Power grid system and method with zone autonomous control

Abstract

To provide a power grid system and method using zone autonomous control.SOLUTION: A power grid system including an advanced distribution management system (ADMS) and distribution zone measurement devices for measuring zone distribution operational parameters of a plurality of distribution zones, the distribution zones having associated distribution zone measurement devices and a distribution zone controller in communication with the distribution zone measurement devices and the ADMS. The power distribution zone controller receives power distribution zone operation data for the assigned power distribution zone from the power distribution zone measurement device, determines a power distribution zone orchestration index based on the power distribution zone operation data, communicates the power distribution zone orchestration index to the ADMS, and determines an adaptive control action for one or more power distribution controls within the assigned power distribution zone based on the power distribution zone orchestration index.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] These teachings relate generally to power grids, and more particularly to power grid operation and management. [Background technology]

[0002] In recent years, the complexity of the power grid has increased. The increase in variable energy sources and bulk power electronic controllers in the transmission system and the increase in controllable loads and variable energy sources in the distribution system contribute to the increased complexity of the power grid. These factors increase the number of controllable nodes and circuit configuration possibilities in the power grid. The increased complexity of the power grid can create challenges for centralized control. For example, the complexity of the power grid adds a large number of nodes to monitor, manage, and control.

[0003] Various needs are met, at least in part, by providing a power grid system with zone autonomous control as described in the following detailed description, particularly when considered in conjunction with the drawings. A full and enabling disclosure of aspects of the present specification, including the best mode thereof, directed to one of ordinary skill in the art, is set forth in this specification, which makes reference to the accompanying drawings. [Brief explanation of the drawings]

[0004] [Figure 1] FIG. 1 is a block diagram of a power grid system according to various embodiments of these teachings. [Figure 2] FIG. 1 is a block diagram of a transmission zone controller in accordance with various embodiments of these teachings. [Figure 3] 1 is a flow diagram of a method of operating a transmission zone controller to generate adaptive or predictive control actions for a transmission zone of a power grid in accordance with various embodiments of these teachings. [Figure 4] 1 is a schematic diagram of an example transmission zone in a power grid, in accordance with various embodiments of these teachings. [Figure 5]FIG. 1 includes a map of an exemplary transmission zone in a power grid, in accordance with various embodiments of these teachings. [Figure 6] FIG. 1 is a block diagram of a distribution zone controller in accordance with various embodiments of these teachings. [Figure 7] 1 is a flow diagram of a method of operating a distribution zone controller to generate adaptive or predictive control actions for a distribution zone in a power grid, in accordance with various embodiments of these teachings. [Figure 8] 1 is a flow diagram of a method of operating a distribution zone controller in accordance with various embodiments of these teachings. [Figure 9] 1 is a block diagram of a distribution zone in a power grid in accordance with various embodiments of these teachings. [Figure 10] 1 is a schematic diagram of a power distribution zone having subzones and clusters in accordance with various embodiments of these teachings. [Figure 11] 1 is a flow diagram of a method of operating a transmission zone controller in accordance with various embodiments of these teachings. [Figure 12] 1 is a flow diagram of a method of operating a transmission zone controller in accordance with various embodiments of these teachings. [Figure 13] 1 is a flow diagram of a method of operating a transmission zone controller in accordance with various embodiments of these teachings. [Figure 14] 1 is a flow diagram of a method of operating a transmission zone controller in accordance with various embodiments of these teachings. [Figure 15] 1 is a block diagram of a federated grid management system for a power grid in accordance with various embodiments of these teachings. [Figure 16] 1 is a flow diagram of a method for operating a federated grid management system in accordance with various embodiments of these teachings. [Figure 17A] 1 is a flow diagram of a method for operating a federated grid management system in accordance with various embodiments of these teachings. [Figure 17B]1 is a flow diagram of a method for operating a federated grid management system in accordance with various embodiments of these teachings. [Figure 17C] 1 is a flow diagram of a method for operating a federated grid management system in accordance with various embodiments of these teachings. [Figure 18] 1 is a flow diagram of a method for operating a power grid system having multiple zones in accordance with various embodiments of these teachings. [Figure 19] 1 is a flow diagram of a method for operating a power grid system having multiple zones in accordance with various embodiments of these teachings. [Figure 20] FIG. 1 is a diagram including an example computer system for a power grid system in accordance with various embodiments of these teachings. DETAILED DESCRIPTION OF THE INVENTION

[0005] Elements in the figures are illustrated for simplicity and clarity and are not necessarily drawn to scale. For example, the dimensions and / or relative placement of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of various embodiments of the present teachings. Also, common but well-understood elements that are useful or necessary in commercially feasible embodiments are often not depicted to facilitate a less obtrusive view of these various embodiments of the present teachings. While certain acts and / or steps may be described or depicted in a particular order of performance, those skilled in the art will understand that such specificity with respect to order is not actually required.

[0006] The power grid systems and methods described herein divide the power grid system into various zones, for example, within a distribution and / or transmission power grid. In some aspects, the systems and methods leverage zonal autonomous control to manage the power grid as a set of coordinated zones. The power grid systems and methods described herein can also use a federated grid model that provides a federated data fabric so that there is data fidelity and consistent modeling of the grid is common across the distribution and transmission systems. The federated grid model can provide overall grid orchestration and form zones of autonomous control based on centrally defined policies. The federated grid model can set policies and push policies to the zones for local execution. The zonal autonomous control can be executed by zone controllers with data organized, mapped, stored, and / or learned in a standardized manner to help achieve data fidelity. The federated grid model can receive data from various zone controllers.

[0007] Traditional approaches to power grid system control and management have been top-down approaches with central systems communicating with many, sometimes thousands of, points throughout the power grid. The approaches for power grid system control and management provided herein provide the ability to manage growing power grids of increasing complexity using decentralized control and automation solutions.

[0008] The techniques provided herein also provide an all-in-one solution for configuring and managing assets, including both primary and secondary assets, in a power grid system, whereas conventional techniques use separate management solutions for primary and secondary assets. Zones are formed, and for each zone, it is determined which assets are present (e.g., primary assets) and which intelligent electronic devices (IEDs) are connected to the assets (e.g., secondary assets). For each zone, data regarding the primary and secondary assets is collected, and various analytics are calculated based on the collected data. From the analytics, the primary and secondary assets can be ranked within the zone for asset evaluation and management.

[0009] Referring to Figure 1, there is shown a power grid system 100. In Figure 1, the power grid system 100 is in communication with a federated grid management system 134, an advanced distribution management system (ADMS) 144, and multiple databases.

[0010] The power grid system 100 may be divided into several zones. For example, the transmission power grid may be divided into transmission zones 102, and the distribution zone may be divided into distribution zones 104. In some aspects, the power grid system 100 includes multiple transmission zones 102 and multiple distribution zones 104.

[0011] The power grid system 100 can be divided into multiple transmission zones 102 based on, for example, the assets, boundaries, and operational area of ​​the zone. The operational area of ​​a zone can refer to the zone's primary function, e.g., power generation, transmission, or distribution. The operational area of ​​a zone can depend on which assets are present within the zone. As described, the operational area of ​​a zone can take into account the division of the power grid system 100 into multiple transmission zones. For example, if a portion of the power grid system 100 has an operational area for power generation, that portion of the power grid system 100 can be designated as a power generation zone 180B (see, e.g., FIG. 4). In another example, a microgrid within the power grid system 180 may be designated as its own zone, e.g., a microgrid / distributed energy resource (MG / DER) zone.

[0012] As used herein, a transmission zone may be a subportion of a transmission power grid network with a particular logical structure and boundaries. As shown in FIG. 1 , each transmission zone within multiple transmission zones 102 may have a transmission zone controller 112 dedicated to the assigned transmission zone. Each transmission zone also includes a transmission zone measurement device 108 and a transmission zone controller 110 that serve as measurement and control nodes or transmission zones. The transmission zone measurement device 108 and the transmission zone controller 110 may be used to identify and control operational and non-operational violations within the transmission zone. Additionally, the transmission zone controllers 112 may communicate or coordinate with each other to improve the reliability and resilience of the power grid system.

[0013] Transmission zone 102 may include primary substation equipment 106, one or more of transmission zone measurement devices 108, one or more of transmission zone controllers 110, and a transmission zone controller 112. Transmission zone measurement devices 108 and transmission zone controller 110 are operably coupled to primary substation equipment 106. Transmission zone measurement devices 108 and transmission zone controller 110 communicate with transmission zone controller 112.

[0014] Primary substation equipment 106 may include any primary equipment present in a substation, such as, for example, transformers, switchgear (e.g., circuit breakers), high voltage direct current (HVDC) controllers, flexible alternating current transmission system (FACTS) devices, or current and voltage transformers. Primary equipment may be any equipment through which power flows at a substation.

[0015] The transmission zone measurement devices 108 may include sensors, intelligent electronic devices (IEDs), smart meters, etc. in substations that provide monitoring functionality for the primary substation equipment 106. The transmission zone measurement devices 108 may be operable to measure, sense, or otherwise determine one or more transmission zone operating parameters. The transmission zone operating parameters may include, for example, voltage, frequency, inertia, congestion, reactive power load, or power factor.

[0016] The transmission zone controller 110 may include an intelligent electronic device (IED), a gateway, or any secondary equipment in the substation that provides control or maintenance functions for the primary substation equipment 106. In some examples, the transmission zone controller 110 may include a protective relay. The transmission zone controller 110 may be operable to adjust operational parameters of at least one of a main transformer, a switch, a current transformer, a voltage transformer, a circuit breaker, a voltage regulator, a Flexible Alternating Current Transmission System (FACTS) device, a power electronics controller, an HVDC link controller, a renewable generation source, or a grid-forming inverter of the substation.

[0017] Transmission zone controller 112 is operable to receive data from transmission zone measurement devices 108 and control transmission zone controller 110. For example, transmission zone controller 112 can communicate commands to transmission zone controller 110 to implement control actions. Transmission zone controller 112 can be in communication with federated grid management system 134. In some examples, at least one transmission zone 102 of the plurality of transmission zones includes a transmission zone controller 112. In other examples, each of the plurality of transmission zones includes a transmission zone controller 112. Transmission zone controller 112, according to some embodiments, is shown in further detail in FIG. 2.

[0018] Distribution zone 104 may include a primary facility 114, one or more of distribution zone measurement devices 116, one or more of distribution zone controllers 118, and a distribution zone controller 120. Distribution zone 104 may be a subportion of a distribution power grid network having a particular logical structure and boundaries. Distribution zone measurement devices 116 and distribution zone controller 118 are operably coupled to primary facility 114. Distribution zone measurement devices 116 and distribution zone controller 118 communicate with distribution zone controller 120. Distribution zone 104 may also include one or more interconnections with another distribution zone.

[0019] Primary equipment 114 may include any electrical distribution system asset, and may be any equipment through which power flows at a substation. Distribution assets may include, for example, substation equipment, distribution radial feeders, or transmission lines. Substation equipment may include, for example, transformers, switchgear, voltage regulators, capacitive banks, or power factor control devices.

[0020] The distribution zone measurement devices 116 may include sensors or intelligent electronic devices (IEDs) in substations that provide monitoring functionality for the primary equipment 114. The distribution zone measurement devices 116 may be operable to measure, sense, or otherwise determine one or more distribution zone operational parameters. The distribution zone operational parameters may include, for example, voltage, power factor, active / reactive power, load per node, battery-based energy storage system (BESS) capacity, distributed energy resource (DER) generation, renewable energy resource (REN) energy source generation, frequency, electric vehicle (EV) load, microgrid generation, microgrid load, feeder voltage, feeder current, feeder load imbalance, power quality data, etc.

[0021] The distribution zone controller 118 may include an intelligent electronic device (IED) or any secondary equipment in a substation that provides control or maintenance functions for the primary equipment 114 .

[0022] Distribution zone controller 120 is operable to receive data from distribution zone measurement devices 116 and control distribution zone controller 118. For example, distribution zone controller 120 can communicate commands to distribution zone controller 118 to implement control actions. In some examples, at least one distribution zone 104 of the plurality of distribution zones includes a distribution zone controller 120. In other examples, each of the plurality of distribution zones includes a distribution zone controller 120. Distribution zone controller 120, according to some embodiments, is shown in further detail in FIG. 6.

[0023] The power grid system 100 may be coupled to multiple local, remote, and / or cloud databases to retrieve data and / or store generated data for performing various functions described herein. In some embodiments, the data stored in the databases may include a training database 122, a zonal forecast / planning database 128, a zonal operations database 130, a zonal orchestration index database 132, a power restoreability index database 124, and a zonal policy database 125.

[0024] The training database 122 can store training data used to train any of the machine learning models described herein. The training database 122 can store historical data that can be used for training purposes to train the machine learning models described herein.

[0025] The zone forecast / planning database 128 may include forecast or planning data for one or more distribution zones and / or one or more transmission zones. The forecast data may include, for example, forecast load data, forecast weather data, or forecast distributed energy resource (DER) data. The planning data may include, for example, planned additions, repairs, upgrades, removals, contracts, etc. for the transmission or distribution power grid system 100.

[0026] Zone operations database 130 may store any operational data related to the operation of transmission zone 102 and / or distribution zone 104 of power grid system 100. Zone operations database 130 may be in communication with any component of power grid system 100, such as transmission zone controller 112, transmission zone measurement device 108, transmission zone controller 110, distribution zone controller 120, distribution zone measurement device 116, and / or distribution zone controller 118. Zone operations database 130 may also be in communication with federated grid management system 134 to communicate zone operational data to one or more components of federated grid management system 134. Zone operations database 130 may also be in communication with one or more of the machine learning models described herein so that operational data from zone operations database 130 can be utilized for training purposes.

[0027] Zone orchestration metrics database 132 may store zone orchestration metrics determined by one or more transmission zone controllers 112, which are described further below with reference to FIGURE 2. Zone orchestration metrics database 132 may communicate with one or more transmission zone controllers 112 or components thereof, and in some aspects communicates with federated grid management system 134.

[0028] Power restorability index database 124 may store power restorability indexes determined by one or more of distribution zone controllers 120, which will be further described with reference to FIG. 13. Zone orchestration index database 132 may communicate with one or more of distribution zone controllers 120 or components thereof, and in some aspects communicates with federated grid management system 134 and / or ADMS 144.

[0029] The zone policy database 125 can include at least one of a transmission zone policy for the transmission zone 102, a distribution zone policy for the distribution zone 104, or a zone predictive policy for the transmission zone 102, or a zone predictive policy for the distribution zone 104. The policy can include at least one of information regarding at least one of adaptive control sources, how to map adaptive control sources to violations, predictive control sources, how to map predictive control sources to violations, how to operate multiple distribution zones, how to form subzones or clusters based on the power grid topology, machine learning goals for the zones, calculating metrics related to the operation of the zones, or coordination between multiple zones.

[0030] ADMS 144 can communicate with one or more of distribution zone controllers 120. ADMS 144 can be configured to dynamically categorize the distribution power grid into multiple distribution zones. In some approaches, ADMS 144 can categorize or identify multiple distribution zones within the distribution power grid based on at least one of the topology of the distribution power grid or predetermined logic. ADMS 144 can be operable to receive power distribution operational data from distribution zone controllers 120. In some examples, ADMS 144 can also be configured to dynamically categorize a distribution zone 104 into multiple subzones 250 based on one or more subzoning rules. In yet other examples, ADMS 144 can also be configured to dynamically categorize subzones 250 into multiple clusters 258 based on one or more clustering rules or policies. The subzoning rules or policies and clustering rules or policies can be defined in ADMS 144 or zone policy database 125. Subzones and clusters are described in more detail with reference to FIGS. 9 and 10 .

[0031] In some embodiments, the power grid system 100, the federated grid management system 134, and the ADMS 144 may be a computer system, such as the computer system 510 shown in FIG.

[0032] 20, computer system 510 includes a processor 511, memory 512, an input / output (I / O) adapter 513, and a network adapter 514 communicating over a bus. In some embodiments, computer system 510 may include other common components of a processor-based device. Processor 511 is configured to execute computer-readable instructions stored in memory 512 to perform one or more functions described herein. Processor 511 is further configured to receive and / or transmit data via I / O adapter 513 and / or network adapter 514. In some embodiments, input device 515 and output device 516 may include user interface devices such as a display screen, touch screen, keyboard, microphone, speaker, camera, motion sensor, etc. In some embodiments, computer system 510 may communicate with one or more other devices or databases over a network 517 via network adapter 514. In some embodiments, network 517 may include a local or wide area network such as the Internet. Although computer system 510 is shown with a single processor 511 and memory 512, in some embodiments, computer system 510 may be implemented on a cloud-based computer having multiple distributed processors and memories.

[0033] Further details of functions that may be performed by the system of FIG. 1 according to some embodiments are described herein and further illustrated with reference to FIGS.

