the system may include sensors of various types positioned both within the facility and in proximity to a distribution line of the external power grid.
  • the sensors transmit event data to a base station or central controller.
  • the sensors may detect aberration events independently of the base station controller.
  • Facility power conditions are modeled at the base station based on the event data over time, i.e., the model is trained to recognize normal and fault conditions based on a variety of available data. New event data can then be processed and evaluated using the model to classify the current condition or event as normal operations or a fault status.
  • the base station may identify the type(s) and location(s) of the faults based on the new event data and the historical model, and report such faults to a service provider, such as a maintenance office or system at the facility and/or the local power generation, transmission, and distribution utilities.
  • a service provider such as a maintenance office or system at the facility and/or the local power generation, transmission, and distribution utilities.
  • Inventive methods according to the disclosure may include receiving power event data from diverse sensors both outside and inside a facility and computing a historical model of the facility power system status conditions based on the event data.
  • the current status of the facility power system may be identified by classifying new incoming event data according to the model, and the model may be updated based on additional data. Such updating may occur as single, occasional, periodic, or continuous recalculations.
  • aberrant noise and spark emissions may be detected as well as aberrant waveforms.
  • the equipment at key poles servicing the hospital can be monitored for such aberrations; likewise, the power systems at the hospital can also be monitored for such aberrations. In this way, service personnel may be dispatched prior to terminal failure.
  • Figure 1 is a diagram of an implementation of a local power monitoring system in relation to a consumer facility in an electrical grid.
  • Figure 2 is a diagram of a monitoring and decision method for use with systems of
  • Figure 3 is a detailed view of sensor data conversions compatible with the systems and methods of FIGS. 1-2.
  • Figure 4 is a detailed partial view of an embodiment of the monitoring and decision method of FIG. 2.
  • An electrical grid is defined as, among other components, an electrical power system network comprised of generating station(s) (a.k.a. power plant), utilities, substations, feeders, consumer(s), etc. Between the ends (i.e. generating station, consumer), electrical power may flow through substations at various voltage levels. Ideally, this is architected so as to minimize the power loss along the generation-transmission-distribution pathway by maintaining a higher voltage whenever possible.
  • An electric utility is a company within the electric power industry (often a public utility) that engages in any of electricity generation, transmission, and/or distribution as pertains to an electric grid.
  • a distribution utility constructs and maintains the distribution wires connecting the transmission system to the final electricity consumer.
  • substations are a key component of the constitutive generation, transmission, and distribution systems comprising the involved grid. The purpose of a distribution substation is to transfer power from the transmission system to the distribution system of an area.
  • distribution substations also regulate voltage (although for long distribution lines, i.e., circuits, voltage regulation equipment may also be installed along the circuits) and isolate faults.
  • Several distribution substations (DS) may comprise a distribution utility.
  • “Feeders” represent the power lines through which electricity is transmitted within power systems.
  • a distribution feeder represents one of the circuits emanating from a DS, and it transmits power from a DS to the designated distribution points serving electricity to the consumer.
  • a feeder may segue into primary and/or lateral distribution lines which carry medium voltage power to distribution transformers located near the electricity consumer. Distribution lines may include two or three wires which carry, respectively, two or three phases of current.
  • a transformer is an electrical device consisting of two or more coils of wire that transfer electrical energy between two or more circuits by means of a varying magnetic field (a varying current in one coil of the transformer produces a varying magnetic flux, which, in turn, induces a varying electromotive force across a second coil wound around the same core).
  • a distribution transformer provides the final voltage transformation within an electric power distribution system.
  • the electricity consumers are served with single-phase power in the form of secondary distribution lines (SDLs) which carry lower voltage power to the electricity consumer.
  • SDLs secondary distribution lines
  • feeder line 130 supplies power to facility 140 from substation 121.
  • a first sensor package A (150) is placed in proximity to feeder line 130 and detects events from the power grid observable at line 130.
  • the sensor package A is configured to relay event data to a modeling unit 170 which is preferably located within the facility 140. Event data may be communicated from the sensor package 150 to the modeler on an occasional or periodic basis or as a continuous data stream.
  • first sensor package A may include audible noise detectors or spectrum analyzers and/or spark analyzers or other visual or photo sensors. In some embodiments, this equipment may be implemented with low-cost components such as simple microphones.
