Power monitoring system and power monitoring method for power grid

Abstract

To provide a better indication of a transient event on a power grid.SOLUTION: The power monitoring system includes a power vector analyzer (PVA) 24 and a control center 30 that receives transient event data including one or more power images and associated metadata from the PVA, and one or more processors convert the one or more power images and associated metadata from the PVA into one or more transient event vectors and store them in a vector database 37.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to power grid monitoring, and more particularly to test and measurement systems for power grid monitoring, and more particularly to power vector analyzers (PVAs). [Background technology]

[0002] U.S. patent application Ser. No. 18 / 914,685, filed Oct. 14, 2024 (hereinafter the "'685 patent application," the contents of which are incorporated herein by reference), discloses a power vector analyzer (PVA) device for analyzing and monitoring power on a line.

[0003] Typically, units called phasor measurement units (PMUs) monitor the power grid. PMUs measure the voltage, current, and frequency of the electricity flowing through them. PMUs collect time-synchronized data, which is useful for detecting and identifying grid faults such as blackouts, voltage sags, and other power quality issues. PMUs are installed at various locations within the power grid to provide a comprehensive view of the system's health and enable real-time monitoring and control.

[0004] A PMU typically displays a phasor diagram, which shows the phase angles of the voltage and current vectors for each of the three phases at the location of a three-phase source on the grid. Phasor diagrams, such as 10 in Figure 1, are continually updated as the phase angles change due to reactive loads. Similarly, the voltage and current display on the right shows the voltages of the three different phases as 12, 14, and 16, and the currents of the three different phases as 13, 15, and 17. Area 18 in the current display indicates a transient event. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] U.S. Patent No. 6,525,522 [Patent Document 2] US Patent Application Publication No. 2025 / 0130279 [Patent Document 3] Japanese Patent Application Publication No. 2025-071074 [Patent Document 4] Japanese Patent Publication No. 2024-020154 [Non-patent literature]

[0006] [Non-Patent Document 1] "Phasor measurement unit" article, Wikipedia (English version), [Online], [Retrieved July 23, 2025], Internet<https: / / en.wikipedia.org / wiki / Phasor_measurement_unit> [Non-patent document 2] "5 Series B MSO Mixed Signal Oscilloscope Data Sheet," Tektronix, [online], [Retrieved July 23, 2025], Internet<https: / / www.tek.com / ja / datasheet / 5-series-b-mso-mixed-signal-oscilloscope-datasheet> [Non-patent document 3] "Analysis of EV Traction Inverter," Tektronix, [online], [Retrieved July 23, 2025], Internet<https: / / www.tek.com / ja / products / reference-solutions / ev-traction-inverter-testing> [Non-patent document 4] "Three-Phase Inverter / Motor / Drive Analysis," Tektronix, [online], [Retrieved November 22, 2025], Internet <https: / / www.tek.com / ja / datasheet / inverter-motor-drive-analysis-5series-mso-option-5-imda-application-datasheet> Summary of the Invention [Problem to be solved by the invention]

[0007] However, it is not possible to easily determine the direction of the transient power, the magnitude, the transient apparent power, or how it oscillates between inductive and capacitive reactance at a particular instance. [Means for solving the problem]

[0008] Embodiments as disclosed herein provide a better view and deeper understanding of the characteristics of transient events on the power grid, such as complex dynamic bidirectional apparent power transient events. The origin of these events, referred to herein as transient events, may consist of any of numerous examples, such as a large inductive power start-up, a sudden power injection from a megawatt charging station, a downed power line, an exploding power transformer, or a lightning strike. The present embodiments provide a graphical display that captures all aspects of the dynamic power transient fluctuations in power magnitude, phase angle, and direction over the duration of the transient event.

[0009] The present embodiment normalizes and isolates transient events by incorporating a new tracking limit test circle and defining a tracking null normalization process that removes static power from each PVA and observes the transient event at various GPS locations. This feature allows the system to ignore static power, which changes continuously at a rate slower than that seen in transient events. The static power may be different at various locations on the PVA at various times. The power levels at various monitoring points on the grid may change at various points on the grid at various times, but may not be related to transient events. The embodiment normalizes or nulls out the static power at each normalized location. In this way, each PVA location observing a dynamic transient will observe the transient as it propagates from its source to various other remote locations, causing changes or affecting the PVA. This provides a multifaceted view of the transient event, which can help locate it with the help of an AI vector database of many types of past transient events and known information about these events.