[0034] Transmission Operations, Management and Control In some embodiments, the systems and methods provided herein can be used to operate, manage, or control a transmission power grid. The increased number of controllable node points and circuit configuration possibilities in a transmission power grid can make centralized control of the transmission power grid difficult. However, the systems and methods described herein distribute control across multiple transmission zone controllers, such as transmission zone controller 112. For example, a transmission power grid can be divided into multiple transmission zones 102, and a transmission zone controller 112 associated with an assigned transmission zone of the multiple transmission zones 102 can be used to control and manage the assigned transmission zone. Such a configured transmission power grid control can result in lower latency, greater use of real-time edge information, improved modeling accuracy, and management, resulting in improved control. Additionally, in traditional transmission power grids, data from measurement devices such as IEDs may not be used effectively. For example, not all IED data may be used for higher-level grid decision-making. In contrast, systems and methods for transmission management and control leverage data from IEDs for specific transmission zones or for higher-level grid decision-making and control.

[0035] It is also contemplated that the systems and methods described herein for operating, managing, and controlling a transmission power grid can provide real-time control of zone assets, such as primary substation equipment. The methods and systems can receive feedback regarding zone operations to improve transmission zone modeling and predictive operation. Furthermore, by operating the transmission power grid as multiple transmission zones, the amount of data utilities need to process with associated communications can be reduced, and calculation zones can also be reduced. Furthermore, the systems and methods can proactively respond to the increasing integration of renewable energy networks (RENs) and distributed energy resources (DERs) into the transmission power grid and extreme weather events.

[0036] The systems and methods herein can facilitate visualization and management of the transmission power grid as a set of different zone types, which can be dynamically formed based on the power grid network topology. Multiple transmission zones 102 can be intelligently formed, with each zone having an associated programmable zone operation. The transmission zone controller 112 can operate the assigned transmission zones via adaptive control actions during normal operation modes. The federated grid management system 134 can also intervene in normal operation modes and issue intervention controls to the transmission zones 102, for example, during abnormal conditions. In some aspects, the transmission zone controller 112 can also operate the assigned transmission zones via predictive control actions, which can be control actions for future time intervals based on zone forecast data and machine learning.

[0037] 2 illustrates a transmission zone controller 112, according to some embodiments. The transmission zone controller 112 is associated with a transmission zone 102. In some aspects, the transmission zone controller 112 is associated with and configured to operate an assigned transmission zone of the plurality of transmission zones 102. Furthermore, in some aspects, each transmission zone within the plurality of transmission zones 102 can be assigned the same controller as the transmission zone controller 112.

[0038] Transmission zone controller 112 may include one or more of machine learning engine 150, zonal autonomous management agent 152, zonal adaptive control agent 154, and zonal predictive control agent 156. Machine learning engine 150, zonal autonomous management agent 152, zonal adaptive control agent 154, and zonal predictive control agent 156 may communicate with each other. It is also contemplated that the operations or functions described with reference to FIG. 2 may be performed by a single agent, engine, or module.

[0039] The machine learning engine 150 may include one or more machine learning models. The machine learning engine 150 may communicate with and receive training data from the training database 122.

[0040] In one example, the machine learning engine 150 can include an autonomous control machine learning model. The autonomous control machine learning model can receive as input, for example, transmission zone operational data from the transmission zone measurement devices 108 and zone policies. The autonomous control machine learning model can receive as input, for example, zone orchestration metrics from the zone orchestration metrics database 132 or the zone autonomous management agent for the transmission zone 102. The autonomous control machine learning model can determine or identify, as output, one or more adaptive control actions, for example, for the transmission zone controller 110. The autonomous control machine learning model can be trained on at least one of the zone operational parameter history, optimal control measure history, or zone adaptive policy history for the transmission zone 102. In some approaches, if the transmission zone is one of multiple transmission zones, the autonomous control machine learning model may also be trained on historical zone orchestration metrics and historical operational data from another zone of the multiple transmission zones, for example, a transmission zone of the same type as the transmission zone 102. In this manner, the autonomous control machine learning model can learn from the operation of similar types of zones.

[0041] In another example, machine learning engine 150 may include a predictive control machine learning model. The predictive control machine learning model may receive zone forecast and / or plan data as input, for example, from zone forecast / plan database 128. The predictive control machine learning model may also receive zone policies as input, for example, from zone policy database 125. The predictive control machine learning model may determine or identify one or more predictive control actions for transmission zone 102, for example, for transmission zone controller 110, as output.

[0042] The zone autonomy management agent 152 may be configured to determine a transmission zone orchestration metric for the transmission zone 102. The zone orchestration metric may be a measure of the performance of the transmission zone 102 relative to a baseline performance or reference metric. The zone autonomy management agent 152 may determine the zone orchestration metric based on at least one of zone operational data, zone policies, or zone forecast data from the transmission zone measurement devices 108, for example. The zone autonomy management agent 152 may also communicate with one or more databases, such as the zone policy database 125, the zone forecast / plan database, and the zone orchestration metric database 132. For example, the zone autonomy management agent 152 may receive data from the zone policy database 125 and the zone forecast / plan database. In some examples, the zone autonomy management agent 152 may send data to the zone orchestration metric database 132.

[0043] The zone adaptive control agent 154 can determine one or more adaptive control actions for the transmission zone 102 based on, for example, at least one of the transmission zone operational data or the zone policy. The zone policy can define operational parameters, rules, and / or constraints for the zone operation. The zone policy can also define rules for the partitioning or division of the transmission zones within the power grid. For example, the zone policy can define rules regarding how the transmission zone is formed and how the zone operational data is used and analyzed within the transmission zone. In another example, the zone policy can define how the zone controller should react during abnormal operation, such as when a problem or violation occurs within the zone. Additionally, the transmission zone controller 112 for a particular transmission zone can coordinate with other transmission zone controllers.

[0044] A zone policy may define how a transmission zone controller 112 performs operations, handles problems, or analyzes data for interaction with other transmission zone controllers. For example, if a particular transmission zone controller 112 is unable to handle a particular situation, another transmission zone controller within the power grid or federated grid management system may assume control to handle the situation defined in the zone policy. In another example, a zone policy may define a penalty for a transmission zone controller 112 if the transmission zone controller 112 violates an operational rule defined in the zone policy. In some implementations, the operational rule may relate to compensation. In one example, a transmission zone's operational rule may specify that if the voltage drops below a predetermined ratio for a particular situation, the penalty for violating the operational rule may be for the zone to pay some compensation to customers. In some implementations, a zone policy may specify operational rules related to generation, trading, and / or pricing associated with the zone. In one example, a zone policy may define a maximum and minimum price at which power should be purchased from a particular zone. In another example, the operating rules may specify that a zone should generate a predetermined power output (e.g., in MW), but if the zone does not generate the predetermined power output, the zone may have to pay for generating electricity that is not the predetermined amount defined in the operating rules.

[0045] In some aspects, one or more machine learning models of machine learning engine 150, such as autonomous control machine learning models, can be integrated as part of zone adaptive control agent 154. Zone adaptive control agent 154 can communicate with zone policy database 125 and receive data, such as policies, therefrom. Zone adaptive control agent 154 can communicate with one or more of transmission zone controllers 110. In this manner, zone adaptive control agent 154 can be configured to communicate or send commands to one or more of transmission zone controllers 110.

[0046] Zonal predictive control agent 156 can determine predictive control actions for transmission zone 102 based on, for example, at least one of zone policies and zone forecast data. Using zonal predictive control agent 156, transmission zone controller 112 can predict future behavior of the transmission power grid to determine predictive control actions to achieve objectives or target performance of the transmission power grid. For example, the predictive control actions can include any control actions for transmission zone controller 110 for future time periods. In some aspects, one or more machine learning models of machine learning engine 150, such as predictive control machine learning models, can be integrated with or part of zonal predictive control agent 156. Zonal predictive control agent 156 can communicate with zone policy database 125 to receive data, such as policies. Additionally, zonal predictive control agent 156 can communicate with zone forecast / plan database 128 to receive data, such as forecast data.

[0047] 3 illustrates a method of operating a transmission zone controller to generate adaptive or predictive control actions for a transmission zone of a power grid, according to some embodiments. In some examples, the transmission zone controller is transmission zone controller 112 described with reference to FIGS. 1 and 6, and the transmission zone is transmission zone 102 described with reference to FIG. 1.

[0048] In step 160, the transmission zone controller receives the transmission zone operational data from the assigned transmission zone. For example, the transmission zone controller 112 may receive the transmission zone operational data from one or more of the transmission zone measurement devices 108 in the transmission zone 102.

[0049] In some approaches, the transmission zone controller may also receive a zone adaptation policy for the transmission zone 102. The zone adaptation policy may include or define standard rules for using zone control resources to mitigate operational or non-operational violations in the transmission zone 102. The transmission zone controller may receive the zone adaptation policy from, for example, zone policy database 125 or from federated grid management system 134.

[0050] In step 162, the transmission zone controller determines a transmission zone orchestration index for the assigned transmission zone based on the transmission zone operational data. For example, the transmission zone controller 112 may determine the transmission zone orchestration index.

[0051] As discussed above, a transmission zone orchestration metric may be a measure of the performance of an assigned transmission zone relative to a baseline performance or reference metric.

[0052] In some examples, the zone orchestration indicator indicates at least one of an operational violation or a non-operational violation within the assigned zone. For example, the transmission zone controller can identify operational or non-operational violations by comparing the transmission zone operational data to thresholds or reference data defined in the zone adaptation policy. The operational violations can indicate whether one or more of voltage, power, load, reactive power, power factor, congestion stability, frequency, inertia, or grid strength are within respective threshold limits or reference ranges. For example, the operational violations can include one or more of voltage and / or frequency values ​​outside threshold limits, active / reactive power outside threshold limits, transmission line limits exceeding dynamic ratings, generator overload, transformer overload, or low power factor. The non-operational violations can be related to at least one of power grid maintenance, hardware, software, or communication, operator, or cybersecurity-related issues. The transmission zone controller can be further configured to isolate nodes or devices in the assigned transmission zone when a non-operational violation is identified.

[0053] In some examples, the zone orchestration indicator may be a numeric value representing a bitstream encoding operational or non-operational violations, with the bits in the bitstream ordered with serious violations located on the left side of the bitstream and less serious violations located on the right side of the bitstream based on severity.

[0054] In some approaches, the transmission zone controller can communicate the transmission zone orchestration indicator to another transmission zone in step 164. For example, the transmission zone controller 112 can communicate the transmission zone orchestration indicator to a transmission zone controller associated with another transmission zone.

[0055] In some approaches, the transmission zone controller may communicate the transmission zone orchestration indicator to the federated grid management system in step 166. For example, the transmission zone controller 112 may communicate the transmission zone orchestration indicator to the federated grid management system 134.

[0056] In step 168, the transmission zone controller determines an adaptive control action for the controllers in the assigned zone based on the transmission zone orchestration metrics. For example, transmission zone controller 112 may determine an adaptive control action for one or more of transmission zone controllers 110 in transmission zone 102. In some examples, the transmission zone controller may also determine an adaptive control action for a controller of another one of the multiple transmission zones, e.g., to compromise or compete with other transmission zones.

[0057] In some approaches, the adaptive control operations may control at least one of a voltage, a power factor, a load, and a frequency of assets, such as primary substation equipment in an assigned transmission zone or another one of the multiple transmission zones. Additionally, the adaptive control operations may control at least one of a battery-based energy storage system (BESS), a distributed energy resource (DER), or a renewable energy network (REN) in the assigned zone or another one of the multiple transmission zones.

[0058] In some approaches, the adaptive control action may affect a conflict or compromise between the assigned transmission zone and another one of the multiple transmission zones.

[0059] In some approaches, the transmission zone controller may also receive transmission zone operational data or transmission zone orchestration indicators from another one of the multiple transmission zones. The transmission zone controller can then determine adaptive control actions based at least in part on the zone operational data or zone orchestration indicators from another one of the multiple transmission zones. For example, the transmission zone controller can control conflicts and / or compromises between the multiple transmission zones.

[0060] In step 170, the transmission zone controller communicates a command to a control device based on the adaptive control action. For example, the transmission zone controller 112 can communicate the command to one or more of the transmission zone control devices 110 in the transmission zone 102. In some examples, the transmission zone controller can also communicate the command to a control device of another one of the multiple transmission zones. The command can be configured to cause the control device to perform an adaptive control action in real time. In some examples, the command is configured to perform a pre-scheduled control based on the transmission zone orchestration metrics. The pre-scheduled control may be defined, for example, in a zone adaptation policy.

[0061] In some approaches, the transmission zone controller can communicate commands to the control devices upon identifying an operational violation. As described above, the transmission zone orchestration indicators can indicate operational violations in assigned zones. Accordingly, the transmission zone controller can implement control actions to address the operational violations.

[0062] In some approaches, the transmission zone controller may also communicate an alarm or electronic message to a user interface associated with the assigned zone. For example, upon identifying a non-operational violation within an assigned zone, instead of or in addition to communicating a command to a control device, the transmission zone controller may send an alarm or electronic message to notify a user of the non-operational violation.

[0063] In step 172, the transmission zone controller may receive the zone policy. For example, the transmission zone controller 112 may receive the zone policy from the federated grid management system 134 or from the zone policy database 125.

[0064] In step 174, the transmission zone controller may determine a predictive control action for the control devices in the assigned zone based on the zone policy and the transmission zone operational data. For example, transmission zone controller 112 may determine a predictive control action for one or more of transmission zone control devices 110 in transmission zone 102.

[0065] In some approaches, the transmission zone controller may determine predictive control actions using a predictive control machine learning model trained on at least one of zonal operating parameter history, optimal control measure history, or zonal predictive policy history and zonal operating forecast data.

[0066] In step 176, the transmission zone controller may communicate a command to a controller based on the predicted control action. For example, transmission zone controller 112 may communicate a command to one or more transmission zone controllers 110.

[0067] 4 and 5, examples of different types of transmission zones are shown that may be within a power grid system, such as power grid system 100. The different types of transmission zones may include at least one of a renewable energy network (REN) zone 180A, a generation (GEN) zone 180B, a transfer zone 180C, a flexibility zone 180D, a microgrid (MG) or distributed energy resource (DER) zone 180E, or an industrial zone 180F.

[0068] REN zone 180A can include one or more substations with incoming and / or outgoing lines integrated into the REN. In REN zone 180A, the transmission zone controller can provide one or more of inertia, fast frequency response (FFR), auxiliary services (AS), voltage ride-through (VRT), or frequency ride-through (FRT) support.

[0069] GEN zone 180B can include one or more substations with incoming generation (GEN) and one or more outgoing lines. In GEN zone 180B, a transmission zone controller can provide one or more of inertia, FFR, stability, or black start support. In one example, the transmission zone controller can provide black start support by controlling the restart of equipment in GEN zone 180B when there is a complete or partial outage of the power supply in GEN zone 180B due to an extreme problem, such as a cyber event. Part of such black start operations performed by the transmission zone controller can be restarting GEN zone 180B in the pocket to return the zone to normal operation.

[0070] Transfer zone 180C may include one or more substations with one or more incoming lines and one or more outgoing lines.

[0071] A flexibility zone 180D can include one or more substations with incoming generation (GEN) and outgoing lines to one or more distribution systems and / or one or more loads. In a flexibility zone 180D, a transmission zone controller can provide AS support along with penalty tracking.

[0072] The MG / DER zone 180E can include one or more substations with one or more input lines and one or more output lines to a microgrid (MG) or distributed energy resources (DER). A microgrid has its own power generation and distribution and can be coupled to the main power grid, but can also function as a separate mini-grid that can operate on its own. Distributed energy resources may be part of the microgrid and may include diesel stations, solar power, and wind power. In the MG / DER zone 180E, if there is a problem with the main grid, a transmission zone controller can isolate the zone and allow the zone to operate as an independent grid. The transmission zone controller can also support another transmission zone in the power grid that is experiencing problems. For example, the transmission zone controller assigned to the MG / DER zone 180E can manage when the microgrid starts up to support nearby zones.

[0073] The industrial zone 180F may include one or more substations with one or more incoming lines from a power generation (GEN) and one or more outgoing lines to industrial loads. In the industrial zone 180F, a transmission zone controller may provide one or more of ancillary services (AS), demand response (DR), and load management control (LMC) support. The industrial zone 180F may supply power to the primary grid and may be a large load on the primary grid. Depending on the scenario, the industrial zone 180F may need to limit its load or supply excess power to the primary grid. Thus, the transmission zone controller assigned to the industrial zone 180F may direct when to limit power within the industrial zone 180F or when to supply excess power to nearby zones.

[0074] In each type of zone, a transmission zone controller, such as transmission zone controller 112, can monitor, manage, and / or control one or more of voltage, frequency, inertia, congestion, reactive power load, and power factor. A transmission zone controller, such as transmission zone controller 112, can also manage, monitor, and provide secondary control of one or more of voltage, frequency, inertia, congestion, reactive power load, and power factor of downstream zones. Additionally, a transmission zone controller can control coordination with multiple upstream zones, downstream zones, and remote zones within the transmission power grid system.