  • the sensor package A may detect both the light activity followed by a change in the baseline or mean audio frequencies at the feeder line 130.
  • Equipment malfunctions such as failure of a transformer would be expected to significant audible and visible aberrations which would be communicated to the modeler 170.
  • facility 140 may also be serviced by additional or alternative feeder lines such as feeder line 135 as seen in dashed lines of FIG. 1.
  • facility 140 may operate as a campus of multiple structures and have multiple access points to the external power grid despite some shared operations and services within the campus.
  • feeder line 135 may be serviced from the same substation 121 as feeder line 130 or from a different substation 122, or feeder line 135 could distribute from a different power utility generator or distributor. Similar to sensor package 150, optional feeder line 135 may be outfitted with a sensor package A’ (155) to monitor grid events on at the feeder line 135 and report to the model and decision processor 170.
  • sensor package A 155
  • the particular types of sensors in package A’ (155) may be the same as or different from the sensors in package A (150), but, when used, would transmit event data in to modeler 170 as described above.
  • Sensor package B preferably includes one or more of an electromagnetic interference (EMI) sensor, radiofrequency interference (RFI) sensor, a digital fault recorder (DFR), and a phasor measurement unit (PMU).
  • EMI electromagnetic interference
  • RFID radiofrequency interference
  • DFR digital fault recorder
  • PMU phasor measurement unit
  • sensor package B may include a subsynchronous oscillation detection unit (SSODU) capable of detecting and/or estimating interharmonic phasors.
  • SSODU subsynchronous oscillation detection unit
  • sensor package B (160) may detect various events such as voltage drops, phase or current changes, and distortion in the power supply as well as EMI or RFI interference in the hyper-local environment.
  • internal sensor package B 160 is reproduced in multiple instances throughout the physical facility so that more accurate modeling and detection can be performed as discussed below. For example, monitoring the facility power events within different departments or even in individual rooms at a hospital facility will permit higher resolution data analysis and more targeted deployment of resources when corrective action is needed.
  • the processor or modeler 170 receives event data from the sensor packages 150, 155, 160.
  • the modeling process is executed in one central device or base station; but some modeling algorithms may be amenable to parallel or distributed processing. Indeed, in some implementations, the optimal system for a given facility may involve many internal and external sensor packages and may use multiple modelers to detect and monitor events in different areas of a facility.
  • FIG. 2 is a diagram of a monitoring and decision method 200 for use with systems as exemplified in FIG. 1.
  • the modeling engine 210 may receive data 251 from external sensor package A as well as data 252 from internal sensor packages as discussed above. Either or both of “A” data 251 and “B” data 252 may be subject to certain data conversion steps 261, 262, which are discussed in more detail in connection with FIG. 3, below.
  • step 220 an initial model is built based on a time series of training data from the sensor packages which predicts local power status conditions based on the sensor inputs.
  • the model may be applied in step 230 to determine a state.
  • the new input data and state determination may be used to update the model in step 240.
  • step 270 If application 230 results predicting or observing a fault condition, the engine identifies the fault in step 270. In step 280, additional features of the fault, for example, the type(s) (either actual, if known, or predicted) and location(s). The process may then proceed to notifying 290 a service provider, such as facility maintenance systems or the electrical utility operator.
  • a service provider such as facility maintenance systems or the electrical utility operator.
  • Figure 3 is a diagram of data conversion steps 300 which may be used in the systems and methods of FIGS. 1-2.
  • Sensor data 350 may be received in conversion process 360.
  • Conversion 360 may include various tasks depending on the types of sensor proving the data 350 and system design considerations.
  • the data 350 is used to generate a heatmap 362, as certain modeling algorithms operate on the basis of visual or pseudo-visual data or data representations, as discussed further below.
  • heatmaps may be 4D and represent interference or aberrations as accumulated and recorded over time rather than discrete events.
  • the heatmap may represent the intensity of interference observed in a particular area of the facility, and the time element may help correlate that phenomenon to operation of other equipment in that area or nearby, or to observed power grid events. Additional conversion operations include conversion of physical phenomena to discrete vector data suitable for further processing as in step 364. For example, an audio spectrum analyzer may convert a real sample to a Di -dimensional noise vector, while similarly a spark analyzer may convert a real sample to a D2-dimensional spark vector.
  • other sensors may provide data in formats that are more suitable for numerical modeling in their native forms, e.g., numerical voltage and phase data from discrete sampling of the power system within the facility.
  • Data conversion 360 may also include de-noising and/or auto encoding 366 to fill in missing or sparse datasets. Additionally, conversion 360 may account for equipment lifetime factors and calibration drifts. For example, power distribution equipment may experience thermal stress, mechanical stress, electrical stress, and combinations thereof from both normal lifetime usage and acute intense events. Adjustment process 368 may account for equipment age and known stressors to normalize the data that is used in subsequent modeling processes.