[0010] The present embodiment also creates image and text sequences of the transient event captured from each PVA that captured the event. The embodiment creates a tensor representation of this group of images to obtain a single AI embedding vector for the event data from all PVAs. A language describes the cause, location, or other key characteristics of the event and is associated with the embedding vector for that event. Over time, the vector database grows so the AI ​​system can classify new events occurring on the grid. The vector database can reside in a distribution center, transient substation, control station, or can be distributed throughout the system, automatically updating between sites. [Brief explanation of the drawings]

[0011] [Figure 1] Figure 1 shows an example of a diagram displayed by a phasor measurement unit. [Figure 2] Figure 2 shows an embodiment of a power grid using a power vector analyzer (PVA). [Figure 3] Figure 3 shows a system diagram of an embodiment of a power control system that includes multiple PVAs distributed across a power grid, a tensor builder, and an artificial intelligence embedded processing with a vector database. [Figure 4] Figure 4 shows an embodiment of a user interface on a power vector analyzer (PVA) that displays the quiescent power of a three-phase source. [Figure 5] Figure 5 shows an embodiment of the user interface on the PVA during static power nulling. [Figure 6] Figure 6 shows an embodiment of a user interface on the PVA displaying nulled quiescent power. [Figure 7] Figure 7 shows an embodiment of a user interface on the PVA that displays measured power transient events against nulled quiescent power. [Figure 8] Figure 8 shows an embodiment of the user interface on the PVA displaying tracking limit test circles for three phases of power. [Figure 9] Figure 9 shows an embodiment of the user interface on the PVA, displaying small transient events that cross the limit circle and generate a trigger. [Figure 10] Figure 10 shows an embodiment of a user interface on the PVA displaying transient events after application of tracking nulling. DETAILED DESCRIPTION OF THE INVENTION

[0012] 2 illustrates an embodiment of a power grid that includes PVAs at strategic locations, which in one embodiment can be identified by GPS coordinates using satellites such as 38. These PVAs may exist in more or fewer locations than those shown. The power grid may include, for example, power generating plants such as 20, transmission pylons such as 22, transmission or distribution substations such as 26, alternative energy generating sites such as wind farms 36, solar farms (not shown), power distribution centers (PDCs) such as 28, and one or more control centers such as 30. PVAs may also exist at power consuming sites, including office or industrial buildings such as 32, single-family homes such as 34, and residential buildings such as 35.

[0013] In an embodiment, the power grid may have a large area with multiple sub-grids, or it may have only one sub-grid. The PDC 28, the control center 30, and all PVAs in the power grid communicate via wireless, wired, or satellite communications. Each PVA may communicate only with the PDC, only with the control center, or among itself. In one embodiment, a vector database 37, shown in FIG. 3, aggregates all information from all PVAs. This can be used to develop derived functions related to grid monitoring and grid enhancement, including, but not limited to, prescribed artificial intelligence (AI) / machine learning (ML) services. AI / ML services may include, but are not limited to, predictive measures such as predictive maintenance, load sharing / peak power distribution, and identifying abnormal trends.

[0014] For reference, an example PVA configuration based on some examples of the present disclosure can be implemented using existing hardware, including an MSO58 oscilloscope (see Non-Patent Document 2) running the Inverter Motor Drive Analysis (IMDA) software package (see Non-Patent Document 4), three TCP0030A high-current probes, and three THDP0100 high-voltage probes, all manufactured by Tektronix, plus additional analysis software. The MSO58 oscilloscope includes a processor and storage memory, which enable it to run, for example, a Windows® operating system and PC application software. Therefore, each PVA may run machine learning software, such as Tektronix's "OptaML," which provides a tensor builder, as described in more detail below (see also Patent Document 4).

[0015] FIG. 3 shows a block diagram of how PVAs and the control center communicate transient events and how the control center can classify transient events. As described with respect to FIG. 2, multiple PVAs (e.g., 24) exist at various locations on the power grid. All PVAs communicate transient event data back to the control center 30. Each PVA may see the same event, providing a unique, multi-dimensional perspective for each PVA location. "Power images," as used herein, refer to images showing transient events communicated by these PVAs. These images include tracking limit test circles, described below, which are useful for identifying the presence and partial magnitude of transient events.