[0075] In some approaches, the federated grid management system 134 can, for example, partition or form multiple transmission zones within the transmission power grid. For example, the federated grid management system 134 can partition the multiple transmission zones based on a power grid architecture, which can be determined based on a single line diagram (SLD) / nanowatt (NW) model of the transmission power grid.

[0076] Power Distribution Operations, Management, and Control In some embodiments, the systems and methods provided herein can be used to operate, manage, or control a distribution power grid. The increasing number of controllable assets and circuit configuration possibilities in a distribution power grid can make centralized control of the distribution power grid challenging. The approaches described herein divide the distribution power grid into multiple distribution zones with a zone-based network of distribution zone controllers. Furthermore, the approaches described herein enable intelligent advanced distribution management system (ADMS) solutions using distributed intelligence for zone automation and control. The combination of ADMS operations with a zone-based network of distribution zone controllers can help improve or optimize distribution power grid operations and reduce unpredictability. Furthermore, the use of a zone-based network of distribution zone controllers can reduce latency, increase the use of real-time information, improve modeling accuracy, and provide improved distribution power grid control.

[0077] The systems and methods for operating, managing, and controlling a distribution power grid described herein can be used to provide real-time control of zone assets. Feedback from the distribution zone controllers can also improve distribution zone modeling and predictive operation. The use of a zone-based network of distribution zone controllers can also reduce zone interruptions and interruptions of individual circuits within a zone. Furthermore, operating a distribution power grid as multiple distribution zones can reduce the amount of data utilities need to process with associated communications and can also reduce computational bandwidth. Furthermore, the systems and methods can effectively manage the increasing integration of renewable energy networks (RENs) and distributed energy resources (DERs) into the distribution grid and extreme weather events.

[0078] Within a distribution zone, a distribution zone controller can perform voltage / volt-ampere reaction (VAR) optimization (VVO), conservation voltage reduction (CVR), fault location, isolation, and service restoration (FLISR), switching, ramping, power control, power quality control, voltage control, and power factor control to reduce or minimize supply interruptions. Distribution zone controllers can also have machine learning capabilities to learn about zone operations and control behaviors. Distribution zone controllers can further integrate control of electronic vehicles (EVs), passive loads, distributed energy resources (DERs), microgrids, battery energy storage systems (BESSs), and load shedding with traditional asset control. Furthermore, a zone-based network of distribution zone controllers can coordinate responses between zones to manage zone restoration and distribution power grid needs. Furthermore, a zone-based network of distribution zone controllers can provide the ability to isolate one or more distribution zones for resiliency and provide resiliency for adjacent zones.

[0079] 6 illustrates a distribution zone controller 120, according to some embodiments. The distribution zone controller 120 is associated with or assigned to a distribution zone 104. In some aspects, the distribution zone controller 120 is associated with and configured to operate an assigned distribution zone of the plurality of distribution zones 104. Furthermore, in some aspects, each distribution zone within the plurality of distribution zones 104 can be assigned the same controller as the distribution zone controller 120.

[0080] Distribution zone controller 120 may include one or more of machine learning engine 186, zone monitoring agent 182, zone adaptive control agent 184, and zone predictive control agent 188. Machine learning engine 186, zone monitoring agent 182, zone adaptive control agent 184, and zone predictive control agent 188 may communicate with each other. It is also contemplated that the operations or functions described with reference to FIG. 3 may be performed by a single agent, engine, or module.

[0081] The machine learning engine 186 can include one or more machine learning models. The machine learning engine 186 can communicate with and receive training data from the training database 122.

[0082] In one example, the machine learning engine 186 can include a baseline machine learning model. The baseline machine learning model can receive at least one of load data, controller settings, distributed energy resource (DER) generation profile data, or intermittency profile data for the distribution zone as input. The baseline machine learning model can then determine or identify one or more baseline operational parameters or controller settings for the distribution zone as output. The baseline machine learning model can be trained with at least one of historical load data for the distribution zone, simulated load data for the distribution zone, historical settings of one or more distribution zone controllers, historical distributed energy resource (DER) generation profile data for the distribution zone, simulated distributed energy resource (DER) generation profile data for the distribution zone, simulated intermittency profile data for the distribution zone, or historical intermittency profile data for the distribution zone.

[0083] In another example, the machine learning engine 186 can include an adaptive control machine learning model. The adaptive control machine learning model can receive, as input, distribution zone operational data from, for example, the distribution zone measurement devices 116 and zone policies. The adaptive control machine learning model can also receive, as input, zone orchestration metrics for the distribution zone 104, for example, from the zone orchestration metrics database 132 or from a zone monitoring agent. The adaptive control machine learning model can determine or identify, as output, one or more adaptive control actions for, for example, the distribution zone controller 118. The adaptive control machine learning model can be trained using at least one of zone orchestration metrics history, distribution zone operational parameter history, simulated distribution zone operational parameters, distribution control measure history, simulated distribution control measure, simulated distribution zone adaptive policy, or distribution zone adaptive policy history for the distribution zone 104. The adaptive control machine learning model may also be trained using at least one of distribution zone operational parameter history, simulated distribution zone operational parameters, simulated distribution adaptive control measure, or distribution adaptive control measure history. In some approaches, if the distribution zone is one of multiple distribution zones, the adaptive control machine learning model may also be trained on historical zone orchestration metrics and historical operational data from another of the multiple distribution zones, for example, a distribution zone of the same type as distribution zone 104. In this way, the adaptive control machine learning model can learn from the operation of similar types of zones.

[0084] In another example, the machine learning engine 186 may include a predictive control machine learning model. The predictive control machine learning model may receive as input zone forecast and / or plan data, for example, from the zone forecast / plan database 128. The predictive control machine learning model may also receive as input zone policies, for example, from the zone policy database 125. The predictive control machine learning model may, as output, determine or identify one or more predictive control actions for the distribution zone 104, for example, the distribution zone controller 118. The predictive control machine learning model may be trained using at least one of historical distribution zone operating parameters, simulated distribution zone operating parameters, historical distribution control measurements, simulated distribution control measurements, simulated distribution forecast data, or historical distribution forecast data for the distribution zone 104.

[0085] The zone monitoring agent 182 may be configured to determine a distribution zone orchestration metric for the distribution zone 104. The zone orchestration metric may be a measure of the performance of the transmission zone 102 relative to a baseline performance or reference metric. The zone monitoring agent 182 may determine the zone orchestration metric based on at least one of distribution zone operational data from the distribution zone measurement devices 116, a zone policy, or zone forecast data, for example. The zone monitoring agent 182 may also communicate with one or more databases, such as the zone policy database 125, the zone forecast / plan database, and the zone orchestration metric database 132. For example, the zone monitoring agent 182 may receive data from the zone policy database 125 and the zone forecast / plan database. In some examples, the zone monitoring agent 182 may transmit data to the zone orchestration metric database 132 or another distribution zone controller.

[0086] In some examples, if the power distribution zone 104 includes subzones 250 and clusters 258 , the zone monitor agent 182 may also communicate with and receive data from the subzone measurement devices 254 and cluster controllers 264 .

[0087] In some examples, zone monitoring agent 182 may also include a low voltage (LV) module configured to receive operational data from low voltage circuits within distribution zone 104. The LV module may receive the distribution zone operational data from distribution zone measurement devices 116, which may include, for example, an advanced metering infrastructure (AMI) or a meter data management system. The distribution zone operational data received or monitored by the LV module may include at least one of electric vehicle (EV) load, rooftop solar (PV) generation, power quality, total load, critical load, or load imbalance.

[0088] The zone adaptive control agent 184 can determine one or more adaptive control actions for the distribution zone 104 based on, for example, at least one of the distribution zone operational data or the zone policy. The zone policy can define operational parameters, rules, and / or constraints for the zone operation. In some aspects, one or more machine learning models of the machine learning engine 186, such as an adaptive control machine learning model, can be integrated as part of the zone adaptive control agent 184. The zone adaptive control agent 184 can communicate with the zone policy database 125 and receive data, such as policies, therefrom. The zone adaptive control agent 154 can communicate with one or more of the distribution zone controllers 118. In this manner, the zone adaptive control agent 184 can be configured to communicate or send commands to one or more of the distribution zone controllers 118.

[0089] Zonal predictive control agent 188 can determine predictive control actions for distribution zone 104 based on, for example, at least one of the zone's policies and zonal forecast data. Using zonal predictive control agent 188, distribution zone controller 120 can predict future behavior of the distribution power grid to determine predictive control actions to achieve objectives or target performance of the transmission power grid. For example, the predictive control actions can include any control actions for distribution zone controller 118 for future time periods. In some aspects, one or more machine learning models of machine learning engine 186, such as predictive control machine learning models, can be integrated with or part of zonal predictive control agent 188. Zonal predictive control agent 188 can communicate with zone policy database 125 to receive data, such as policies. Additionally, zonal predictive control agent 188 can communicate with zonal forecast / plan database 128 to receive data, such as forecast data.

[0090] In some examples, the distribution zone controller 120 may also include a zone configuration module configured to adjust one or more thresholds, limits, or set points for feeders, assets, and / or devices within the distribution zone 104. The zone configuration module may adjust the one or more thresholds, limits, or set points based on the distribution zone operational data. For example, the zone configuration module may adjust thresholds, operating limits, or set points for one or more of the primary equipment 114, the distribution zone controller 118, or the distribution zone measurement device 116. In some examples, the zone configuration module may adjust one or more of the distribution energy resource, the battery energy storage system, or the volt / VAR optimization parameters.

[0091] In some examples, the distribution zone controller 120 may also include a zone feedback module configured to receive distribution zone operational data after implementation of one or more control actions in the distribution zone 104 .

[0092] 7 illustrates a method for operating a distribution zone controller to generate adaptive or predictive control actions for a distribution zone in a power grid, according to some embodiments. In some examples, the distribution zone controller is distribution zone controller 120 described with reference to FIGS. 1 and 6, and the distribution zone is distribution zone 104 described with reference to FIG.

[0093] In step 190, the distribution zone controller receives the distribution zone operational data from the assigned distribution zone. For example, the distribution zone controller 120 may receive the distribution zone operational data from one or more of the distribution zone measurement devices 116 in the distribution zone 104.

[0094] In step 192, the distribution zone controller determines a distribution zone orchestration metric for the assigned distribution zone based on the distribution zone operational data. For example, distribution zone controller 120 may determine a distribution zone orchestration metric for distribution zone 104 based on the distribution zone operational data.

[0095] In some examples, the distribution zone orchestration metric may be a measure of the operation of an assigned distribution zone with reference to baseline operational data for the assigned distribution zone, which may include, for example, at least one of a baseline load for the assigned distribution zone, one or more baseline settings of a distribution zone controller, a baseline distributed energy resource (DER) generation profile for the assigned distribution zone, or a baseline intermittency profile for the assigned distribution zone.

[0096] In some examples, the distribution zone orchestration indicators may indicate at least one of an operational violation or a non-operational violation in the assigned distribution zone. The distribution zone controller 120 may be configured to identify the operational violation based on the distribution zone operational data and the distribution zone policies.

[0097] In some examples, the distribution zone controller can be further configured to determine at least one of a load / generation increase index or a distributed energy resource (DER) intermittency level for the assigned distribution zone. The load / generation increase index can indicate the degree to which load / generation has increased in the assigned distribution zone. The DER intermittency level can indicate the difference between actual DER generation and predicted DER generation for a particular time interval within the assigned distribution zone. The distribution zone controller can then determine settings for one or more distribution zone controllers within the assigned distribution zone based on at least one of the load / generation increase index or the distributed energy resource (DER) intermittency level. Furthermore, the distribution zone controller can determine a distribution zone orchestration index based on at least one of the load / generation increase and the DER intermittency level.

[0098] In step 194, the distribution zone controller communicates the distribution zone orchestration indicator to another distribution zone. For example, the distribution zone controller 120 can communicate the distribution zone orchestration indicator to another distribution zone, such as to a distribution zone controller 120 assigned to the other distribution zone.

[0099] The distribution zone controller communicates the distribution zone orchestration indicators to an advanced distribution management system (ADMS) in step 196. For example, the distribution zone controller 120 can communicate the distribution zone orchestration indicators to the ADMS 144.

[0100] In some approaches, the distribution zone controller may be configured to communicate an intervention control command to the distribution zone controller: a distribution zone orchestration indicator for an assigned zone and a zone orchestration indicator for another zone of the plurality of zones. In some examples, the intervention control command can be configured to address at least one of an operational violation or a non-operational violation in the plurality of distribution zones. The intervention control command can be a compromise between the distribution zones to address the violation within the distribution power grid.

[0101] In step 198, the distribution zone controller determines adaptive control actions for the controllers in the assigned distribution zone based on the distribution zone orchestration metrics. For example, distribution zone controller 120 may determine adaptive control actions for the controllers in distribution zone 104.

[0102] In step 200, the distribution zone controller communicates a command to a controller based on the adaptive control action. For example, the distribution zone controller 120 can communicate the command to one or more of the distribution zone controllers 118. The command can be configured to cause one or more of the distribution zone controllers 118 to perform the adaptive control action. In some examples, the command may be configured to control at least one of an electric vehicle load, or a passive load, or an active load, where a passive load is an industrial, commercial, or residential load that can be switched on or off and cannot be controlled due to partial use.

[0103] In step 202, the distribution zone controller receives forecast data for the assigned distribution zone. For example, the distribution zone controller 120 may receive forecast data for the distribution zone 104 from the zone forecast / planning database 128.

[0104] In some approaches, the distribution zone controllers may also receive the predictive policies. The distribution zone controllers may receive the predictive policies from, for example, ADMS 144 or zone policy database 125.

[0105] In step 204, the distribution zone controller determines predictive control actions for the controllers in the assigned distribution zone based on the zone policies, the forecast data, and the distribution zone operational data. For example, the distribution zone controller 120 may determine predictive control actions for one or more of the distribution zone controllers 118 in the assigned distribution zone.

[0106] In some approaches, the distribution zone controllers may also determine predictive control actions based on zone predictive policies.

[0107] In step 206, the distribution zone controller communicates commands to the controllers based on the predicted control actions. For example, the distribution zone controller 120 can communicate commands to one or more of the distribution zone controllers 118.

[0108] 8 illustrates various methods for determining settings for distribution zone controllers 118 within a distribution zone 104. In some approaches, a distribution zone controller may be configured to evaluate a plan for an assigned distribution zone and determine corresponding controller settings to implement such plan. A distribution zone controller 120 may be configured to perform one or more of the steps detailed in FIG. 8.

[0109] In step 210, the distribution zone controllers may identify and configure distribution zones based on predetermined rules, which may be transmitted to the distribution zone controllers from, for example, an Advanced Distribution Management System (ADMS).

[0110] In step 212, the distribution zone controller may determine a baseline load for the distribution zone based on historical operational data for the distribution zone and a baseline distributed energy resource (DER) generation / intermittency profile. The baseline DER generation / intermittency profile may define the expected generation of one or more energy resources, such as solar or wind resources. The solar or wind resources may be considered to operate intermittently. The baseline DER generation / intermittency profile may define how such resources are expected to perform over a period of time.

[0111] In step 214, the distribution zone controller may determine at least one of the real-time aggregate load or aggregate growth for the distribution zone.

[0112] In step 216, the distribution zone controller may determine at least one of a load increase index or a generation increase index for the distribution zone. The load increase index may be a number that reflects the real-time aggregate load in the distribution zone relative to a baseline load. The generation increase index may be a number that measures the amount of demand relative to the amount of expected generation.

[0113] In step 218, the distribution zone controller may adjust settings of one or more of the distribution zone control devices within the distribution zone based on the load increase indicator and / or the generation increase indicator.

[0114] In another example, a distribution zone controller is configured to receive a disaster recovery plan for an assigned distribution zone, and the distribution zone controller can determine the configuration of one or more distribution zone control devices based on the disaster recovery plan.

[0115] In step 220, the distribution zone controller receives a fault recovery plan for a potential fault within the distribution zone. A fault recovery plan may be any predefined procedure or means for responding after a fault, intended to detect, locate, isolate, and / or recover from a fault in the power grid. A fault may be any condition that prevents a circuit element from functioning in a required manner. Examples of faults may include a short circuit, an open circuit, a failed device, or an overload.

[0116] In step 222, the distribution zone controller determines a fault configuration for the potential fault. The fault configuration may include one or more settings of the distribution zone controller that can implement a fault recovery plan or restore operation of the power grid.

[0117] In step 224, the distribution zone controller adjusts the controllers in the distribution zone according to the fault settings upon the occurrence of a real or actual fault. For example, the distribution zone controller can communicate commands to one or more distribution zone controllers to implement the fault settings.

[0118] In another example, a distribution zone controller may be configured to receive an outage restoration plan for an assigned distribution zone. The distribution zone controller may then determine settings for one or more distribution zone control devices based on the outage restoration plan.