  • FIG. 4 shows a detailed view of the modeling process 220 from FIG. 2.
  • Training dataset 410 may be time series of data from sensor packages A and B, modified by appropriate data conversion steps, as discussed above in connection with FIGS. 1-3.
  • a forward-propagating step 420 the initial training is performed based on the training data input 410 to produce a model 430. Pertinent features of the data can be extracted from the model in step 450, which are then used to develop a classifier 460. As new data 440 is received, it is evaluated in relation to the model 430 and proceeds through feature extraction 450 and classification 460. That result may then be used to update the model 230 in back propagation step 470.
  • model 430 is a convolutional generative adversarial neural network (CGANN) algorithm.
  • the CGANN is a combination of generative adversarial networks (GAN) and convolutional neural networks (CNN).
  • GAN generative adversarial networks
  • CNN convolutional neural networks
  • a GAN model consists of two different neural networks; a generator G is often represented as (z), and a discriminator D is often represented as (x).
  • the generator G is responsible for the generation of data, and the discriminator D functions to ascertain the quality of the generated data and provide feedback to generator G. Through multiple cycles, the generation and discrimination network train each other. D is trained to maximize the probability of assigning the correct label to both training examples and samples from G, and G is trained to minimize log (1 - ((z))).
  • the GAN approach has a number of advantages, such as the fact that the learning process does not take a great deal of time, as GANs do not require label data, and the generated data is similar to real data; accordingly, there is an inherent ability to learn complicated distribution data (grouping or the density of the observation).
  • the generator network and discriminator network for a GAN can be any of the neural network types.
  • the CNN is used for a convolutional adversarial neural network (CANN).
  • CNN has shown excellent performance for several applications, such as object detection, medical analysis, and image classification.
  • the basic concept of CNN is to obtain local features from input at higher layers and combine them into more complex features at lower layers.
  • CNN utilizes the back-propagation algorithm.
  • CNN is usually utilized on visual data, and if CNN is utilized on non-visual data, it is necessary to encode the data in a way that mimics the properties of visual data.
  • CANN networks utilize convolutional layers within the generator network and discriminator network of GAN.
  • a CANN system is a network with convolutional layers, followed by normalization or pooling layers and an activation function.
  • the discriminator network takes the data and downsamples it with the assistance of convolutional and pooling layers and then utilizes a dense classification layer to predict the data.
  • the generator network takes a random noise mechanism, and finally generates the data.
  • a fully convolutional network is a network without fully connected dense layers at the end of the network. Instead, it consists of convolutional layers and can be end-to-end trained, such as that of a convolutional network with fully connected layers. There are no pooling layers in a generator network, while the discriminator network has fully connected layers with a classifier at the end of the layer.
  • classifier is a nonlinear support vector machine (SVM) classifier.
  • SVM is a widely accepted supervised machine learning technique that is used for either classification or regression.
  • SVM has the ability to ascertain the unknown relationship between a set of input variables and the output of the system, can be trained with quadratic programming (QP) and exhibits good learning ability for small samples.
  • QP quadratic programming
  • SVM can also leverage the structural risk minimization (SRM) principle to minimize the training error.
  • the output from the feature extractor may fed into the nonlinear SVM model as inputs, while the pre-trained CNN is utilized as a starting point for new input data using a nonlinear SVM classifier.
  • the transfer learning mechanism facilitates enhanced accuracy for new tasks.
  • the CNN and finely tuned SVM amalgam can effectively handle nonlinear complexities and short-term dependencies of the electrical time series data.
  • a monitoring system may combine a pole- mounted noise sensor outside of a hospital with an EMI sensor inside a nearby room of the hospital.
  • a CGANN model trained on data generated by the sensors over time will establish a baseline of normal operating conditions, as well as correlating aberration events, i.e., powerline surges may be detected as both noise and EMI in the facility, and appropriate corrective measures can be taken such as calling service personnel for equipment maintenance or replacement, or the protection or relocation of sensitive medical equipment in the affected areas.
  • These data fusion systems and methods combining both external grid event and internal power system observations, enables predictive/preventive maintenance rather than simply corrective maintenance. Thus, critical equipment failures may be avoided.
  • power supply failures at a facility may cascade into system disruptions in the broader community. The advance warnings provided by the technology of the present disclosures may prevent such disruptions.
  • CANN Convolutional Adversarial Neural Network