[0016] The tensor builder 33 is responsible for taking apparent power images and metadata from multiple PVAs and integrating them into a single tensor space to create vectors. The process of building tensors is part of the process of building vectors, which involves placing images from the database into videos and integrating the videos into a single vector through the AI ​​embedding model 35 and its transformers. Alternatively, each image and text can be passed through an AI model, such as CLIP (Contrastive Language-Image Pre-training), to create image and text vectors in the vector database 37. While this process creates vectors for each power image from each PVA, multiple vectors for a single event must be combined and compared, for example, by pooling or averaging. The end result is that the AI ​​embedding process, once configured and pre-trained as needed, can continuously add and distinguish new data without the need for retraining, even as grid characteristics change over time. New transient events are formed as tensors, which then become vector embedding representations. This vector is then matched with vectors stored in a database to classify the characteristics of the event. If there is no match, the system notifies the operator, who then provides a classification for the vector to be stored in the database.

[0017] As mentioned above, the vector database may also contain vectors related to monitoring the grid without transient events. The control center may collect information from the PVA periodically or during specific events other than transient events, such as peak power usage or high load events. The ML system may create vectors for these events with solutions such as load balancing or changes in power distribution. If there are conditions during normal operation that require a response, the ML system may provide services to better manage power distribution.

[0018] FIG. 4 shows an embodiment of a PVA. This embodiment of the PVA can display the quiescent power signal on a line in a power grid. FIG. 4 shows a user interface 40 with controls on the left and the user interface 40 on the right. Points 42, 44, and 46 represent the "reference" apparent power signal for each of the three phases on a polar grid, with each phase 120 degrees out of phase with the other two. Lines 48, 50, and 52 and the points on these axes represent zero phase between their voltage and current. Points "above" these lines have inductive reactance, and points "below" these lines have capacitive reactance. Lines 50 and 52 are 120 degrees out of phase with line 48 and represent the phase difference of the power line. The term "reference apparent power" refers to the apparent power displayed before quiescent power removal and is used to distinguish it from apparent power measured after nulling.

[0019] FIG. 5 shows an embodiment of a user interface for the null calculation process, which is described in more detail below. The null process essentially removes quiescent power from apparent power measurements, allowing for more accurate display and measurement of transient power fluctuations. This process may involve using a quadrature synchronous detector (QSD) such as that described in the '685 patent application, which is incorporated by reference in its entirety. A QSD or similar device generates a null vector that "nulls" the quiescent power, displaying only the apparent power. The line 54 between points such as 42 and the center of chart 56 represents the process of determining the null vector; the system adds this null vector to the reference apparent power to remove the quiescent power from future measurements. FIG. 6 shows the resulting display after all three points have been moved to the center 56, indicating that quiescent power has been nulled and that apparent power is now zero on all three phases.

[0020] Figure 6 also shows limit circles 58, which allow the user or control center to set a limit mask, which defines how "far" or how large the apparent power measurement must be from the null center before it triggers a response in the PVA. By applying the null, the quiescent power of each line is "removed" from the display, allowing for better detection of transient events.

[0021] Figure 7 shows the transient apparent power variation relative to the null center, with the transient power shown for each phase, such as 60 for one phase. One or more lines have power levels that exceed the limit mask. When the apparent power transient signal exceeds the limit mask 58, the PVA sends a power image and associated metadata of the transient event to the control center. The user interface displays the message "Transient Detected." Note that the power image sent to the control center is a possible scenario. The control center receives power images from multiple PVAs, which allows for a geographical understanding of transient events, since PVAs in various locations may have different data depending on their location.

[0022] The PVA itself can act as a local node in the AI ​​network, detecting transient events, creating vectors, searching its local copy of the vector database, receiving the transient event classification, and then communicating the classification to other local nodes, including the control center, which can then update their local copies of the vector database.

[0023] The figures described above show events with a "fixed" null. This null does not change with the static power at the PVA's location in the grid. Embodiments of the present application use a "tracking" null to allow the transient event to be separated from the static power. This requires the use of a "tracking" limit circle.

[0024] In the figures above, the limit circles do not track the center of the static power. As mentioned above, users can define limit circles for plotted power signals to identify dynamic transient events. If the system does not track nulls, there will be three limit circles for each power phase, such as tracking limit circle 62 at point 42, as shown in Figure 8. Tracking nulls can be defined separately for each of the three tracking limit circles, which together form a tracking limit mask. The static power for each is the center point of the mask circle.

[0025] Figure 9 shows the display after a small transient event occurs on the power line. In this embodiment, all three phases exceeded the tracking limit mask. The transient event that triggers reporting to the central controller could occur in only one of these phases. The quiescent power in each circle is subtracted from the event total to obtain a power image. In this display, all three limit mask circles move to the center of the vector display. In this case, the power of the transient event is shown as a deviation from the quiescent power, as shown in Figure 10.