[0119] In step 226, the distribution zone controller receives an outage restoration plan for the distribution zone. The outage restoration plan may be any predefined procedure or means for detecting an outage and / or responding to an outage for the purpose of restoring power on the power grid.

[0120] In step 228, the distribution zone controller determines the outage settings of the outage restoration plan. The outage settings may include settings for one or more distribution zone controllers that can implement the outage restoration plan or restore power on the power grid.

[0121] In step 230, the distribution zone controller adjusts the controllers in the distribution zone according to the outage settings when an actual outage occurs. For example, the distribution zone controller may communicate commands to one or more of the distribution zone controllers to implement the outage settings.

[0122] In another example, a distribution zone controller is configured to receive a load management plan for an assigned distribution zone. The distribution zone controller can then determine settings for one or more distribution zone control devices based on the load management plan.

[0123] In step 232, the distribution zone controller receives a load management plan for the distribution zone. The load management plan may be any predefined procedure or action for load changes in the power grid, intended to detect the load changes and / or operate power grid equipment in response to the load changes.

[0124] In step 234, the distribution zone controller determines load management settings for the load management plan. The load management device settings can include settings for one or more of the distribution zone controllers that can implement the outage restoration plan or restore power in the power grid.

[0125] In step 236, the distribution zone controller adjusts the controllers in the distribution zone according to the load management settings when a load change occurs. For example, the distribution zone controller may communicate commands to one or more distribution zone controllers to implement the load management settings.

[0126] In another example, a distribution zone controller is configured to receive a commitment of a new distributed energy resource (DER) or a registration of an assigned distribution zone. The distribution zone controller can then determine the configuration of one or more distribution zone controllers based on the commitment or registration of the new distributed energy resource (DER).

[0127] In step 238, the distribution zone controller receives a distributed energy resource (DER) commitment or registration for the distribution zone. The distributed energy resource (DER) commitment may include power generation and storage devices that are connected or will be connected to the power grid. The DER commitment or registration may include various energy types, such as solar, wind, and battery storage.

[0128] In step 240, the distribution zone controller determines updated configurations for processing the commitment or enrollment of distributed energy resources (DERs). The updated configurations may include settings for one or more distribution zone controllers designed to manage or operate the power grid in response to the commitment or enrollment of distributed energy resources (DERs).

[0129] In step 242, the distribution zone controller adjusts the controllers in the distribution zone according to the updated settings when a new commitment or registration occurs. For example, the distribution zone controller may communicate commands to one or more distribution zone controllers to implement the updated settings.

[0130] In yet another example, a distribution zone controller is configured to receive voltage / VAR flows on the feeders and buses under steady-state operation. The distribution zone controller can then determine voltage / VAR flows on the feeders and buses after a planned reconfiguration and determine a target voltage / VAR profile based on the voltage / VAR flows on the feeders and buses after the planned reconfiguration.

[0131] In step 244, the distribution zone controller receives the voltage / VAR flows on the feeders or buses in the distribution zone under steady state conditions and after a reconfiguration or Fault Location, Isolation, and Service Restoration (FLISR).

[0132] In step 246, the distribution zone controller adjusts the voltage / VAR flow based on changes in the load taps, renewable energy generation sources, capacitor banks, and distributed energy resources (DERs) within the distribution zone. Changes in the load taps, renewable energy generation sources, capacitor banks, and distributed energy resources (DERs) may occur due to a distribution zone reconfiguration or due to a fault location, isolation, and service restoration (FLISR).

[0133] Distribution Subzone Calculation In some embodiments, the systems and methods provided herein can divide a distribution zone into subzones to operate, manage, or control the subzones. A distribution zone within a distribution power grid can be divided or categorized into subzones. For example, a subzone can represent a radial feeder within the distribution power grid. The subzones may be further divided or categorized into clusters. In one example, a cluster can represent a low-voltage (LV) network within the distribution power grid. A distribution zone controller assigned to the distribution zone can then determine various situational awareness parameters of the distribution zone for each subzone or cluster. The situational awareness parameters can indicate a level of load flexibility, generation flexibility, or power quality flexibility within the subzone or cluster. The situational awareness parameters can then be used to determine an orchestration metric for each subzone or cluster so that the subzones or clusters can be ranked. The ranking can indicate a level of priority for at least one of adaptive control action, emergency situations, or planning for future time intervals, for example.

[0134] 9 illustrates a power distribution zone 104, according to some embodiments. In FIG. 9, the power distribution zone 104 is divided into a plurality of subzones 250. At least one of the plurality of subzones 250 may be further divided into a plurality of clusters 258.

[0135] Distribution zone 104 may include a primary facility 114, one or more of distribution zone measurement devices 116, one or more of distribution zone control devices 118, and a distribution zone controller 120. The components of distribution zone 104 are described in detail with reference to FIG.

[0136] One or more of the multiple subzones 250 may include one or more assets 252, one or more subzone measurement devices 254, and one or more subzone control devices 256. A subzone 250 may be a feeder within the power distribution zone 104. For example, if a power distribution system has four feeders, each feeder may be considered a subzone. All devices or assets 252 connected to a feeder may be part of a subzone. Dividing a power distribution zone into subzones may streamline management of data for the power distribution zone.

[0137] The one or more assets 252 may include one or more portions of the primary equipment 114 of the distribution zone 104. That is, the primary equipment 114 may be divided or allocated to the subzones 250 based on the division of the subzones 250 within the distribution zone 104.

[0138] The subzone measurement devices 254 can be configured to measure at least one subzone operational parameter of the subzone 250. The subzone operational parameters can include, for example, voltage, power factor, active / reactive power, load per node, battery-based energy storage system (BESS) capacity, distributed energy resource (DER) generation, renewable energy resource (REN) energy source generation, frequency, electric vehicle (EV) load, microgrid generation, microgrid load, feeder voltage, feeder current, feeder load imbalance, power quality data, etc. The subzone measurement devices 254 can include one or more of the distribution zone measurement devices 116 in the distribution zone 104. That is, the distribution zone measurement devices 116 can be divided or assigned to the subzones 250 based on the division of the subzones 250 within the distribution zone 104.

[0139] Subzone controller 256 may be configured to adjust at least one subzone operational parameter for subzone 250. Subzone controller 256 may include one or more of distribution zone controllers 118 in distribution zone 104. That is, distribution zone controllers 118 may be divided or assigned to subzones 250 based on the division of subzones 250 within distribution zone 104.

[0140] One or more of the plurality of clusters 258 may include one or more assets 260, one or more cluster measurement devices 262, and one or more cluster controllers 264. A cluster 258 may be one or more load points connected to an electrical feeder in a subzone 250. For example, an electrical feeder may have multiple load points that draw power from the feeder. One or more load points may be considered a cluster 258, and each load point may have a device that provides electrical data related to the cluster 258. Such a device may be a cluster measurement device 262, described further below. In some aspects, each of the plurality of clusters 258 may be a low voltage (LV) network in a distribution power grid system connected via one or more distribution transformers.

[0141] The one or more assets 260 may include one or more pieces of equipment of the primary equipment 114 of the distribution zone 104. That is, the primary equipment 114 may be divided or assigned to the clusters 258 based on the division of the clusters 258 within the distribution zone 104.

[0142] The cluster measurement device 262 can be configured to measure at least one sub-zone operational parameter of the cluster 258. The cluster operational parameters can include, for example, voltage, power factor, active / reactive power, load per node, battery-based energy storage system (BESS) capacity, distributed energy resource (DER) generation, renewable energy resource (REN) energy source generation, frequency, electric vehicle (EV) load, microgrid generation, microgrid load, feeder voltage, feeder current, feeder load imbalance, power quality data, etc. The cluster measurement device 262 can include one or more of the distribution zone measurement devices 116 in the distribution zone 104. That is, the distribution zone measurement devices 116 can be divided or assigned to the clusters 258 based on the division of the clusters 258 in the distribution zone 104.

[0143] Cluster controller 264 can be configured to adjust at least one cluster operational parameter of cluster 258. Cluster controller 264 can include one or more of the distribution zone controllers 118 in the distribution zone 104. That is, the distribution zone controllers 118 can be divided or assigned to the clusters 258 based on the partitioning of the clusters 258 within the distribution zone 104.

[0144] 10 illustrates a distribution zone 270 in a power grid, according to some examples. Distribution zone 270 may be configured similarly to distribution zone 104 illustrated and described with reference to FIGS. 1 and 9. Distribution zone 270 includes subzone 272. Subzone 272 further includes cluster 274. In FIG. 10, subzone 272 is a feeder, and cluster 274 includes low-voltage load points connected to the feeder.

[0145] 11 illustrates a method for dividing a distribution zone into subzones and clusters and operating a distribution zone controller to rank the subzones and clusters to prioritize adaptive control actions within the distribution zone, according to some embodiments. In some examples, the distribution zone controller is distribution zone controller 120 described with reference to FIGS. 1 and 6, and the distribution zone is distribution zone 104 described with reference to FIGS. 1, 6, and 9.

[0146] In step 280, the distribution zone controller may divide the assigned distribution zone into multiple sub-zones. For example, the distribution zone controller may divide the assigned distribution zone into multiple sub-zones based on a policy defined in ADMS 144 or zone policy database 125. The policy may specify rules or logic for dividing the sub-zones based on, for example, at least one of assets within the assigned distribution zone, network topology, or operational conditions.

[0147] The distribution zone controller may receive sub-zone operational data for each of the plurality of sub-zones at step 282. The distribution zone controller may receive the sub-zone operational data from one or more sub-zone measurement devices 254.

[0148] In some embodiments, the distribution zone controller can determine at least one subzone characteristic for the assigned subzone based on the subzone operational data. The subzone characteristic can include at least one of a critical load, a non-critical load, an electric vehicle load, a vehicle-to-grid generation, a demand response (DR) load, a prosumer generation (PV / DER), a voltage / current imbalance, a total harmonic distortion, a microgrid-enabled generation, or a microgrid-enabled load. The distribution zone controller can further compare the at least one subzone characteristic to a baseline operational characteristic. The baseline operational characteristic can reflect operation of the assigned subzone under normal operating conditions. The normal operating condition can be an operating condition without any violations.

[0149] In some embodiments, the distribution zone controller may further divide at least one subzone into multiple clusters in step 284. For example, the distribution zone controller may divide the subzone into multiple clusters based on a policy defined in ADMS 144 or zone policy database 125. The policy may specify rules or logic for dividing the clusters based on, for example, at least one of the assets within the subzone, the network topology, or the operational conditions.

[0150] In some approaches, an assigned distribution zone can include multiple feeders, and clustering rules can instruct the ADMS to divide each feeder into subzones and each load connection point through a distribution transformer within a subzone into a cluster.

[0151] In some embodiments, the distribution zone controller may receive cluster operational data for each of the plurality of clusters in step 286. For example, the distribution zone controller may receive the cluster operational data from the cluster measurement device 262.

[0152] In some embodiments, the distribution zone controller can determine at least one cluster characteristic based on the cluster operation data of the assigned cluster. The cluster characteristic can include one or more of a critical load, a non-critical load, an electric vehicle load, a vehicle-to-grid generation, a load under demand response (DR) scheme, a prosumer generation (PV / DER), a voltage / current imbalance, a total harmonic distortion, a microgrid-enabled generation, or a microgrid-enabled load. The distribution zone controller can further compare the at least one cluster characteristic with a baseline operation characteristic, the baseline operation characteristic reflecting operation of the assigned cluster under normal operating conditions. The distribution zone controller can further determine a load situation awareness parameter indicative of the load characteristics within the respective cluster based on the at least one cluster characteristic.

[0153] In step 288, the distribution zone controller may also determine a distribution zone orchestration metric for the assigned distribution zone based on the sub-zone operational data and the cluster operational data.

[0154] In some approaches, the distribution zone orchestration index may be determined based on at least one of a load flexibility index, a generation flexibility index, or a power quality index.

[0155] The distribution zone controller can determine a load flexibility index based on the load situation awareness parameter. The load flexibility index may be a value representing a level at which the load can be adjusted. To determine the load flexibility index, the distribution zone control can determine a load situation awareness parameter for each of a plurality of clusters. The distribution zone controller can determine the load situation awareness parameter based on at least one cluster characteristic. The load situation awareness parameter can indicate load characteristics within each cluster. In some examples, the load situation awareness parameter includes at least one of loads available for reduction, loads available for demand response execution, electric vehicle loads, and MG-enabled loads, a level of load dispatch flexibility, a percentage of serviceable critical loads, a level of non-critical loads available for reduction, or a level of loads registered in a DR scheme.

[0156] The distribution zone controller can determine a generation flexibility index based on a generation situation awareness parameter. The generation flexibility index may be a value representing a level at which power generation can be adjusted in each cluster. The distribution zone controller can determine a generation situation awareness parameter based on at least one cluster characteristic. The generation situation awareness parameter may be indicative of a generation characteristic within each cluster. In some examples, the generation situation awareness parameter can include at least one of: incoming generation, vehicle-to-grid generation, microgrid-enabled generation, PV-enabled generation, distributed energy resource-enabled generation, a level of power generation dispatch flexibility, a level of available DER generation, a level of microgrid generation available for grid supply, or a level of available ancillary services.

[0157] The distribution zone controller can determine a power quality index for each of the plurality of clusters based on a power quality situation awareness parameter. The power quality flexibility index is a value representing a level at which the load can be adjusted. The distribution zone controller can determine the power quality situation awareness parameter based on at least one cluster characteristic. The power quality situation awareness parameter can indicate power quality characteristics within the respective cluster. In some examples, the power quality situation awareness parameter can include at least one of a voltage / current imbalance, a total harmonic distortion (THD), a voltage / frequency variation, SAIDI / CAIDI / SAIFI, a power quality impact level, a level of a voltage sag / swell event, a SAIDI / CAIDI level, a SAIFI / CAIFI level, a harmonic content level, a power quality impact rating, a level of no voltage sag / swell event, a SAIDI / CAIDI level, a SAIFI / CAIFI level, or a harmonic content.

[0158] In step 290, the distribution zone controller may determine an adaptive control action for the assigned distribution zone. For example, the distribution zone controller may determine an adaptive control action for at least one of the sub-zone controller 256 or the cluster controller 264 based on the distribution zone orchestration metrics.

[0159] In some approaches, the distribution zone controllers can use an adaptive control machine learning model to determine adaptive control actions. The adaptive control machine learning model can be trained on at least one of subzone operating parameter history, simulated subzone operating parameters, cluster operating parameter history, simulated cluster operating parameters, distribution control action history, simulated distribution control action, simulated distribution zone adaptive policy, or distribution zone adaptive policy history. The adaptive control machine learning model is described in further detail with reference to FIG. 6.

[0160] In step 292, the distribution zone controller may communicate a command to at least one of the sub-zone controller or the cluster controller based on the adaptive control action.

[0161] In some embodiments, the distribution zone controller can further determine a predictive control action for the assigned distribution zone. The distribution zone controller can receive forecast data for a sub-zone or cluster. For example, the distribution zone controller can receive the forecast data from a zone forecast / plan database 128. The distribution zone controller can also receive a zone policy. For example, the distribution zone controller can receive a zone policy from a zone policy database. The distribution zone controller can then determine a predictive control action based on at least one of the sub-zone operational data, the cluster operational data, the forecast data, and the zone policy.

[0162] In some approaches, the distribution zone controller can determine the predictive control action using a predictive control machine learning model. The predictive control machine learning model can be trained on at least one of subzone operating parameter history, simulated subzone operating parameters, cluster operating parameter history, simulated cluster operating parameters, distribution control action history, simulated distribution control action, subzone forecast data history, simulated subzone forecast data, simulated cluster forecast data, or cluster forecast data history. In some approaches, the distribution zone controller can determine the adaptive control action using an adaptive control machine learning model. The adaptive control machine learning model can be trained on at least one of subzone operating parameter history, simulated subzone operating parameters, cluster operating parameter history, simulated cluster operating parameters, distribution control action history, simulated distribution control action, simulated distribution zone adaptive policy, or distribution zone adaptive policy history. The predictive control machine learning model is described in further detail with reference to FIG. 6.

[0163] 12 illustrates a method of operating a distribution zone controller to prioritize adaptive and predictive control actions within a distribution zone, according to some embodiments. In some examples, the distribution zone controller is distribution zone controller 120 described with reference to FIGS. 1 and 6, and the distribution zone is distribution zone 104 described with reference to FIGS. 1, 6, and 9. It is contemplated that one or more steps of the method of FIG. 12 may be performed in conjunction with the method of FIG. 11.

[0164] Steps 300 through 312 show a method for determining priorities for adaptive control actions in a distribution zone.

[0165] In step 300, the distribution zone controller may divide an assigned distribution zone of the plurality of distribution zones into a plurality of subzones. The plurality of subzones may be modeled as a digital twin by the distribution zone controller. The digital twin may model the subzone (or, in some embodiments, the zone) and learn through the subzone's data to understand and / or predict the subzone's operational characteristics and how the subzone will behave in certain scenarios. The subzone's digital twin model may make predictions based on historical data, operational data, and any other available data related to the particular subzone. For example, the digital twin model may be used to determine how the subzone will respond to a current sag.

