Distributed energy resource management

Abstract

A process for responding to an energy demand event includes identifying an energy demand event and ranking a plurality of distributed energy resources according to a dynamic health status of each distributed energy resource. At least one distributed energy resource is allocated to meet the demand event. An anomaly count of at least one of the at least one distributed energy resource is monitored throughout the energy demand event.

Description

Technical Field

[0001] The present invention relates to the control and scheduling of distributed energy resources, and more particularly, to a system for optimally providing energy from a plurality of distributed energy resources to one or more energy systems in response to an energy demand event. Background Art

[0002] Distributed energy systems utilize power plants (energy sources), such as traditional non-renewable power plants, modern renewable production facilities, or any combination thereof, to generate energy. This energy is distributed to one or more end systems via an energy distribution system. In some cases, such as solar power generation, the amount of power generated by a given facility can vary. In such cases, excess energy over a period of time can be stored in a variety of energy resources, such as battery systems, storage tanks, and electric vehicles. The various resources for storing energy are geographically distributed, with some resources being mobile and others being immobile.

[0003] An energy demand event occurs when insufficient energy is generated to meet demand, or when no energy is generated due to a planned or unplanned event. An energy demand event requires energy to be drawn from one or more stored energy resources in order to supply energy to another location or the overall energy grid. In some systems, multiple energy demand events may occur simultaneously.

[0004] Due to the distributed nature of energy resources, stored energy is geographically distributed and may not be readily available at a particular location (e.g., energy may be stored at one location and a demand event occurs 25 miles away). Additionally, during a demand event, some resources may be more suitable for providing stored energy to some energy systems and less suitable for providing stored energy to other energy systems.

[0005] Therefore, it is desirable to adaptively dispatch and deliver power from multiple distributed energy resources, where the system takes into account energy demand events and the energy capabilities and requirements of the energy resources. Summary of the Invention

[0006] In an exemplary embodiment, a process for responding to an energy demand event includes identifying an energy demand event, ranking a plurality of distributed energy resources according to a dynamic health state of each distributed energy resource, allocating at least one distributed energy resource to satisfy the demand event, and monitoring an anomaly count of at least one of the at least one distributed energy resource throughout the energy demand event.

[0007] In addition to one or more features described herein, ranking a plurality of distributed energy resources includes receiving a set of key performance indicator metrics from each resource, determining a key performance indicator value corresponding to each key performance indicator metric using a key performance indicator determiner, and determining a dynamic health status indicator value corresponding to the key performance indicator value for each key performance indicator metric using a dynamic health status determiner.

[0008] In addition to one or more features described herein, at least one of the key performance indicator determiner and the dynamic health state determiner is a software module local to the corresponding distributed energy resource.

[0009] In addition to one or more features described herein, at least one of the key performance indicator determiner and the dynamic health state determiner is a software module local to the corresponding distributed energy resource that is remote from the corresponding distributed energy resource.

[0010] In addition to one or more features described herein, at least one of the key performance indicator determiner and the dynamic health state determiner is a rule-based determiner.

[0011] In addition to one or more features described herein, at least one of the key performance indicator determiner and the dynamic health state determiner is based at least in part on machine learning, and wherein the machine learning of at least one of the key performance indicator determiner and the dynamic health state determiner is retrained using an output of at least one of the key performance indicator determiner and the dynamic health state determiner.

[0012] In addition to one or more features described herein, each of the key performance indicator determiner and the dynamic health state determiner is based at least in part on machine learning.

[0013] In addition to one or more features described herein, the process also includes determining an overall dynamic health status value based on an average of each key performance indicator dynamic health status value.

[0014] In addition to one or more features described herein, the average is a weighted average.

[0015] In addition to one or more features described herein, at least one of the dynamic health status indicator values ​​is based at least in part on a historical average of key performance indicator values ​​of a corresponding key performance indicator metric.

[0016] In addition to one or more features described herein, allocating at least one distributed energy resource to satisfy a demand event includes applying a throughput versus latency optimization algorithm, wherein the throughput of a resource is the amount of energy provided by the resource and the latency of the resource is the time until delivery of the energy provided by the resource is completed.