[0026] The PVA with tracking null and tracking gate for power grid monitoring according to embodiments of the present disclosure represents a major leap forward in the realm of power grid management and analytics. Embodiments of the present disclosure include a novel approach to grid-wide monitoring of complex, dynamic transient events, using advanced mechanisms such as tracking gate limit test circles and tracking null normalization. Embodiments of the present disclosure capture triggered transient power events from multiple PVAs, observe the events, and submit the data to an AI-embedded system for classification of the event's key characteristics. The innovative design and capabilities of this PVA represent a major advancement in modernizing and enhancing power grid analysis and maintenance.

[0027] Aspects of the disclosed technology may operate on specially created hardware, firmware, digital signal processors, or specially programmed general-purpose computers, including processors that operate according to programmed instructions. The terms "controller" or "processor" herein contemplate microprocessors, microcomputers, ASICs, and dedicated hardware controllers, among others. Aspects of the disclosed technology may be implemented with computer-usable data and computer-executable instructions, such as one or more program modules, executed by one or more computers (including a monitoring module) or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc., which, when executed by a processor in a computer or other device, perform particular tasks or implement particular abstract data types. Computer-executable instructions may be stored in computer-readable storage media, such as hard disks, optical disks, removable storage media, solid-state memory, RAM, etc. Those skilled in the art will appreciate that the functionality of the program modules may be combined or distributed as desired in various embodiments. Furthermore, such functionality may be embodied in whole or in part in firmware or hardware equivalents, such as integrated circuits, field programmable gate arrays (FPGAs), etc. Certain data structures may be used to more effectively implement one or more aspects of the disclosed technology, and such data structures are considered within the scope of the computer-executable instructions and computer-usable data described herein.

[0028] The disclosed aspects may, in some cases, be implemented in hardware, firmware, software, or any combination thereof. The disclosed aspects may also be implemented as instructions carried by or stored on one or more computer-readable media, which may be read and executed by one or more processors. Such instructions may be referred to as a computer program product. As used herein, computer-readable media refers to any medium that can be accessed by a computing device. By way of example, and not limitation, computer-readable media may include computer storage media and communication media.

[0029] "Computer storage media" means any medium that can be used to store computer-readable information. By way of example and not limitation, computer storage media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory and other memory technologies, compact disc read-only memory (CD-ROM), digital video disc (DVD) and other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage and other magnetic storage devices, and any other volatile or nonvolatile, removable or non-removable medium implemented in any technology. "Computer storage media" excludes signals themselves and transitory forms of signal transmission.

[0030] A communication medium means any medium usable for communicating computer-readable information. By way of example, and not limitation, communication media may include coaxial cable, fiber optic cable, air, or any other medium suitable for communicating electrical, optical, radio frequency (RF), infrared, acoustic, or other types of signals. Example

[0031] The following examples are provided to aid in understanding the technology disclosed in this application. Embodiments of the technology may include one or more of the examples described below, and any combination thereof.

[0032] A first embodiment is a power monitoring system, One or more power vector analyzers; one or more ports for receiving transient event data from the one or more power vector analyzers, the transient event data including one or more power images and associated metadata relating to the transient event; One or more processors and a power controller having said one or more processors: converting the one or more power images and the associated metadata from the one or more power vector analyzers into one or more transient event vectors; storing said one or more transient event vectors in a vector database; The one or more processors are configured to execute a program that causes the one or more processors to perform the steps of:

[0033] A second embodiment is the power monitoring system of the first embodiment, wherein the one or more processors: searching said vector database for a vector that matches any of said one or more transient event vectors; If a match is found, classifying the transient event using a classification based on the match; If no match is found, add the vector to the vector database. The one or more processors are further configured to execute a program that causes the one or more processors to perform the following:

[0034] Example 3 is a power monitoring system of either Example 1 or 2, wherein the program that causes the one or more processors to convert the one or more power images and associated metadata into one or more transient event vectors includes a program that causes the one or more processors to create a transient event vector for each of the power images and associated metadata.

[0035] Example 4 is the power monitoring system of Example 3, wherein the one or more processors are further configured to execute a program that causes the one or more processors to perform the following processes: aggregating the transient event vectors of each power image associated with the transient event by either averaging or pooling to generate an aggregated transient event vector; and searching the vector database using the aggregated transient event vector.