[0166] A digital twin can model one or more specific assets within a subzone. In a power grid distribution system, a digital twin can model the assets within a subzone as software assets. For example, a subzone may include a transformer as a physical asset. The digital twin model associated with the subzone may then include a 3D model of the transformer that analyzes the transformer's historical data to help an operator understand how the transformer is operating, loading, reacting, etc. The digital twin model of the subzone can be accessed by an operator to support decision-making or to predict how the asset will behave or perform in certain scenarios.

[0167] In step 302, the distribution zone controller may also divide at least one of the plurality of subzones into a plurality of clusters. The plurality of clusters may also be modeled as digital twins by the distribution zone controller. The digital twin model of the cluster is similar to that described above for the subzones.

[0168] In step 304, the distribution zone controller may determine, based on the sub-zone operational data, one or more of the following parameters for the current period: a load situation awareness parameter, a generation situation awareness parameter, or a power quality situation awareness parameter.

[0169] In step 306, the distribution zone controller may determine, based on the sub-zone operational data, one or more of the following indicators for the current period: a load flexibility indicator, a generation flexibility indicator, or a power flexibility indicator.

[0170] In step 308, the distribution zone controller may determine a distribution zone orchestration index for at least one sub-zone based on the load flexibility index, the generation flexibility index, and the power quality flexibility index.

[0171] In step 310, the distribution zone controller may determine a rank for the plurality of sub-zones based on the zone orchestration metrics. The rank may indicate a level of priority for at least one of adaptive control action, an emergency situation, or planning for a future time interval. In some examples, the emergency situation includes at least one of a fault or a weather-related condition.

[0172] In step 312, the distribution zone controller may determine a priority for the adaptive control action for the assigned distribution zone based on the rank. The distribution zone controller may also communicate one or more commands to distribution zone controllers in the assigned distribution zone, the commands configured to perform the adaptive control action.

[0173] Steps 314 through 326 show a method for determining the priority of predictive control actions in a distribution zone.

[0174] In step 314, the distribution zone controller may divide the assigned distribution zone of the plurality of distribution zones into a plurality of sub-zones, which may be modeled as digital twins by the distribution zone controller.

[0175] In step 316, the distribution zone controller may divide at least one subzone of the plurality of subzones into a plurality of clusters. The plurality of clusters may be modeled as a digital twin by the distribution zone controller.

[0176] In step 318, the distribution zone controller may determine one or more of a load situation awareness parameter, a generation situation awareness parameter, or a power quality situation awareness parameter for a future time period based on the sub-zone operational data.

[0177] In step 320, the distribution zone controller may determine one or more of a load flexibility index, a generation flexibility index, or a power quality flexibility index for a future time period based on the sub-zone operational data.

[0178] In step 322, the distribution zone controller may determine a distribution zone orchestration index for at least one sub-zone based on the load flexibility index, the generation flexibility index, and the power quality flexibility index.

[0179] In step 324, the distribution zone controller may determine a rank for the plurality of sub-zones based on the zone orchestration metrics.

[0180] In step 326, the distribution zone controller may prioritize predictive control actions for assigned distribution zones based on the rank.

[0181] Distribution Intelligent Fault Location, Isolation, and Service Restoration (FLISR) In some embodiments, the systems and methods provided herein can divide a distribution zone into subzones and clusters to perform intelligent fault location, isolation, and service restoration within the distribution zone. A distribution zone controller assigned to the distribution zone can then determine a power restorability index for the distribution zone for each subzone or cluster. The power restorability index may guide the prioritization of power restoration control actions in the distribution zone.

[0182] 13 illustrates a method of operating a distribution zone controller to determine and execute restoration control actions in a distribution zone, according to some embodiments. In some examples, the distribution zone controller is distribution zone controller 120 described with reference to FIGS. 1 and 6, and the distribution zone is distribution zone 104 described with reference to FIGS. 1, 6, and 9.

[0183] In step 330, the distribution zone controller may receive sub-zone operational data for the assigned distribution zone. For example, the distribution zone controller 120 may receive the sub-zone operational data from one or more sub-zone measurement devices 254.

[0184] In some embodiments, the distribution zone controller can determine at least one subzone characteristic for the assigned subzone based on the subzone operational data, The subzone characteristic can include at least one of a critical load, a non-critical load, an electric vehicle load, a vehicle-to-grid generation, a demand response (DR) load, a prosumer generation (PV / DER), a voltage / current imbalance, a total harmonic distortion, a microgrid-enabled generation, or a microgrid-enabled load.

[0185] In step 332, the distribution zone controller may receive cluster operational data for the assigned distribution zone. For example, the distribution zone controller 120 may receive the cluster operational data from one or more of the cluster measurement devices 262.

[0186] In some embodiments, the distribution zone controller can determine at least one cluster characteristic of the assigned subzone based on the subzone operational data, where the cluster characteristic can include at least one of a critical load, a non-critical load, an electric vehicle load, a vehicle-to-grid generation, a load under demand response (DR) scheme, a prosumer generation (PV / DER), a voltage / current imbalance, a total harmonic distortion, a microgrid-enabled generation, or a microgrid-enabled load.

[0187] In step 334, the distribution zone controller may determine a power restorability indicator for at least one subzone within the assigned distribution zone based on at least one of the subzone operational data or the cluster operational data.

[0188] In some embodiments, the distribution zone controller may determine the power restoreability index based on at least one of a load restoration index, a generation flexibility index, or a resiliency index.

[0189] The distribution zone controller can determine a load restoration index for at least one of the plurality of clusters based on a load situation awareness parameter. The load restoration index may be a value representing a level at which the load can be adjusted. The distribution zone controller can determine a load situation awareness parameter for at least one of the plurality of clusters based on at least one cluster characteristic. The load situation awareness parameter may indicate a load characteristic. In some examples, the load situation awareness parameter can include at least one of a load available for reduction, a load available for demand response execution, an electric vehicle load, a mass transport (MG)-enabled load, a level of load dispatch flexibility, a percentage of serviceable critical load, a level of non-critical load available for reduction, or a level of load registered in a demand response scheme.

[0190] The distribution zone controller can determine a generation flexibility index for at least one of the plurality of clusters based on a generation situation awareness parameter. The generation flexibility index is a value representing a level at which power generation can be adjusted. The distribution zone controller can determine the generation situation awareness parameter based on at least one cluster characteristic. The generation situation awareness parameter can be indicative of a power generation characteristic. In some examples, the generation situation awareness parameter can include at least one of: incoming generation, vehicle-to-grid generation, microgrid-enabled generation, PV-enabled generation, distributed energy resource-enabled generation, a level of power generation dispatch flexibility, a level of available DER generation, a level of microgrid generation available for grid supply, or a level of available ancillary services.

[0191] The distribution zone controller can determine a resiliency index for at least one of the plurality of clusters based on a power restoration situation awareness parameter. The resiliency index may be a value representing a level of power reliability. The distribution zone controller can determine the power restoration situation awareness parameter based on at least one cluster characteristic. The power restoration situation awareness parameter can indicate a power restoration characteristic. In some examples, the power restoration situation awareness parameter can include at least one of a voltage or current imbalance, a voltage violation, a frequency violation, an asset dielectric load, an asset total harmonic distortion, a generation load imbalance, a system average interruption duration index (SAIDI), a customer average interruption duration index (CAIDI), a system average interruption frequency index (SAIFI), or a customer average interruption frequency index (CAIFI), a number of outage assets, a restoration time, a number of asset overloads, a restoration time, a generation / load balance, or an unserviceable load amount.

[0192] In step 336, the distribution zone controller may determine a power restoration control action based on the power restoreability indicator. In some examples, the power restoration control action may adjust settings for one or more of the plurality of sub-zone controllers 256 for power restoration of the power grid system. In some examples, the power restoration control action may adjust settings for one or more of the cluster controllers 264 for power restoration of the power grid system.

[0193] In some embodiments, the distribution zone controller can determine a restoration control action based on a restoration machine learning model. The restoration machine learning model can be trained on at least one of sub-zone operating parameter history, cluster operating parameter history, resiliency index history, restoration control measure history, fault location history, fault type history, fault severity level history, restoration time history, or simulated fault per location data.

[0194] In step 338, the distribution zone controller may communicate a command to one or more of the sub-zone controllers or to one or more cluster controllers based on the power restoration control action. In some examples, the distribution zone controller 120 may communicate the command to the sub-zone controller 256 or the cluster controller 264. In some approaches, at least one of the multiple sub-zones may include an associated sub-zone controller. The sub-zone controller may be communicatively coupled to the distribution zone controller and configured to implement the restoration control action.

[0195] In some embodiments, the distribution zone controller can also determine a predictive restoration control action for an assigned distribution zone based on the predicted power restorability index. The distribution zone controller can foresee or predict a fault or event occurring in the distribution zone. The predictive restoration control action may be an action taken to avoid such a predicted fault or event. If a fault or event cannot be avoided, the predictive restoration control action may be an action to correct, mitigate, or otherwise respond to the predicted fault or event in the distribution zone. When determining a predictive restoration control action, the distribution zone controller can ensure that restoration is possible without causing physical challenges to the distribution grid. For example, the predictive restoration control action can ensure that power, or in some cases maximum power, is restored in the distribution zone. The controller can determine the predictive restoration control action using the power restorability index for a particular distribution zone. For example, in the case of a fault at a particular location in the distribution zone, the distribution zone controller determines a power restorability index. The power restorability index can indicate a lower or higher likelihood of power restoration if a fault occurs at that particular location. If the power restoration possibility index indicates that power restoration possibility is low, the utility may consider adding additional generation or controlling demand in the distribution zone, or may develop a plan to restore some power to that particular location.

[0196] In some embodiments, the distribution zone controller determines the predictive restoration control action based on a predictive restoration machine learning model that may be trained on at least one of historical subzone operating parameters, simulated subzone operating parameters, historical cluster operating parameters, simulated cluster operating parameters, historical predicted resiliency index, historical restoration control measures, historical fault locations, historical fault types, historical fault severity levels, historical restoration times, or simulated faults per location data.

[0197] 14 illustrates a method of operating a distribution zone controller to prioritize adaptive and predictive control actions within a distribution zone, according to some embodiments. In some examples, the distribution zone controller is distribution zone controller 120 described with reference to FIGS. 1 and 6, and the distribution zone is distribution zone 104 described with reference to FIGS. 1, 6, and 9.

[0198] Steps 350 through 362 show a method for determining priorities for adaptive control actions in a distribution zone.

[0199] In step 350, the distribution zone controller may divide an assigned one of the plurality of distribution zones into a plurality of sub-zones, which may be modeled as digital twins.

[0200] In step 352, the distribution zone controller may divide at least one subzone of the plurality of subzones into a plurality of clusters. The clusters may be modeled as digital twins.

[0201] In step 354, the distribution zone controller may determine situation awareness parameters for the current time period based on the sub-zone operational data and / or the cluster operational data. The situation awareness parameters may include at least one of a load situation awareness parameter, a generation situation awareness parameter, or a power restoration situation awareness parameter. The distribution zone controller may determine situation awareness parameters for at least one of the sub-zones and / or at least one of the clusters.

[0202] In step 356, the distribution zone controller may determine one or more indicators for the current time period based on the sub-zone operational data and / or the cluster operational data. The indicators may include at least one of a load flexibility indicator, a generation flexibility indicator, or a power restoration flexibility indicator. The distribution zone controller may determine an indicator for at least one of the sub-zones and / or at least one of the clusters.

[0203] In step 358, the distribution zone controller may determine a power restoreability index for at least one sub-zone based on the load flexibility index, the generation flexibility index, and the power quality flexibility index.

[0204] In step 360, the distribution zone controller may determine a rank for the plurality of sub-zones based on the power restoreability index. The rank may indicate an order of restoration in the assigned distribution zone.

[0205] In step 362, the distribution zone controller may determine a priority for adaptive restoration control action for the assigned distribution zone based on the rank.

[0206] Steps 364 through 376 show a method for determining the priority of predictive control actions in a distribution zone.

[0207] In step 364, the distribution zone controller may divide the assigned distribution zone of the plurality of distribution zones into a plurality of sub-zones. The distribution zone controller may model the sub-zones as digital twins.

[0208] In step 366, the distribution zone controller may divide at least one subzone of the plurality of subzones into a plurality of clusters. The distribution zone controller may model the clusters as digital twins.

[0209] In step 368, the distribution zone controller may determine predictive situation awareness parameters for a future time period based on the sub-zone operational data and / or the cluster operational data. The predictive situation awareness parameters may include at least one of a load situation awareness parameter, a generation situation awareness parameter, or a power restoration situation awareness parameter. The distribution zone controller may determine the predictive situation awareness parameters for at least one of the sub-zones and / or at least one of the clusters.

[0210] In step 370, the distribution zone controller may determine a forecast index for a future period, i.e., a forecast load flexibility index, a forecast generation flexibility index, or a forecast power restoration flexibility index, based on the sub-zone operational data. The distribution zone controller may determine the forecast index for at least one of the sub-zones and / or at least one of the clusters.

[0211] In step 372, the distribution zone controller may determine a predicted power restoreability index for at least one sub-zone based on the predicted load flexibility index, the predicted generation flexibility index, and the predicted power quality flexibility index.

[0212] In step 374, the distribution zone controller may determine a rank for the plurality of sub-zones based on the predicted power restoreability index. The rank may indicate an order of restoration in the assigned distribution zone.

[0213] In step 376, the distribution zone controller may prioritize predicted restoration control actions for assigned distribution zones based on the rank.

[0214] Federated Grid Management System In some embodiments, the systems and methods provided herein can use a federated grid management system to provide an aggregated data representation of all physical assets in the power grid, providing a unified view of the power grid across markets, planners, operators, and prosumers. Such an aggregated data representation can improve visibility and data sharing across the power grid. The aggregated data representation can also provide increased data fidelity at the local level with power grid edge intelligence to facilitate increased visibility and control for decentralized location decisions. The federated grid management system can include a digital twin, e.g., a cloud-based digital twin, to improve visibility for increased data sharing and collaboration across all participants or users of the power grid.

[0215] In some aspects, the federated grid management system can coordinate data presented to users of the power grid. In this way, the federated grid management system can provide data exchange and control for transmission system operators (TSOs), distribution system operators (DSOs), and distribution network operators (DNOs). Traditional approaches for power grid data acquisition and modeling can use an “all-encompassing” approach in which all data is visible and accessible and not tailored to specific power grid users or participants. An “all-encompassing” approach can be technically and financially prohibitive as power grid complexity increases with accelerated decarbonization and electrification trends. The federated grid management system can exchange and control data on the power grid based on power grid participants or users. For example, providing tailored data fidelity based on location within the power grid and specific users or participants can improve the digitization, automation, and organization of the power grid for different planners, operators, and participants connected to the power grid. Coordinating data exchange and control in this manner can help, for example, improve data visibility on the power grid as variable renewable energy (VRE) and distributed energy resources (DERs) increase.

[0216] 15 illustrates a federated grid management system 134, according to some embodiments. The federated grid management system 134 can include a federated grid modeling agent 136, a zonal autonomous control management agent 138, a zonal predictive control management agent 139, a machine learning engine 140, and a data fabric engine 142.

[0217] The federated grid modeling agent 136 can be configured to model a power grid having multiple zones with a unified structure. The unified structure may be a zone topology, a zone network analogy (e.g., representing zones in a common format so that the power grid network has a unified structure), a zone representation, or a zone model that is the same for each of the multiple zones. The federated grid modeling agent 136 can model a transmission grid as multiple transmission zones, where the multiple transmission zones have a unified structure. The federated grid modeling agent 136 can also model a distribution grid as multiple distribution zones, where the multiple distribution zones have a unified structure. In some examples, the multiple distribution zones can be modeled as loads in the transmission grid. The federated grid modeling agent 136 can communicate with the training database 122.

[0218] Zone autonomous control and management agent 138 can be configured to determine or identify one or more adaptive control actions within power grid system 100. For example, zone autonomous control and management agent 138 can determine the adaptive control action based on at least one of zone forecast data and operational data (e.g., zone orchestration metrics) for transmission zone 102. In some aspects, one or more machine learning models of machine learning engine 140 can be integrated with zone autonomous control and management agent 138. For example, an adaptive control machine learning model can determine or identify an adaptive control action for transmission zone 102. The adaptive control machine learning model can be trained on at least one of historical forecast data or historical zone operational data for multiple zone controllers. Zone autonomous control and management agent 138 can communicate with planning database 128 to receive data, such as forecast data. Zone autonomous control and management agent 138 can also communicate with one or more of transmission zone controllers 112. In this manner, zone autonomous control and management agent 138 can be configured to communicate or transmit adaptive control actions to one or more of transmission zone controllers 112 .