[0017] In addition to one or more features described herein, applying throughput versus latency optimization includes evaluating throughput and latency of each of a plurality of distributed energy resources, and allocating at least one distributed energy resource to satisfy a demand event includes allocating an optimal subset of the plurality of distributed energy resources to satisfy the demand event.

[0018] In addition to one or more features described herein, allocating the optimal subset of the plurality of distributed energy resources includes instructing at least one mobile distributed energy resource to move from a first location to a second location.

[0019] In addition to one or more features described herein, monitoring an anomaly count of at least one of the at least one distributed energy resource throughout the energy demand event includes monitoring each key performance indicator, incrementing the anomaly count in response to detecting an anomaly, comparing the anomaly count to a threshold, and disengaging the distributed energy resource from the energy demand event in response to the anomaly count exceeding the threshold.

[0020] In addition to one or more features described herein, the process may also include responding to the end of the energy demand event by discontinuing monitoring of anomaly counts for at least one of the at least one distributed energy resource and disengaging the distributed energy resource from the energy demand event.

[0021] In addition to one or more features described herein, the plurality of distributed energy resources includes a set of mobile distributed energy resources and a set of immobile distributed energy resources.

[0022] In addition to one or more features described herein, the set of mobile distributed energy resources includes at least one vehicle, and wherein the at least one vehicle includes a rechargeable energy storage system and a controller.

[0023] In addition to one or more features described herein, the method includes determining a key performance indicator value corresponding to each key performance indicator metric using a key performance indicator determiner, and determining a dynamic health status indicator value corresponding to the key performance indicator value for each key performance indicator metric using a dynamic health status determiner, and wherein at least one of the key performance indicator determiner and the dynamic health status determiner is a software module of the controller.

[0024] In addition to one or more features described herein, each mobile distributed energy resource in the set of mobile distributed energy resources includes a controller, and wherein each controller includes a corresponding key performance indicator determiner and a corresponding dynamic health state determiner.

[0025] In addition to one or more features described herein, the process also includes identifying at least one parasitic energy demand event, repeating the ranking of the plurality of distributed energy resources based on the dynamic health state of each distributed energy resource, and allocating at least one distributed energy resource to satisfy the at least one parasitic energy demand event. Allocating the at least one distributed energy resource to satisfy the at least one parasitic energy demand event includes identifying a distributed energy resource currently allocated to the energy demand event and reallocating the identified distributed energy resource to one of the at least one parasitic energy demand event.

[0026] The above features and advantages and other features and advantages of the present disclosure will become apparent when the following detailed description is read in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Additional features, advantages, and details appear, by way of example only, in the following detailed description, which refers to the accompanying drawings, in which:

[0028] Figure 1 is a view of a distributed energy resource dispatching system, including a top view of a motor vehicle and a plurality of attached distributed energy resources;

[0029] Figure 2 Describes the high-level processing flow of the resource scheduler for energy demand events;

[0030] Figure 3 Describes the scheduling process operated by the scheduler when an energy demand event occurs;

[0031] Figure 4 Describes an example scheduling algorithm that uses throughput versus latency optimization; and

[0032] Figure 5 A process for monitoring resources engaged to satisfy an energy demand event throughout an energy demand event is described. DETAILED DESCRIPTION

[0033] The following description is merely exemplary in nature and is in no way intended to limit the present disclosure, its application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.

[0034] According to exemplary embodiments, methods, apparatus, and systems are provided for scheduling and implementing energy delivery from distributed energy resources to at least one receiving energy system. To implement scheduling, a scheduler identifies a health status metric, an abstract resource metric, and an external factor metric for each distributed energy resource. A key performance indicator (KPI) is determined for each metric, and a dynamic health status determiner is used to combine the KPIs into a dynamic health status indicator.

[0035] The dynamic health status indicator of each distributed resource is provided to the distributed energy resource scheduler. The dynamic health status indicator can be provided as a single percentile value of all performance indicators of the aggregated resource, or as a table including the performance indicators and the aggregated percentile values. The distributed energy resource scheduler identifies areas of the overall energy distribution system with energy demand and allocates distributed energy resources to meet the demand. In some examples, allocation can include directing one or more distributed energy resources to move from a current location to a new location. In another example, allocation can include identifying a future location of the distributed energy resource and instructing the receiving energy system to prepare to connect to the distributed energy resource at a future time.