[0036] Example 5 is a power monitoring system of any of Examples 1 to 4, wherein the program that causes the one or more processors to convert the one or more power images and associated metadata into one or more transient event vectors includes a program that causes the one or more processors to arrange each of the one or more received power images into an image sequence and integrate the image sequence into one transient event vector.

[0037] Example 6 is the power monitoring system of any of Examples 1 to 5, wherein the power controller is located at a central location and the one or more power vector analyzers are distributed throughout the power grid.

[0038] Example 7 is a power monitoring system according to any one of Examples 1 to 6, wherein each of the one or more power vector analyzers is distributed throughout the power grid, each of the power vector analyzers incorporates the power controller, and the one or more power vector analyzers communicate with one or more other power vector analyzers to update the vector database of each of the power vector analyzers.

[0039] Example 8 is a power monitoring system of any of Examples 1 to 7, wherein each of the power vector analyzers further has one or more processors, and the one or more processors are configured to execute a program that causes the one or more processors to perform a process of defining a limit mask for each of the power phases displayed on the display of the power vector analyzer.

[0040] Example 9 is a power monitoring system of Example 8, wherein the one or more processors are further configured to execute a program that causes the one or more processors to receive a signal indicating that the power vector analyzer nulls the quiescent power of each power phase to be displayed on the display of the power vector analyzer, and to display the apparent power of each power phase.

[0041] Example 10 is the power monitoring system of Example 9, wherein the one or more processors are further configured to perform the following processes: determining that a transient event has occurred in one or more phases because the power has exceeded a tracking limit mask for that phase; subtracting the quiescent power of each of the power phases from the total event power; and displaying the image of the transient event as one or more power images in the center of the display while displaying the transient event as a deviation from the quiescent power.

[0042] Example 11 is the power monitoring system of any of Examples 1 to 10, wherein the vector database resides in a centralized location, and the one or more processors are further configured to execute a program that causes the one or more processors to monitor the operation of the power grid and provide one or more artificial intelligence and machine learning services including at least one of predictive measures, predictive maintenance, load balancing, peak power distribution, and identifying abnormal trends.

[0043] Example 12 is a method for monitoring power in a power grid, comprising: receiving one or more power images and associated metadata relating to a transient event of at least one of the three phases of power from one or more power vector analyzers; converting the one or more power images and associated metadata from the one or more power vector analyzers into one or more transient event vectors; and storing the one or more transient event vectors in a vector database.

[0044] Example 13 is the method of example 12, further comprising: searching the vector database for a vector that matches any of the one or more transient event vectors; and, if a match is found, classifying the transient event using a classification based on the match.

[0045] Example 14 is a method of either example 12 or 13, wherein the process of converting the one or more power images and associated metadata into one or more transient event vectors includes generating a transient event vector for each of the power images and associated metadata.

[0046] Example 15 is the method of Example 14, wherein the process of converting the one or more power images and associated metadata into one or more transient event vectors includes aggregating, by either averaging or pooling, the transient event vectors of each of the power images associated with a transient event to create an aggregated transient event vector, and searching the vector database using the aggregated transient event vector.

[0047] Example 16 is a method of any of Examples 12 to 15, wherein the process of converting the one or more power images and associated metadata into one or more transient event vectors includes a process of arranging each of the one or more received power images into an image sequence, and a process of combining the image sequence into one transient event vector.

[0048] Example 17 is the method of any of Examples 12 to 16, further comprising: receiving a signal at the one or more power vector analyzers indicating that the one or more power vector analyzers null the quiescent power of each of the power phases displayed on a user interface of any of the one or more power vector analyzers; and displaying the apparent power of each of the power phases.

[0049] Example 18 is the method of example 17, further comprising: determining that a transient event has occurred in one or more phases because the power has exceeded a tracking limit mask for that phase; subtracting the quiescent power of each of the power phases from the total event power; and selecting one or more power images as the image of the transient event, and displaying the power image of the transient event in the center of the display while displaying the transient event as a deviation from the quiescent power.

[0050] Example 19 is the method of any of Examples 12 to 18, further comprising: monitoring operation of the power grid; and providing one or more artificial intelligence and machine learning services including at least one of predictive measures, predictive maintenance, load balancing, peak power balancing, and identifying abnormal trends.