[0219] Zonal predictive control and management agent 139 can be configured to determine or identify one or more predictive control actions for transmission zones 102 in power grid system 100. For example, zonal predictive control and management agent 139 can determine the predictive control actions based on at least one of additions to the power grid or operational data (e.g., zone orchestration metrics) for transmission zones 102. In some aspects, one or more machine learning models of machine learning engine 140 can be integrated with zonal predictive control and management agent 139. For example, the predictive control machine learning model can determine or identify predictive control actions for transmission zones 102. The predictive control machine learning model can be trained on at least one of historical zonal operational data of multiple zone controllers or historical additions to the power grid. Zonal predictive control and management agent 139 can also communicate with one or more of transmission zone controllers 112. In this manner, zonal predictive control and management agent 139 can be configured to communicate or send the predictive control actions to one or more of transmission zone controllers 112. Data fabric engine 142 can communicate with user interface 378. The data fabric engine 142 can adjust the level of data presented through the user interface 378 based on a particular user or application. In this way, the data fabric engine 142 can control the level of data fidelity presented to a user through the federated grid management system 134. The data fabric engine 142 arranges input data from multiple distribution zones in an internally common or consistent format so that the model of the distribution grid is uniform. The data fabric engine 142 also tailors the presentation of data on the distribution grid to a level of detail specific to a particular user of the distribution grid (e.g., a high level for a particular asset or level of interest zoomed in within the distribution system).Thus, the data fabric engine 142 can automatically represent or store data in a common format and tailor the visualization or presentation of the data on the power distribution grid to a particular level.

[0220] Further, in some embodiments, the federated grid management system 134 may communicate with one or more of the distribution zone controllers 120 or with one or more of the transmission zone controllers 112, as shown in FIG. 1 . Data or information received from the zone controllers may be stored in a database associated with the federated grid management system 134. The data or information received from the zone controllers may be organized, mapped, stored, or learned in a uniform manner by the federated grid management system 134. For example, the data or information from the zone controllers may be organized, mapped, or tagged in a standardized manner such that the federated grid management system 134 can identify the data or information as belonging to a particular type of zone based on how the data or information is organized, mapped, or tagged. The federated grid management system 134 can then apply or use the information or data associated with the zone accordingly.

[0221] 16 illustrates a method of operating a federated grid management system to determine adaptation policies for a transmission zone and communicate intervention commands for the transmission zone, according to some embodiments. In some examples, the federated grid management system may be federated grid management system 134 described with reference to FIGS. 1 and 15. It is contemplated that the method of FIG. 16 may be performed by one or more components of federated grid management system 134.

[0222] In step 380, the federated grid management system may receive zone operational data from at least one transmission zone of the plurality of transmission zones. The zone operational data may include, for example, zone orchestration metrics determined by a transmission zone controller associated with the at least one transmission zone.

[0223] In step 382, ​​the federated grid management system may receive zonal forecast data associated with at least one transmission zone. In some examples, the federated grid management system may receive the zonal forecast data from a zonal forecast / planning database. In some examples, the federated grid management system may receive the zonal forecast data from a transmission zone controller associated with the at least one transmission zone.

[0224] In step 384, the federated grid management system may determine a zone adaptation policy for at least one transmission zone based on the zone operational data and the zone forecast data. The zone adaptation policy may define one or more rules for the transmission zone controller in a normal operation mode.

[0225] In step 386, the federated grid management system may communicate the zone adaptation policy to a transmission zone controller associated with at least one transmission zone. The federated grid management system may also communicate the zone adaptation policy to a transmission zone controller associated with another one of the plurality of transmission zones.

[0226] In step 388, the federated grid management system can determine an intervention command for the transmission zone based on the zone adaptation policy. In some examples, the intervention command can be communicated to one or more transmission control devices associated with the at least one transmission zone. The intervention command can, for example, intervene in the operation of a transmission zone controller associated with the at least one transmission zone. In one example, the zone policy for the at least one transmission zone can be designed using analysis from the federated grid management system such that if an emergency control action is taken within the zone, the federated grid management system can issue an intervention command to the transmission zone controller to handle the emergency. Such an emergency can be a fault in the transmission zone where local protection is unable to control the fault or fails to operate. In such a scenario where there is an outage in a transmission zone but power restoration does not occur, the federated grid management system can issue an intervention command to reroute power from another source, such as an adjacent transmission zone, to restore power.

[0227] The federated grid management system may communicate an intervention command to the transmission zone controller in step 390. Communicating an intervention command to the transmission zone controller may intervene in the normal operating mode.

[0228] Figure 17A illustrates a method of operating a federated grid management system according to some embodiments. In some examples, the federated grid management system may be the federated grid management system 134 described with reference to Figures 1 and 15. It is contemplated that the method of Figure 16 may be performed by one or more components of the federated grid management system 134.

[0229] In step 396, the federated grid management system can determine an architecture for the power grid. The power grid can include a transmission grid and a distribution grid. The architecture for the power grid can be determined based on, for example, a Single Line Diagram / Nanowatt (SLD / NW) model of the power grid.

[0230] In step 398, the federated grid management system may form multiple transmission zones in the power grid. In some examples, the federated grid management system may form multiple transmission zones based on assets (e.g., primary assets and / or secondary assets) and interconnections within the power grid. The federated grid management system may partition or form the transmission zones based on one or more assets and one or more policies or rules that define how the transmission zones are formed in the power grid. It is contemplated that the federated grid management system may dynamically form the zones such that the partitions between transmission zones change to accommodate assets being added to or removed from the power grid.

[0231] In step 400, the federated grid management system may identify primary and secondary assets in each of a plurality of transmission zones.

[0232] In step 404, the federated grid management system may also identify a plurality of distribution zones within the power grid. The federated grid management system may represent or model the distribution zones as loads in one or more of the plurality of transmission zones. In some embodiments, the federated grid management system may also identify, form, or partition the transmission zones within the power grid.

[0233] In step 406, the federated grid management system may combine the transmission zones to generate a real-time power grid model.

[0234] In step 408, the federated grid management system may control the power grid based on the real-time power grid model. For example, the federated grid management system may issue one or more intervention commands to transmission zone controllers in the transmission zone to intervene in a normal operation mode.

[0235] In step 410, the federated grid management system may also generate a user-specific federated grid model. The user-specific federated grid model may be tailored to a particular user of the power grid, for example, in data presentation. The user-specific federated grid model may include one or more of an operational federated grid mode, a market federated grid model, a user federated grid mode, or an asset performance management federated grid model.

[0236] 17B illustrates another method of operating a federated grid management system, according to some embodiments. In some examples, the federated grid management system may be the federated grid management system 134 described with reference to FIGS. 1 and 15. It is contemplated that the method of FIG. 16 may be performed by one or more components of the federated grid management system 134.

[0237] In step 396, the federated grid management system 134 determines the power grid architecture. The federated grid management system 134 may determine the power grid architecture via, for example, a single line diagram (SLD) and / or a nanowatt (NW) model of the power grid.

[0238] In step 402, the federated grid management system 134 also receives planning data for the power grid. The planning data may include planned or future contracts, nanowatt (NW) plans, or other requirements for the power grid. The planning data may be associated with the state of the power grid at a future time. In some examples, a user may enter the planning data into the federated grid management system 134 via a user interface (e.g., user interface 378). In other examples, the federated grid management system 134 may receive the planning data from the zonal forecast / planning database 128.

[0239] In step 398, the federated grid management system 134 forms multiple transmission zones in the power grid 398. In some examples, the federated grid management system 134 forms the multiple transmission zones based on one or more of the power grid architecture or planning data. The federated grid management system 134 can form or determine the division of the transmission zones in the power grid based on, for example, one or more policies. The policies can define rules for forming or dividing the transmission zones in the power grid based on, for example, the power grid architecture or the planning data. The planning data can indicate new components that may be added to the power grid in the future and affect the power grid architecture. Thus, the transmission zones can be rearranged based on the planning data. In one example, the policies can dictate or include rules specifying that the zones are formed based on an industry, a microgrid (e.g., solar or wind assets), a power source, or a dominant load cluster present in the power grid architecture. The policies can specify that the industry, microgrid, power source, or dominant load cluster is formed as a zone. In another example, a substation including incoming and outgoing lines from the substation can be a zone. The rules within the policy can form zones based on the dominant factors of the power grid (e.g., load rich, microgrid) as dictated by the power grid architecture.

[0240] In step 400, the federated grid management system 134 may also identify primary assets and secondary assets within the formed multiple transmission zones. As described further below, a primary asset may be any portion of a distribution facility. For example, a primary asset may include at least one of a transformer, a breaker, or a generator. A secondary asset may be an intelligent electronic device (IED) that controls the primary asset. For example, a secondary asset may be a relay, a gate control unit, or a gateway. A secondary asset may be an intelligent electronic device (IED) that controls the primary asset. The federated grid management system 134 may identify primary assets and secondary assets within the power grid based on, for example, power grid architecture and / or planning data.

[0241] In step 403, the federated grid management system 134 may receive a short-term forecast and / or a long-term forecast for the power grid. In some examples, a user may input forecast data, including short-term and / or long-term forecasts, into the federated grid management system 134 via a user interface (e.g., user interface 378). In other examples, the federated grid management system 134 may receive forecast data, including short-term and / or long-term forecasts, from the zonal forecast / planning database 128. In the embodiment shown in FIG. 17C , step 403 is omitted.

[0242] In step 404, the federated grid management system 134 identifies a plurality of distribution zones in the power grid. The federated grid management system 134 models or represents one or more of the plurality of distribution zones as loads in the transmission system, i.e., as loads coupled to the plurality of transmission zones formed in step 398.

[0243] In step 406, the federated grid management system 134 combines the multiple transmission zones to generate a real-time power grid model, which may incorporate data for both transmission zones and distribution zones (e.g., because the distribution zones are modeled as loads within the transmission zones).

[0244] At step 408, the federated grid management system 134 may control the power grid based on the real-time power grid model. For example, the federated grid management system 134 may send or issue one or more intervention commands or actions to the transmission zone controllers 112 and / or the distribution zone controllers 120 to control power grid operation.

[0245] In step 410, federated grid management system 134 generates a user-specific federated grid model 410. The user-specific federated grid model 410, or portions thereof, may be presented to a user via, for example, user interface 378. The user-specific federated grid model may include one or more of an operational federated grid model, a market federated grid model, a user federated grid model, or an asset performance management federated grid model.

[0246] The operational federated grid model may display data related to multiple transmission and / or distribution zones and / or facilitate management of zonal asset controls for multiple transmission and / or distribution zones. The operational federated grid model may also, in some aspects, facilitate viewing and / or managing operational expenditures on a per-zone basis. The operational federated grid model may include one or more load control modules (LCMs) for the multiple transmission and / or distribution zones. The operational federated grid model may also enable a user to view or manage transmission system reliability (TSR) and resource management (RM) for the multiple transmission and / or distribution zones.

[0247] The market federation grid model may display data related to and / or facilitate management of virtual power plants (VPPs) within the power grid. The market federation grid model may also include or be coupled to a supply-demand balancing organization and / or a bid analysis system. Additionally, the market federation grid model may also include or be coupled to one or more customer management systems (CMS) to facilitate management of load demands by power grid customers and other interactions with the power grid.

[0248] The user federated grid model may display data and / or facilitate management of transmission system operations (TSOs) for multiple transmission zones and / or distribution system operations (DSOs) for multiple distribution zones. Additionally, the user federated grid model may display data and / or facilitate management of one or more renewable energy networks (RENs), distributed energy resources (DERs), microgrids (MGs), and / or aggregators (Aggs).

[0249] The asset performance management federated grid model displays data on and / or facilitates zone asset management for the plurality of distribution zones and / or one or more of the plurality of distribution zones. Additionally, the asset performance management federated grid model displays data on and / or facilitates operations and maintenance (O&M) and / or fleet management of assets for the plurality of distribution zones and / or one or more of the plurality of distribution zones.

[0250] Zone Asset Management In some embodiments, the systems and methods provided herein can be used to manage assets within a zone of a power grid system, for example, via an asset management controller. The asset management controller can manage one or more assets within a distribution zone and / or a transmission zone. The zone asset management controller can manage both primary and secondary assets within a zone. Traditional approaches for asset management typically include two separate management systems, one for primary assets and one for secondary assets. In traditional approaches, the systems for primary assets and the systems for secondary assets may not communicate or interact with each other. The approaches described herein utilize a single asset management system or controller for both primary and secondary assets. Using a single asset management system or controller can increase the flexibility and modularity of the system, allowing utilities to deploy systems per application. A single asset management system provides simplified asset management that can be more efficient and reduce operational costs, for example, by avoiding the need to increase the use and deployment of additional human resources to configure assets, assess their health, and collect data. A single asset management system can provide a holistic view of asset usage, optimization, and lifecycle management.

[0251] In some aspects, the zonal asset management architecture described herein can enable one or more of asset fleet management, primary asset management, secondary asset management, asset lifecycle management, zonal advanced analytics, zonal performance prediction, and zonal autonomous control. The asset management controller can coordinate granularity at the zone level. Primary asset management can include providing one or more of health, operations, and control actions or recommendations for primary assets. Secondary asset management can include providing autonomous device operations, upgrades, and management for secondary assets. Asset lifecycle management can include providing end-to-end asset replacement strategies, plans, recommendations, and actions for assets. Zonal advanced analytics can include per-asset and / or per-zone intelligence in the form of digital twin systems. Zonal performance prediction can include short-, medium-, and long-term asset failure prediction, asset risk assessment, asset forecasting, and operations and maintenance (O&M) planning.

[0252] 18 illustrates an exemplary method of operating a power grid system. The method may be performed, for example, by an asset management controller. In the method, the asset management controller measures, monitors, and integrates primary asset data and secondary asset data. In some examples, the method, or portions thereof, may be performed in the asset management controller 145 of the power grid system 100. The asset management controller may be associated with one or more of the multiple zones. For example, the asset management controller may be associated with one or more of the transmission zones 102 and / or one or more of the multiple distribution zones 104.

[0253] In block 430, the asset management controller receives primary asset data for at least one primary asset associated with at least one of the plurality of zones. The primary asset may be any portion of an electrical distribution facility. For example, the primary asset may include at least one of a transformer, a breaker, or a generator. The primary asset data may be any parameter related to the operation or performance of the primary asset. The primary asset data may indicate the health or well-being of the asset. Non-limiting examples of primary asset data include transformer frequency, load, and power factor measured by a secondary asset (e.g., an IED).

[0254] In block 432, the asset management controller receives secondary asset data for at least one secondary asset associated with at least one of the plurality of zones. The secondary asset may be an intelligent electronic device (IED) that controls the primary asset or any other asset that protects, monitors, controls, or measures data related to the primary asset. The secondary asset may be a relay, a gate control unit, or a gateway. The secondary asset data may be any parameter related to the operation or performance of the secondary asset. Non-limiting examples of secondary asset data include IED status, security protocols, and communication details. The secondary asset data may be any data related to the IED and, in some examples, may be provided by the manufacturer of the IED.

[0255] In block 434, the asset management controller determines at least one zone analysis parameter via the at least one machine learning model. The zone analysis parameter may include at least one of a process analysis parameter, a health analysis parameter, a performance analysis parameter, or a security analysis parameter.

[0256] The process analysis parameters may include information indicative of at least one of hardware performance, health, or life cycle of the secondary asset. The process analysis parameters may include at least one of equipment calculation time, equipment performance during the event, hardware diagnostics, firmware logs, equipment-related watchdog events, hardware basic input / output system (BIOS) logs, or equipment time accuracy.

[0257] In some examples, the machine learning model may include a process machine learning model trained via at least one of primary asset data history, secondary asset data history, or process analysis parameter history.

[0258] The health analysis parameter may be indicative of at least one of a health risk, performance, condition state, severity, or reliability of the primary asset. The health analysis parameter may be determined based on data measured from one or more sensors associated with the primary asset. The performance analysis parameter may be indicative of at least one of a design constraint or a load of the primary asset based on a thermal characteristic of the at least one primary asset. The performance analysis parameter may be determined based on at least one of a historical load condition, a historical load pattern, a current load condition, or a current load pattern of the primary asset.

[0259] In some examples, the machine learning model may include a health machine learning model trained via at least one of primary asset data history, secondary asset data history, or health analysis parameter history.

[0260] The performance analysis parameters may indicate at least one of a design constraint or a load of the primary asset based on a thermal characteristic of the primary asset. The performance analysis parameters may be determined based on at least one of a historical load condition, a historical load pattern, a current load condition, or a current load pattern of the primary asset.

[0261] In some examples, the machine learning model may include a performance machine learning model trained via at least one of primary asset data history, secondary asset data history, or performance analysis parameter history.

[0262] The security analysis parameters may indicate a communications and cybersecurity (CCS) risk associated with the secondary asset. The CCS risk may be determined from a security log, a communications log, a series of events, or a traffic analysis associated with a device, such as a secondary asset. In some examples, the CCS risk may be related to a bandwidth level, a latency level, a cybersecurity issue, a pending security patch upgrade, a communications-related misconfiguration, a security-related misconfiguration, or a required update.