[0036] In any example, the distributed energy resource scheduler balances the throughput (amount of energy provided) and latency (time until the provided energy is delivered) of each distributed energy resource based on the key performance indicators of all distributed energy resources, and optimizes the energy delivery from the distributed energy resources to the energy system that needs the resources. It will be understood that the "optimal" solution depends on many tangible and intangible factors. As used herein, optimal, optimum, optimization and any related terms refer to identifying and / or utilizing a system with improved characteristics relative to any identified tangible and intangible factors, and should not be interpreted as being absolutely optimal for every situation.

[0037] The embodiments described herein present numerous advantages and technical effects. Embodiments of the scheduling system provide a context-aware algorithm that efficiently utilizes multiple available distributed energy resources to optimally meet energy demands. This optimization provides cost and load benefits for energy conservation and allocation. Furthermore, the optimization can maintain the battery health of available resources by prioritizing healthier resources and monitoring the use and deployment of resources in a distributed energy resource network.

[0038] These embodiments are not limited to use with any particular vehicle and may be applicable in a variety of environments. For example, distributed energy resources may include vehicles, buildings, battery storage systems, and any number of other mobile or non-mobile energy storage facilities.

[0039] Figure 1 An embodiment of a motor vehicle 10 is shown that includes a body 12 that at least partially defines an occupant compartment 14. The body 12 also supports various vehicle subsystems, including a propulsion system and other subsystems to support the functions of the propulsion system and other vehicle components, such as a braking subsystem, a suspension system, a steering subsystem, a fuel injection subsystem, an exhaust subsystem, etc.

[0040] The vehicle 10 may be an electric vehicle (EV) or a hybrid vehicle. In one embodiment, the vehicle 10 is an electric vehicle that includes at least one electric motor assembly.

[0041] The vehicle 10 includes a battery system 22 that can be electrically connected to electric subsystems, such as vehicle electronics, motors, sensors, etc. The battery system 22 can be configured as a rechargeable energy storage system (RESS). In such an example, the vehicle 10 also includes a controller 24 that is configured to control the battery system 22. The controller 24 can be a single dedicated controller, a general vehicle controller, or multiple controllers distributed throughout the vehicle 10 that operate in coordination with each other to control one or more features of the battery system 22.

[0042] Furthermore, controller 24 is communicatively coupled to remote computer system 130 via communication link 26. Communication link 26 may be wireless (eg, cellular) communication, network-based communication including wired and wireless sub-connections, and / or a direct wired connection.

[0043] The vehicle 10 is one distributed energy resource (resource 120) of the distributed energy system 100. The distributed energy system 100 includes a plurality of distributed energy resources 120, 122, 124, including fixed energy resources 122, such as buildings, energy storage sites, etc., and a plurality of mobile energy resources 124, such as electric vehicles similar to or the same as the vehicle 10, different electric vehicles, and any other mobile energy storage components. The vehicle 10 can be considered an example of a mobile resource 124.

[0044] The remote computer system 130 communicates with each of the assets 120 via bidirectional communication links 26, 126. Included within the remote computer system is a distributed energy resource scheduler (referred to as scheduler 132) that is configured to receive information from each of the assets 120 and respond to incoming energy demands by allocating one or more of the assets 120 to provide energy to meet the demand.

[0045] Continue to refer Figure 1 , Figure 2 There is shown a high level process flow 200 of the scheduler 132. Each resource 120 generates a resource state of health (SOH) metric 210, an abstract resource metric 220, and any available external factor metrics 230. These are collectively referred to as metrics 210, 220, 230.

[0046] The health status metrics 210 may include factors such as discharge rate, average rate of output power, maximum rate of output power, average rate of output voltage, average DC to AC (direct current to alternating current) feedback, number of discharge channels, percentage below threshold, average rate of charge degradation, and average current fluctuation, or any similar metric indicative of the health status of the corresponding resource 120. As used herein, percentage below threshold refers to a threshold value defined by industry standards for DC-AC conversion and may vary according to conventional practice depending on the specific implementation.

[0047] Abstract resource metrics 220 may include the probability of a sufficient charge level, the age of the energy storage system (e.g., a battery) within the resource 120, the number of previous occupancy times of the resource 120, the time since the last service of the resource 120, the fleet charging type, the autonomy level of the resource 120, the number of charging cycles of the resource 120, and any similar metrics.