[0051] All features disclosed in the specification, claims, abstract and drawings, and all steps in any disclosed method or process, may be combined in any combination, except where at least some of such features or steps are mutually exclusive combinations. Each feature disclosed in the specification, abstract, claims and drawings may be replaced by an alternative feature serving the same, equivalent or similar purpose, unless expressly stated otherwise.

[0052] Additionally, the description of this application refers to specific features. It should be understood that the disclosure herein includes all possible combinations of these specific features. When a specific feature is disclosed in connection with a particular aspect or example, that feature can also be used in connection with other aspects and examples, to the extent possible.

[0053] Furthermore, when this application refers to a method having two or more defined steps or processes, these defined steps or processes may be performed in any order or simultaneously, unless the circumstances do not preclude this possibility.

[0054] Although specific examples have been set forth for the convenience of explanation, it will be appreciated that various modifications may be made without departing from the spirit and scope of the present disclosure. [Explanation of symbols]

[0055] 20 Power Plant 22 Power line tower 24 Vector Analyzer (PVA) 26 Transmission / Distribution Substations 28 Power Distribution Center (PDC) 30 Control Center 33 Tensor Builder 35 AI embedded models 36 Wind Power Plants 37 Vector Databases 38 GPS satellites

Claims

1. A power monitoring system, comprising: one or more power vector analyzers; one or more ports for receiving transient event data from the one or more power vector analyzers, the transient event data including one or more power images and associated metadata relating to the transient event; one or more processors and a power controller having the one or more processors: converting the one or more power images and the associated metadata from the one or more power vector analyzers into one or more transient event vectors; storing the one or more transient event vectors in a vector database; a power monitoring system configured to execute a program that causes the one or more processors to perform the above steps.

2. the one or more processors: searching said vector database for a vector that matches any of said one or more transient event vectors; If a match is found, classifying the transient event using a classification based on the match; If no match is found, add the vector to the vector database.

2. The power monitoring system of claim 1, further configured to execute a program that causes the one or more processors to:

3. a program causing the one or more processors to convert the one or more power images and associated metadata into one or more transient event vectors, generating a transient event vector for each of the power images and associated metadata; aggregating, by either averaging or pooling, the transient event vectors for each power image associated with the transient event to generate an aggregate transient event vector; searching said vector database using said integrated transient event vector; 2. The power monitoring system of claim 1, further configured to execute a program that causes the one or more processors to:

4. 2. The power monitoring system of claim 1, wherein the program that causes the one or more processors to convert the one or more power images and associated metadata into one or more transient event vectors includes a program that causes the one or more processors to arrange each of the one or more received power images into an image sequence and integrate the image sequence into a single transient event vector.

5. 2. The power monitoring system of claim 1, wherein each of the one or more power vector analyzers is distributed throughout the power grid, each of the power vector analyzers includes the power controller, and each of the one or more power vector analyzers communicates with one or more other power vector analyzers to update the vector database of each of the power vector analyzers.

6. the one or more processors: receiving a signal indicating that the power vector analyzer is to null the quiescent power of each of the power phases displayed on the power vector analyzer display; Processing to display the apparent power of each power phase 2. The power monitoring system of claim 1, further configured to execute a program that causes the one or more processors to:

7. the one or more processors: determining that a transient event is occurring because power in one or more phases has exceeded a tracking limit mask for that phase; subtracting the quiescent power of each power phase from the total event power; selecting said image of said transient event as one or more power images and displaying said power image of said transient event at the center of said display while displaying said transient event as a deviation from quiescent power; The power monitoring system of claim 1 , further configured to:

8. The vector database resides in a centralized location, and the one or more processors: monitoring the operation of the power grid; providing one or more artificial intelligence and machine learning services including at least one of predictive measures, predictive maintenance, load balancing, peak power balancing, and identifying abnormal trends; 2. The power monitoring system of claim 1, further configured to execute a program that causes the one or more processors to:

9. 1. A method for monitoring power in an electrical grid, comprising: receiving one or more power images and associated metadata relating to a transient event of at least one of the three phases of power from one or more power vector analyzers; converting the one or more power images and associated metadata from the one or more power vector analyzers into one or more transient event vectors; and storing the one or more transient event vectors in a vector database.

10. determining that a transient event is occurring because power in one or more phases has exceeded a tracking limit mask for that phase; subtracting the quiescent power of each power phase from the total event power; selecting said image of said transient event as one or more power images and displaying said power image of said transient event at the center of said display while displaying said transient event as a deviation from quiescent power; 10. The method of monitoring power in a power grid of claim 9, further comprising:

Images