[0263] In some examples, the machine learning model may include a cybersecurity machine learning model trained via at least one of primary asset data history, secondary asset data history, or security analysis parameter history.

[0264] At block 436, the asset management controller identifies at least one asset management control action for a control device associated with the at least one zone based on the at least one zone analysis parameter.

[0265] In some examples, asset management control actions are based on health analysis parameters and performance analysis parameters. The asset management control actions may be performed by a transmission zone controller (e.g., performed by the transmission zone controller 110) or a distribution zone controller (e.g., performed by the distribution zone controller 118) in conjunction with the zone asset management ranking. The asset management control action set management control action may be a primary asset loading guideline. The loading guideline may control the load level of at least one primary asset to reduce risk or to redispatch a supply source to another of multiple zones in the power grid system. In one example, if a transformer (e.g., a primary asset) is not healthy and the transformer is assumed to be loaded at 100%, the asset management control action may adjust the load of the transformer to less than 100% based on a health analysis parameter or a performance analysis parameter that indicates the transformer's health is not good. In another example, if a health analysis parameter or a performance analysis parameter indicates that a secondary asset (e.g., an IED) cannot communicate properly, the asset management control action may manage IED communications.

[0266] In some embodiments, the asset management controller can determine a zone situation awareness index for at least one zone based on at least one zone analysis parameter. The zone situation awareness index can indicate at least one of a number of high-risk assets, asset criticality, and asset type. An asset management control action can then be determined based on the zone situation awareness index. The asset management controller can also rank at least one zone of the plurality of zones based on the zone situation awareness index. In this manner, the asset management controller can use the zone situation awareness index to prioritize asset management control actions. The zone situation awareness index can be based on the number of primary assets and the number of secondary assets in the at least one zone.

[0267] At block 438, the asset management controller communicates a command to a distribution zone controller associated with the at least one zone based on the at least one asset management control action. The command may be communicated to a secondary asset associated with at least one of the plurality of zones. In some examples, the command is configured to perform at least one asset management control action on a primary asset associated with the secondary asset.

[0268] In the method of FIG. 18, it is contemplated that the asset management controller may also be configured to rank at least one primary asset or at least one secondary asset for each zone.

[0269] In some embodiments, the asset management controller can determine a lifecycle risk of at least one secondary asset based on the process analysis parameters. Additionally, the asset management controller can determine a communications and cybersecurity (CCS) risk of the at least one secondary asset based on the security analysis parameters. The asset management controller can then determine a ranking of the at least one secondary asset based on the lifecycle risk and the CCS risk. The ranking of the secondary assets can indicate the relative short-term, medium-term, or long-term health of the secondary assets. The ranking of the secondary assets can also identify one or more high-risk secondary assets or secondary assets requiring actions such as maintenance work, risk assessment of failure, change of operating conditions, replacement, disconnection, or load reduction.

[0270] In some embodiments, the asset management controller can determine an asset risk for at least one secondary asset based on the health analysis parameters. The asset management controller can also determine an asset load risk for at least one primary asset based on the performance analysis parameters. The asset management controller can then determine a ranking of the at least one primary asset based on the life cycle risk and the CCS risk. The ranking of the primary assets can indicate the relative short-term, medium-term, or long-term health of the primary assets. The ranking can also identify one or more high-risk primary assets or assets requiring action such as repair, maintenance action, assessment of risk of failure, change of operating conditions, replacement, disconnection, or load reduction.

[0271] 19 illustrates an exemplary method of operating a power grid system. The method may be performed, for example, by an asset management controller. In the method, the asset management controller measures, monitors, and integrates primary asset data and secondary asset data. In some examples, the method, or portions thereof, may be performed in power grid system 100 or a portion thereof, such as asset management controller 145. The asset management controller may be associated with one or more of the multiple zones. For example, the asset management controller may be associated with one or more of the transmission zones 102 and / or one or more of the multiple distribution zones 104.

[0272] At block 440, the method includes determining primary asset data for one or more primary assets. In some approaches, the asset management controller 145 can determine or receive secondary asset data. The primary asset data can be determined via a power automation and control system (PACS) or via another measurement and control (M&C) system associated with the power grid system. In some examples, the primary asset data may be determined via one or more of the transmission zone measurement devices 108 and / or via one or more of the distribution zone measurement devices 116.

[0273] At block 442, the method includes determining secondary asset data for one or more secondary assets. In some approaches, the asset management controller 145 may determine or receive the secondary asset data. The secondary asset data may be determined via a power automation and control system (PACS) or via another measurement and control (M&C) system associated with the power grid system. In some examples, the secondary asset data may be determined via one or more of the transmission zone measurement devices 108 and / or via one or more of the distribution zone measurement devices 116.

[0274] At block 444, the method includes determining one or more zonal analysis parameters. The zonal analysis parameters may be determined based on primary asset and / or secondary asset data. The zonal analysis parameters may be determined or calculated using one or more machine learning algorithms. In some approaches, the asset management controller 145 may determine or calculate the zonal analysis parameters. The zonal analysis parameters may include one or more of a process analysis parameter, a health analysis parameter, a performance analysis parameter, or a CCS analysis parameter. Each of the zonal analysis parameters is described in further detail with reference to FIG. 18 .

[0275] At block 446, the method includes determining a life cycle risk of the one or more secondary assets from the process analysis parameters. In some approaches, the asset management controller 145 can determine the life cycle risk.

[0276] At block 450, the method includes determining a CCS risk for one or more secondary assets from the CCS analysis parameters. In some approaches, the asset management controller 145 may determine the CCS risk.

[0277] At block 454, the method includes determining a ranking of the secondary assets based on the secondary assets' life cycle risk and CCS risk. As described above, the ranking of the secondary assets may indicate the relative short-term, medium-term, or long-term health of the secondary assets. The ranking of the secondary assets may also identify one or more high-risk secondary assets or secondary assets requiring action, such as maintenance work, assessing the risk of failure, changing operating conditions, replacement, disconnection, or load reduction. The ranking may provide a ranking of secondary assets within a fleet, for example, by zone. Thus, the ranking may be used to perform zonal fleet management.

[0278] At block 456, the method includes managing one or more secondary assets based on the rankings. Managing the secondary assets may include adjusting the operation of the one or more secondary assets. In some examples, managing the secondary assets may include changing the operating conditions or reducing the load on the secondary assets. For example, managing the secondary assets may include inputs such as control commands to transmission zone controller 112 or distribution zone controller 120. Asset management controller 145 may communicate commands or other inputs to transmission zone controller 112 to adjust the operation of one or more devices, such as transmission zone control device 110, in transmission zone 102. Asset management controller 145 may also communicate commands or other inputs to distribution zone controller 120 to adjust the operation of one or more devices, such as distribution zone control device 118, in distribution zone 104. In yet other examples, managing the secondary assets may include repairing, replacing, or disconnecting the secondary assets.

[0279] At block 448, the method includes determining an asset health risk for one or more primary assets from the health analysis parameters of each primary asset. In some approaches, the asset management controller 145 can determine the asset health risk.

[0280] At block 452, the method includes determining an asset stress risk for one or more primary assets from the performance analysis parameters of each primary asset. In some approaches, the asset management controller 145 can determine the asset stress risk.

[0281] At block 458, the method includes determining a ranking of the primary assets based on the asset health risk and asset strain risk of the primary assets. As described above, the ranking of the primary assets may indicate the relative short-term, medium-term, or long-term health of the primary assets. The ranking may also identify one or more high-risk primary assets or primary assets requiring action such as repair, maintenance operations, assessment of risk of failure, change of operating conditions, replacement, disconnection, or load reduction. The ranking may provide a ranking of the primary assets within the fleet, for example, by zone. Thus, the ranking may be used to perform zonal fleet management.

[0282] At block 460, the method includes managing one or more primary assets based on the rankings. Managing the primary assets can include actions to adjust the operation of one or more primary assets. In some examples, managing the secondary assets can include changing operating conditions or reducing the load on the primary assets. For example, managing the secondary assets can include inputs such as control commands to the transmission zone controllers 112 or the distribution zone controllers 120. In some aspects, the asset management controller 145 can coordinate to provide asset load guideline inputs to the transmission zone controllers 112 or the distribution zone controllers 120 to adjust the load levels of the assets to avoid immediate risk. The asset management controller 145 can communicate commands or other inputs to the transmission zone controllers 112 to adjust the operation of one or more devices, such as the transmission zone control devices 110 in the transmission zone 102. The asset management controller 145 can also communicate commands or other inputs to the distribution zone controllers 120 to adjust the operation of one or more devices, such as the distribution zone control devices 118 in the distribution zone 104. In yet other examples, managing the primary assets can include repairing, replacing, or disconnecting the secondary assets.

[0283] The terms and expressions used herein have the ordinary technical meaning given to such terms and expressions by one of ordinary skill in the art, unless a different specific meaning is otherwise set forth herein. As used herein, the word "or" shall be construed as having a disjunctive rather than a conjunctive construction, unless otherwise specified. Terms such as "coupled," "fixed," and "attached to" refer to both direct coupling, fixing, or attachment, and indirect coupling, fixing, or attachment via one or more intermediate components or features, unless otherwise specified herein.

[0284] The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

[0285] The term "approximate" used throughout this specification and claims is used to modify any quantitative expression that can vary within acceptable limits without resulting in a change in the basic function to which it pertains. Thus, values ​​modified with terms such as "about," "approximately," and "substantially" are not limited to the exact value specified. In at least some instances, the term "approximate" may correspond to the precision of equipment for measuring a value or the precision of a method or machine for constructing or manufacturing a component and / or system. For example, the term "approximate" may refer to being within a 10% margin.

[0286] Further aspects of the present disclosure are provided by the subject matter of the following clauses.

[0287] 1. A power grid system comprising: an Advanced Distribution Management System (ADMS); distribution zone measurement devices configured to measure at least one zone distribution operational parameter of an assigned distribution zone of a plurality of distribution zones in the power grid, wherein each of the plurality of distribution zones has an associated distribution zone measurement device; and a distribution zone controller associated with the assigned distribution zone and in communication with the distribution zone measurement devices and the Advanced Distribution Management System, wherein each of the plurality of distribution zones has an associated zone controller, wherein the distribution zone controller is configured to: receive distribution zone operational data for the assigned distribution zone from the distribution zone measurement devices; determine a distribution zone orchestration metric for the assigned distribution zone based on the distribution zone operational data; communicate the distribution zone orchestration metric to the Advanced Distribution Management System (ADMS); determine adaptive control actions for one or more distribution control devices in the assigned distribution zone based on the distribution zone orchestration metric; and communicate commands to the one or more distribution control devices based on the adaptive control action.

[0288] 10. The power grid system of any preceding clause, wherein the ADMS is configured to dynamically classify the power grid into a plurality of distribution zones based on at least one of a power grid topology or predetermined logic.

[0289] 10. The power grid system of claim 1, wherein each of the plurality of distribution zones includes one or more distribution system assets, the one or more distribution system assets including at least one of a substation equipment, a distribution radial feeder, or a transmission line.

[0290] 10. The power grid system of any preceding clause, wherein each of the plurality of power distribution zones includes one or more interconnections with another one of the plurality of power distribution zones.

[0291] 10. The power grid system of any preceding clause, wherein each of the plurality of distribution zones transmits power distribution operational data to the advanced distribution management system.

[0292] 10. The power grid system of claim 1, wherein the distribution zone operational data includes at least one of voltage, power factor, active / reactive power, load per node, battery-based energy storage system (BESS) capacity, distributed energy resource (DER) generation, renewable energy resource (REN) energy source generation, frequency, electric vehicle (EV) load, microgrid generation, microgrid load, feeder voltage, feeder current, feeder load imbalance, or power quality data.

[0293] 10. The power grid system of any preceding clause, wherein the commands are configured to cause one or more distribution controllers to perform adaptive control actions.

[0294] The power grid system of any of the preceding clauses, wherein the commands are configured to control at least one of an electric vehicle load or a passive load or an active load, the passive load being an industrial, commercial, or residential load that can be switched on or off but cannot be controlled due to partial use.

[0295] 10. The power grid system of any of the preceding clauses, wherein at least one of the plurality of distribution zones is further divided into a plurality of subzones based on one or more subzoning rules or policies defined in the advanced distribution management system.

[0296] 10. The power grid system of any preceding clause, wherein the distribution zone controller is further configured to receive power distribution operational data from at least one of the plurality of sub-zones.

[0297] 10. The power grid system of claim 1, wherein at least one of the plurality of distribution zones is further divided into a plurality of load clusters based on one or more clustering rules or policies defined in the advanced distribution management system.

[0298] 10. The power grid system of claim 1, wherein an assigned distribution zone includes a plurality of feeders, and wherein the one or more clustering rules instruct the distribution zone controller to divide each feeder into a subzone and to divide each load connection point through a distribution transformer within the subzone into a cluster.

[0299] 10. The power grid system of any preceding clause, wherein the distribution zone orchestration metric is a measure of the operation of an assigned distribution zone with reference to baseline operational data for the assigned distribution zone.

[0300] 10. The power grid system of any preceding clause, wherein the baseline operational data includes one or more of a baseline load for the assigned distribution zone, a baseline setting for one or more distribution control devices, a baseline distributed energy resource (DER) generation profile for the assigned distribution zone, or a baseline intermittency profile for the assigned distribution zone.

[0301] 10. The power grid system of claim 1, wherein the distribution zone controllers are configured to determine the baseline operational data via a baseline machine learning model trained on at least one of historical load data for the assigned distribution zone, simulated load data for the assigned distribution zone, historical settings of one or more distribution control devices, historical distributed energy resource (DER) generation profile data for the assigned distribution zone, historical simulated distributed energy resource (DER) generation profile data for the assigned distribution zone, simulated intermittency profile data for the assigned distribution zone, or historical intermittency profile data for the assigned distribution zone.

[0302] 10. The power grid system of claim 1, wherein the distribution zone controller is further configured to identify distribution zone operation violations based on the distribution zone operation data and the distribution zone policy, and the distribution zone policy includes information regarding at least one of adaptive control sources, how to map adaptive control sources to violations, predictive control sources, how to map predictive control sources to violations, how to operate the multiple distribution zones, how to form subzones or clusters based on the power grid topology, machine learning objectives for the multiple distribution zones, calculating metrics related to operation of the multiple distribution zones, or coordination among the multiple distribution zones.

[0303] 10. The power grid system of any preceding clause, wherein the distribution zone orchestration indicator indicates at least one of an operational violation or a non-operational violation in an assigned distribution zone.

[0304] 10. The power grid system of claim 1, wherein the adaptive control action is determined based on an adaptive control machine learning model trained on at least one of historical distribution zone operating parameters, simulated distribution zone operating parameters, historical distribution control measurements, simulated distribution control measurements, simulated distribution zone adaptive policies, or historical distribution zone adaptive policies.

[0305] 10. The power grid system of claim 1, further configured to: receive distribution forecast data from at least one of an ADMS, a third party engine, a server, a device, or a website; receive distribution zone forecast policies from the advanced distribution management system; and determine predictive control actions based on the distribution zone operational data and the distribution zone forecast policies.

[0306] 10. The power grid system of claim 1, wherein the predictive control action is determined based on a predictive control machine learning model trained on at least one of historical distribution zone operating parameters, simulated distribution zone operating parameters, historical distribution control measurements, simulated distribution control measurements, simulated distribution forecast data, or historical distribution forecast data.

[0307] 10. The power grid system of any preceding clause, wherein the power distribution forecast data includes at least one of forecast load data, forecast weather data, or forecast distributed energy resource (DER) data.

[0308] 10. The power grid system of claim 1, wherein the distribution zone controller is further configured to receive a distribution zone forecast policy from the advanced distribution management system, and wherein the distribution zone controller determines a predictive control action based on the distribution zone forecast policy.

[0309] 10. The power grid system of any preceding clause, wherein the distribution zone controller includes a zone configuration module configured to adjust one or more thresholds, limits, or set points of one or more feeders, assets, or devices within an assigned distribution zone based on the distribution zone operational data.

[0310] 10. The power grid system of any preceding clause, wherein the distribution parameters include at least one of a distribution energy resource, a battery energy storage system, or a volt / VAR optimization parameter.

[0311] 10. The power grid system of any preceding clause, wherein the distribution zone controller includes a zone monitoring module configured to receive operational data from at least one subzone or cluster within an assigned distribution zone.

[0312] 10. The power grid system of any of the preceding clauses, wherein the distribution zone controller includes a zone control module configured to communicate commands to the one or more distribution control devices based on the adaptive control operation or modify one or more set points of the one or more distribution control devices.

[0313] 10. The power grid system of claim 1, wherein the distribution zone controller includes a zone feedback module configured to receive operational data after implementation of one or more adaptive control actions in an assigned distribution zone.