[0048] Available external factor metrics may include the time of day, the GPS location of the resource 120, the weather at the location of the resource 120, any special conditions applicable to the resource 120 (e.g., within a construction zone, limited range, immovable, etc.), or any similar factors not directly related to the resource 120 itself but that may affect the ability of the resource 120 to provide energy.

[0049] Each factor 210, 220, 230 is synthesized into a key performance indicator using a key performance indicator determiner 250. In some cases, the factors 210, 220, 230 are provided to the remote computing system 130 at the remote server start 240, and the key performance indicator determiner 250 and all subsequent elements of the process flow 200 are located at the remote computing system 130. In other cases, some or all of the resources 120 include a key performance indicator determiner 250 within their own controllers, and the key performance indicators are determined before the factors are provided to the remote computing system 130.

[0050] In some examples, the key performance indicator determiner 250 uses predefined rules for each metric 210, 220, 230 to determine a corresponding pass / fail indication (1=pass, 0=fail) and assigns a corresponding numerical value to the factor 210, 220, 230. In an alternative example, the pass / fail value of the key performance indicator determiner 250 utilizes an AI / machine learning algorithm to determine the key performance indicator for each factor 210, 220, 230, and an optional feedback loop 252 can be used to feed back the output to retrain / update the AI / machine learning model.

[0051] In another example, one or more of the key performance indicator metrics 210 may be percentile values ​​(0%-100%), or similar non-binary values ​​within a preset range, rather than using a pass / fail assessment.

[0052] In yet another example, the KPI metric 210 may be reported as a percentile or non-binary value within a preset range and converted to a binary pass / fail value based on predetermined conditions (e.g., percentile greater than X, non-binary value less than Y, etc.).

[0053] The key performance indicator metrics 210, 220, 230 are then provided to a dynamic health state determiner 260. The dynamic health state determiner 260 determines the dynamic health state of each metric 210, 220, 230 and combines the dynamic health state metrics into an overall dynamic health state of the resource 120. The dynamic health state determiner 260 may be rule-based or utilize an AI / ML feedback loop 262 as shown.

[0054] In an exemplary embodiment, the dynamic health status indicator is a pass / fail value, and the total dynamic health value is the percentile of the dynamic health values ​​that pass. For example, in a resource 120 with ten KPIs, seven of which pass (are assigned a value of "1"), the total dynamic health value is 70%.

[0055] In alternative example embodiments, certain factors 210, 220, 230 may have a weighting constant that is multiplied by the value, thereby increasing or decreasing the impact of the metric on the overall dynamic health.

[0056] In other examples, the dynamic health state of a given resource 120 may be determined based on historically received KPI values ​​(e.g., a threshold percentage of X previous values ​​passed) and / or based on additional external factors or conditions, where the instantaneous pass / fail of a given KPI metric 210, 220, 230 is not itself a determinant of the corresponding dynamic health state.

[0057] After the dynamic health status determiner 260 identifies the health status indicators of the resources 120, the key performance indicators and the dynamic health status indicators are combined into a table, which is provided to the scheduler 132 in the remote computing system 130, and the scheduler 132 uses the table to determine the overall suitability of the corresponding resources 120 based on the corresponding total scores. In some examples, everything before the scheduler 132 can be handled by the resource 120 being analyzed and utilize the remote server starting point 242.

[0058] For example, a table for a backup battery storage device might look like this:

[0059]

[0060]

[0061] The first column represents a factor, the second column provides a pass / fail value for that factor, and the third column provides a dynamic state of health (SoH).The specific thresholds in the second column are application dependent and specific to a given battery backup resource 120.

[0062] Similarly, when the resource 120 is a fuel cell based resource, the key performance indicators may be as follows:

[0063]

[0064] The first column represents the factors, the second column represents the key performance indicator pass / fail values, and the third column represents the resource rating from the dynamic health status determiner 260. In this example, the dynamic health status score is based on the average historical pass / fail rate, including the current pass / fail value of the KPI metric, and is not determined solely by the corresponding current pass / fail value.