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Power Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Molecular Biology (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Public Health (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

L'invention concerne des systèmes et des procédés de gestion de réseau électrique et d'atténuation de panne. Des combinaisons de données provenant de capteurs positionnés à l'intérieur ainsi qu'à l'extérieur d'une installation du nœud clé sont utilisées pour prévoir et détecter des défaillances.
PCT/US2021/022717 2020-03-27 2021-03-17 Systèmes de détection et d'atténuation de défaillance de réseau électrique local WO2021194820A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202063000792P 2020-03-27 2020-03-27
US63/000,792 2020-03-27

Publications (1)

Publication Number Publication Date
WO2021194820A1 true WO2021194820A1 (fr) 2021-09-30

Family

ID=77890441

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/022717 WO2021194820A1 (fr) 2020-03-27 2021-03-17 Systèmes de détection et d'atténuation de défaillance de réseau électrique local

Country Status (1)

Country Link
WO (1) WO2021194820A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117094475A (zh) * 2023-10-18 2023-11-21 合肥工业大学 一种电力配电网故障分析系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140163759A1 (en) * 2009-10-30 2014-06-12 The Trustees Of Columbia University In The City Of New York Digital building operating system with automated building and electric grid monitoring, forecasting, and alarm systems
WO2016004433A1 (fr) * 2014-07-04 2016-01-07 Apparent Inc Agrégation de passerelle de réseau maillé
JP6298465B2 (ja) * 2013-07-12 2018-03-20 パナソニック株式会社 電力管理装置、電力管理システム、サーバ、電力管理方法、プログラム
US10476273B2 (en) * 2013-03-15 2019-11-12 Dominion Energy, Inc. Management of energy demand and energy efficiency savings from voltage optimization on electric power systems using AMI-based data analysis
US20200097988A1 (en) * 2018-05-06 2020-03-26 Strong Force TX Portfolio 2018, LLC Systems and methods for forward market price prediction and sale of energy storage capacity

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140163759A1 (en) * 2009-10-30 2014-06-12 The Trustees Of Columbia University In The City Of New York Digital building operating system with automated building and electric grid monitoring, forecasting, and alarm systems
US10476273B2 (en) * 2013-03-15 2019-11-12 Dominion Energy, Inc. Management of energy demand and energy efficiency savings from voltage optimization on electric power systems using AMI-based data analysis
JP6298465B2 (ja) * 2013-07-12 2018-03-20 パナソニック株式会社 電力管理装置、電力管理システム、サーバ、電力管理方法、プログラム
WO2016004433A1 (fr) * 2014-07-04 2016-01-07 Apparent Inc Agrégation de passerelle de réseau maillé
US20200097988A1 (en) * 2018-05-06 2020-03-26 Strong Force TX Portfolio 2018, LLC Systems and methods for forward market price prediction and sale of energy storage capacity

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117094475A (zh) * 2023-10-18 2023-11-21 合肥工业大学 一种电力配电网故障分析系统
CN117094475B (zh) * 2023-10-18 2024-01-30 合肥工业大学 一种电力配电网故障分析系统

Similar Documents

Publication Publication Date Title
Huang et al. Data quality issues for synchrophasor applications Part I: a review
CN104617677B (zh) 确定电网故障类型的方法、设备及电网管理系统
CN107453483A (zh) 一种电网调度控制系统
Jiang et al. A vision of smart transmission grids
Zahraoui et al. A novel approach for sizing battery storage system for enhancing resilience ability of a microgrid
US20230133489A1 (en) Apparatus, systems, and methods for providing a rapid threshold amount of power to a customer load during transfer between a primary power supply and a secondary power supply
Poudel et al. A two‐stage service restoration method for electric power distribution systems
CN109726214A (zh) 一种设备故障处置辅助决策方法和系统
WO2021194820A1 (fr) Systèmes de détection et d'atténuation de défaillance de réseau électrique local
Wang et al. Optimal capacity planning for manufacturing, transportation, and replacement of quickly-detachable transformer modules in substations of resilient distribution networks
Haq et al. CLEAR—A circuit level electric appliance radar for the electric cabinet
Dhend et al. Efficient fault diagnosis in smart grid using non conventional mother wavelet function
JP3500758B2 (ja) 配電系統監視方法，配電系統制御方法およびそれら装置
Gopinathan et al. Smart Grid Architecture Model (SGAM) for resilience using Energy Internet of Things (EIoT)
Jiang Computational intelligence techniques for a smart electric grid of the future
Aıroboman Reliability Assessment of Power System Network: A Detailed Review
Myrda Optimizing Assets [In My View]
Guo Data analytics and application developments based on synchrophasor measurements
Uzunoğlu Locating distribution power system fault employing Bayes theorem with subjective logic
Ma et al. An initial study on computational intelligence for smart grid
Akpojedje et al. A survey of smart grid systems on electric power distribution network and its impact on reliability
Chan et al. The Paradox of Electromagnetic Interference Affecting Medical Devices at International Hospitals
Gaikwad et al. GSM based Distribution Transformer Monitoring System
US20230138521A1 (en) Switch device for a distribution network fed by more than one independent power source
US20230135520A1 (en) Network protector for secondary distribution network that includes distributed energy resources

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21774364

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21774364

Country of ref document: EP

Kind code of ref document: A1