[0314] 10. The power grid system of claim 1, wherein the distribution zone controller includes a zone low voltage (LV) module, the LV module being a cluster of assigned subzones, and the LV module is configured to receive operational data from low voltage circuits in its assigned distribution zone using an advanced metering infrastructure (AMI) or a meter data management system, and the operational data includes at least one of electric vehicle (EV) load, rooftop solar (PV) generation, power quality, total load, critical load, or load imbalance.

[0315] 10. The power grid system of claim 1, wherein the distribution zone controller includes a zone machine learning module configured to determine adaptive control actions using a machine learning model trained on at least one of the distribution zone operating parameter history, the simulated distribution zone operating parameters, the simulated distribution adaptive control measure, or the distribution adaptive control measure history.

[0316] 10. The power grid system of any preceding clause, wherein the distribution zone controller is further configured to communicate the distribution zone orchestration metrics to an advanced distribution management system (ADMS).

[0317] 10. The power grid system of any of the preceding clauses, wherein the advanced distribution management system (ADMS) is configured to communicate an intervention control command to the distribution zone controller based on the distribution zone orchestration indicator and the distribution zone orchestration indicator from another one of the plurality of distribution zones, wherein the intervention control command addresses at least one of an operational violation or a non-operational violation in the plurality of distribution zones.

[0318] 10. The power grid system of claim 1, further configured: the distribution zone controller determines at least one of a load / generation increase index or a distributed energy resource (DER) intermittency level for an assigned distribution zone; and determines settings of the one or more distribution control devices based on the load / generation increase index or the distributed energy resource (DER) intermittency level.

[0319] 10. The power grid system of claim 1, wherein the load / generation increase index indicates the degree to which load / generation has increased in an assigned distribution zone, and the DER intermittency level indicates the difference between actual DER generation and predicted DER generation for a particular time interval.

[0320] 10. The power grid system of any preceding clause, wherein the distribution zone orchestration index is determined based on at least one of a load / generation growth index and a DER intermittency level.

[0321] 10. The power grid system of claim 1, further configured to: receive a fault recovery plan for a fault in an assigned distribution zone; and determine a configuration of one or more distribution control devices based on the fault recovery plan.

[0322] 10. The power grid system of claim 1, further configured: the distribution zone controller receives an outage restoration plan for an assigned distribution zone; and determines settings for the one or more distribution control devices based on the outage restoration plan.

[0323] 10. The power grid system of claim 1, further configured: the distribution zone controller receives a load management plan for an assigned distribution zone; and determines settings of the one or more distribution control devices based on the load management plan.

[0324] 10. The power grid system of claim 1, further configured to: receive a commitment or registration of a new distributed energy resource (DER) for an assigned distribution zone; and determine a configuration of one or more distribution control devices based on the commitment or registration of the new distributed energy resource (DER).

[0325] 10. The power grid system of claim 1, further configured: the distribution zone controllers receive voltages / VAR flows on the feeders and buses under steady-state operation; determine voltages / VAR flows on the feeders and buses after a planned reconfiguration; and determine a target voltage / VAR profile based on the voltages / VAR flows on the feeders and buses after the planned reconfiguration.

[0326] The method includes, at each of a plurality of zone controllers associated with a plurality of distribution zones, receiving zone power distribution operational data for an assigned distribution zone from a distribution zone measurement device associated with the assigned distribution zone; determining a distribution zone orchestration indicator for the assigned distribution zone based on the zone power distribution operational data; communicating the distribution zone orchestration indicator to an advanced distribution management system (ADMS); determining an adaptive control action for one or more distribution control devices in the assigned distribution zone based on the distribution zone orchestration indicator; and communicating commands to the one or more distribution control devices based on the adaptive control action.

[0327] 10. The method of any of the preceding clauses, wherein each of a plurality of distribution zones includes one or more distribution system assets.

[0328] 10. The method of any of the preceding clauses, wherein the one or more electrical distribution system assets include at least one of a substation equipment, an electrical distribution radial feeder, or a transmission line.

[0329] 10. The method of any of the preceding clauses, wherein each of the plurality of power distribution zones includes one or more interconnections with another one of the plurality of power distribution zones.

[0330] 10. The method of any of the preceding clauses, wherein each of the plurality of distribution zones transmits distribution operational data to an advanced distribution management system.

[0331] 10. The method of claim 1, wherein the zone power distribution operational data includes at least one of power data, quality factor data, or voltage data.

[0332] 10. The method of any of the preceding clauses, wherein the commands are configured to cause one or more distribution controllers to perform adaptive control actions.

[0333] 10. The method of any of the preceding clauses, wherein the commands are configured to control at least one of an electric vehicle load or a passive load.

[0334] The method of any of the preceding clauses, wherein at least one of the plurality of distribution zones is further divided into a plurality of subzones based on one or more subzoning rules or policies defined in the advanced distribution management system.

[0335] 10. The method of any of the preceding clauses, further comprising receiving electrical distribution operational data from at least one of the plurality of subzones.

[0336] The method according to any of the preceding clauses, wherein at least one of the plurality of distribution zones is further divided into a plurality of load clusters based on one or more clustering rules or policies defined in the advanced distribution management system.

[0337] 10. The method of any of the preceding clauses, wherein the distribution zone orchestration metrics reference baseline operational data for the assigned distribution zone and are measures of the operation of the assigned distribution zone.

[0338] The method of any of the preceding clauses, wherein the baseline operational data includes one or more of a baseline load for the assigned distribution zone, a baseline setting for one or more distribution control devices, a baseline distributed energy resource (DER) generation profile for the assigned distribution zone, or a baseline intermittency profile for the assigned distribution zone.

[0339] 10. The method of claim 1, wherein the distribution zone controller is configured to determine the baseline operational data via a baseline machine learning module trained on at least one of historical load data for the assigned distribution zone, historical settings of one or more distribution control devices, historical distributed energy resource (DER) generation profile data for the assigned distribution zone, or historical intermittency profile data for the assigned distribution zone.

[0340] The method of any of the preceding clauses, further comprising identifying a distribution zone operation violation based on the zone distribution operation data and the distribution zone policy.

[0341] The method of any of the preceding clauses, wherein the distribution zone orchestration indicator indicates at least one of an operational violation or a non-operational violation in the assigned distribution zone.

[0342] 10. The method of any of the preceding clauses, wherein the adaptive control action is determined based on an adaptive control machine learning model trained on at least one of distribution zone operating parameter history, distribution control action history, or distribution zone adaptive policy history.

[0343] 10. The method of any of the preceding clauses, further comprising: receiving distribution forecast data; receiving a distribution zone forecast policy from an advanced distribution management system; and determining a predictive control action based on the zonal distribution operational data and the distribution zone forecast policy.

[0344] 10. The method of any of the preceding clauses, wherein the predictive control action is determined based on a predictive control machine learning model trained on at least one of historical distribution zone operating parameters, historical distribution control actions, or historical distribution forecast data.

[0345] 10. The method of claim 1, wherein the distribution forecast data includes at least one of forecast load data, forecast weather data, or forecast distributed energy resource (DER) data.

[0346] 10. The method of claim 1, further comprising: receiving a distribution zone forecast policy from an advanced distribution management system; and determining a predictive control action for an assigned distribution zone based on the zone forecast policy.

[0347] The method of any of the preceding clauses, further comprising adjusting one or more thresholds, limits, or set points of the distribution parameters within the assigned distribution zone.

[0348] 10. The method of any of the preceding clauses, wherein the distribution parameters include at least one of a distribution energy resource, a battery energy storage system, or a volt / VAR optimization parameter.

[0349] The method according to any of the preceding clauses, further comprising receiving operational data from at least one subzone or cluster within the assigned distribution zone.

[0350] 10. The method of any of the preceding clauses, further comprising communicating the distribution zone orchestration metrics to an Advanced Distribution Management System (ADMS).

[0351] 10. The method of any of the preceding clauses, further comprising receiving backup control from an advanced distribution management system (ADMS) based on the distribution zone orchestration indicator and the distribution zone orchestration indicator from another one of the plurality of distribution zones.

[0352] 10. The method of claim 1, further comprising: determining at least one of a load / generation increase index or a distributed energy resource (DER) intermittency level for an assigned distribution zone; and determining settings of one or more distribution control devices based on the load / generation increase index or the distributed energy resource (DER) intermittency level.

[0353] 10. The method of claim 1, further comprising: determining a fault recovery plan for a fault within an assigned distribution zone; and determining configurations of one or more distribution control devices based on the fault recovery plan.

[0354] 10. The method of claim 1, further comprising: determining an outage restoration plan for an assigned distribution zone; and determining settings for one or more distribution control devices based on the outage restoration plan.

[0355] 10. The method of any of the preceding clauses, further comprising determining a load management plan for an assigned distribution zone; and determining settings for one or more distribution control devices based on the load management plan.

[0356] The method of any of the preceding clauses, further comprising: determining a commitment or enrollment of a new distributed energy resource (DER) for an assigned distribution zone; and determining a configuration of one or more distribution control devices based on the commitment or enrollment of the new distributed energy resource (DER).

[0357] 10. The method of claim 9, further comprising: determining voltage / VAR flows on the feeders and buses under steady-state operation; determining voltage / VAR flows on the feeders and buses after the planned reconfiguration; and determining a target voltage / VAR profile based on the voltage / VAR flows on the feeders and buses after the planned reconfiguration. [Explanation of symbols]

[0358] 100 Power Grid Systems 102 Transmission Zone 104 Power Distribution Zone 106 Primary substation equipment 108 Power Transmission Zone Measuring Device 110 Transmission Zone Control Device 112 Transmission Zone Controller 114 Primary equipment 116 Distribution Zone Measuring Device 118 Distribution Zone Control Device 120 Distribution Zone Controller 122 Training Database 124 Power Restoration Possibility Index Database 125 Zone Policy Database 128 Planning Database 130 Zone Operational Database 132 Zone Orchestration Metrics Database 134 Federated Grid Management System 136 Federated Grid Modeling Agents 138 Zone Autonomous Control Management Agent 139 Zone Predictive Control Management Agent 140 Machine Learning Engine 142 Data Fabric Engine 144 Advanced Distribution Management System (ADMS) 145 Asset Management Controller 150 Machine Learning Engines 152 Zone Autonomous Management Agent 154 Zone Adaptive Control Agent 156 Zone Predictive Control Agent 180 Power Grid System 180A Renewable Energy Network (REN) Zone 180B Power Generation (GEN) Zone 180C Transfer Zone 180D Flexibility Zone 180E Distributed Energy Resources (DER) Zone 180F Industrial Zone 182 Zone Monitoring Agent 184 Zone Adaptive Control Agent 186 Machine Learning Engine 188 Zone Predictive Control Agent 250 subzones 252 assets 254 Subzone Measuring Device 256 Subzone Control Device 258 clusters 260 assets 262 Cluster Measurement Device 264 Cluster Control Device 270 Power Distribution Zones 272 subzones 274 clusters 378 User Interface 510 Computer Systems 511 processor 512 memory 513 I / O Adapter 514 Network Adapter 515 Input Device 516 Output Device 517 Network

Claims

1. A power grid system (100), comprising: an Advanced Distribution Management System (ADMS) (144); a distribution zone measurement device (116) configured to measure at least one zonal power distribution operational parameter of an assigned distribution zone (104) of a plurality of distribution zones (104) within a power grid, each of the plurality of distribution zones (104) having an associated distribution zone measurement device (116); a distribution zone controller (120) associated with the assigned distribution zone (104) and in communication with the distribution zone measurement device (116) and the advanced distribution management system (144), wherein each of the plurality of distribution zones (104) has an associated zone controller, the distribution zone controller (120) comprising: receiving distribution zone operational data for the assigned distribution zone (104) from the distribution zone measurement device (116); determining a distribution zone orchestration metric for the assigned distribution zone (104) based on the distribution zone operational data; communicating the distribution zone orchestration indicators to the Advanced Distribution Management System (ADMS) (144); determining adaptive control actions for one or more distribution controllers (118) within the assigned distribution zone (104) based on the distribution zone orchestration metrics; communicating a command to the one or more power distribution control devices (118) based on the adaptive control action; The power grid system (100) is configured as follows.

2. 2. The power grid system of claim 1, wherein the ADMS is configured to dynamically categorize the power grid into the plurality of distribution zones based on at least one of a power grid topology or predetermined logic.

3. 2. The power grid system (100) of claim 1, wherein each of the plurality of distribution zones (104) includes one or more distribution system assets, the one or more distribution system assets including at least one of substation equipment (106), a distribution radial feeder, or a transmission line.

4. The power grid system (100) of any preceding claim, wherein each of the plurality of power distribution zones (104) includes one or more interconnections with another one of the plurality of power distribution zones (104).

5. The power grid system (100) of any preceding claim, wherein each of the plurality of distribution zones (104) transmits distribution operational data to the advanced distribution management system (144).

6. 2. The power grid system (100) of claim 1, wherein the distribution zone operational data comprises at least one of voltage, power factor, active / reactive power, load per node, battery-based storage system (BESS) capacity, distributed energy resource (DER) generation, renewable energy resource (REN) energy source generation, frequency, electric vehicle (EV) load, microgrid generation, microgrid load, feeder voltage, feeder current, feeder load imbalance, or power quality data.

7. The power grid system (100) of claim 1, wherein the command is configured to cause the one or more distribution controllers (118) to perform the adaptive control action.

8. 10. The power grid system (100) of claim 1, wherein the commands are configured to control at least one of an electric vehicle load, a passive load, or an active load, the passive load being an industrial, commercial, or residential load that can be switched on or off but cannot be controlled for partial use.

9. 2. The power grid system (100) of claim 1, wherein at least one of the plurality of distribution zones (104) is further divided into a plurality of subzones (250) based on one or more subzoning rules or policies defined in the advanced distribution management system (144).

10. the distribution zone controller (120) receiving distribution operational data from at least one of the plurality of sub-zones (250); The power grid system (100) of claim 9, further configured:

11. 10. The power grid system (100) of claim 9, wherein at least one of the plurality of distribution zones (104) is further divided into a plurality of load clusters (258) based on one or more clustering rules or policies defined in the advanced distribution management system (144).

12. 12. The power grid system of claim 11, wherein the assigned distribution zone includes a plurality of feeders, and the one or more clustering rules instruct the distribution zone controller to divide each feeder into a subzone and each load connection point through a distribution transformer within the subzone into a cluster.

13. 2. The power grid system (100) of claim 1, wherein the distribution zone orchestration metric is a measure of the operation of the assigned distribution zone (104) with reference to baseline operational data for the assigned distribution zone (104).

14. 14. The power grid system (100) of claim 13, wherein the baseline operational data comprises one or more of a baseline load for the assigned distribution zone (104), a baseline setting for the one or more distribution controllers (118), a baseline distributed energy resource (DER) generation profile for the assigned distribution zone (104), or a baseline intermittency profile for the assigned distribution zone (104).

15. 14. The power grid system of claim 13, wherein the distribution zone controller is configured to determine the baseline operational data via a baseline machine learning model trained on at least one of historical load data for the assigned distribution zone, simulated load data for the assigned distribution zone, historical settings of the one or more distribution controllers, historical distributed energy resource (DER) generation profile data for the assigned distribution zone, historical simulated distributed energy resource (DER) generation profile data for the assigned distribution zone, simulated intermittency profile data for the assigned distribution zone, or historical intermittency profile data for the assigned distribution zone.

16. The distribution zone controller (120) 2. The power grid system of claim 1, further configured to identify distribution zone operation violations based on the distribution zone operation data and a distribution zone policy, wherein the distribution zone policy includes information regarding at least one of adaptive control sources, how adaptive control sources map to violations, predictive control sources, how predictive control sources map to violations, how to operate the plurality of distribution zones, how to form subzones or clusters based on a power grid topology, machine learning goals for the plurality of distribution zones, calculating metrics related to operation of the plurality of distribution zones, or coordination among the plurality of distribution zones.

17. The power grid system (100) of claim 1, wherein the distribution zone orchestration indicator indicates at least one of an operational violation or a non-operational violation in the assigned distribution zone (104).

18. 2. The power grid system (100) of claim 1, wherein the adaptive control action is determined based on an adaptive control machine learning model trained on at least one of historical distribution zone operating parameters, simulated distribution zone operating parameters, historical distribution control measurements, simulated distribution control measurements, simulated distribution zone adaptive policies, or historical distribution zone adaptive policies.

19. The distribution zone controller (120) receiving distribution forecast data from at least one of the ADMS (144), a third-party engine, a server, a device, or a website; receiving a distribution zone forecast policy from the advanced distribution management system (144); determining a predictive control action based on the distribution zone operational data and the distribution zone predictive policy; The power grid system (100) of claim 1, further configured:

20. 20. The power grid system (100) of claim 19, wherein the predictive control actions are determined based on a predictive control machine learning model trained on at least one of historical distribution zone operating parameters, simulated distribution zone operating parameters, historical distribution control measurements, simulated distribution control measurements, simulated distribution forecast data, or historical distribution forecast data.

Images