[0065] In another example, the resource 120 may be a wind-based resource, and the scheduler 132 information table may be as follows:

[0066]

[0067]

[0068] The first column represents the factor, the second column represents the pass / fail condition for the factor, and the third column represents the resource rating from the dynamic health status determiner 260 .

[0069] Continue to refer Figure 1-2 , Figure 3 The scheduling process 300 is shown as being executed by the scheduler 132 when an energy demand event occurs. For example, an energy demand event occurs when a resource 120 indicates that a certain amount of energy will be required and a currently available resource 120 (e.g., the grid) is unavailable. An energy demand event may occur when the grid is shut down due to a weather event, when locally stored energy resources are insufficient, when the cost of energy from the grid is higher than a desired level, or any similar event.

[0070] When an energy demand event occurs, the remote computing system 130 initiates the scheduling process 300 at a start block 310. Initially, the scheduling process 300 dynamically maps the locations of available distributed energy resources 120, including vehicles, buildings, battery storage facilities, etc., in a mapping step 320 by communicating with each resource 120 and determining the current location of that resource 120. In some examples, resources 120 that are known to be immovable (e.g., building-based energy storage systems) may be predetermined, and the locations are not required for the mapping step 320.

[0071] In some examples, mapping step 320 may be limited to resources 120 that are known or expected to be within a particular range of demand events. In other examples, mapping step 320 may be extended to the entire network of resources 120.

[0072] Once all resources 120 have been mapped, process 300 prioritizes (sorts) the available resources 120 based on their total dynamic health values ​​from key performance indicator step 330. In one example, the sorting is performed from low (lowest total dynamic health indicator) to high (highest total dynamic health indicator), where these values ​​are total dynamic health values ​​from a provided table and are based on a set number of recent occupancy. As used herein, occupancy of a particular resource refers to the use of that particular resource 120 in response to the occurrence of a demand event.

[0073] Once the available resources 120 are ranked, process 300 uses an occupancy demand function within the dynamic region of a demand event within a given time period during a determine demand step 340. The occupancy function determines the estimated capacity of each resource 120 within the demand event range and the approximate energy demand required for the demand event. The approximate energy demand for a demand event includes an estimated amount of energy required and an estimated time within which the energy will be required. In the case of using an algorithm to optimize energy delivery, the estimated demand includes an estimated latency requirement (e.g., the demand must be met within a specified time period).

[0074] In a comparison check 350, the demand is compared to the estimated capacity of all available resources 120. When the demand is less than the capacity, the process 300 allocates a higher ranked resource 120 to satisfy the demand event 410 ( Figure 4 ), and the lower-scoring resources 120 are moved to a backup buffer in a provide power step 370. In some cases, such as where the resources 120 include mobile resources 124, the system 300 is configured to instruct the automated system within the mobile resources 124 to move the resources 120 to a location for delivering stored energy to meet the demand event 410. This may include disengaging the resources 120 from a source 420, moving the resources 120, and engaging the resources 120 with the source 420 experiencing the demand event 410. Similarly, when the mobile resources 124 do not include automated driving, the system 300 may predict typical movements of the mobile resources 124 (e.g., a vehicle expected to move from a home location to a work location during a workday) and account for the natural movements of the mobile resources 124.

[0075] When demand exceeds estimated capacity, process 300 creates a plan at step 360 to increase available capacity for the next time period (e.g., hour, day, etc.). The plan may involve moving mobile resources 124, storing excess energy at one or more fixed resources 122, and transferring energy to a source 420 experiencing a demand event 410, or any similar action.

[0076] Continue to refer Figure 3 , Figure 4An example scheduling algorithm 400 is shown that uses throughput versus latency optimization to optimize energy delivery to meet energy demand events 410. The throughput of a given resource 120 is the amount of energy that can be delivered from the resource 120, while the latency of the resource 120 is the time it takes to deliver that energy to a given demand event 410. In some cases, such as an immovable resource 120 (e.g., a battery backup system) that is already connected at a demand event 410, the latency will be limited to the time required to release the energy. In other cases, such as an electric vehicle 10 being moved to provide power at an alternate location, the latency will include both the time to move the resource 120 into position so that the resource can provide energy and the time required to release the energy.

[0077] Figure 4 The example planning algorithm 400 provides an optimal plan to respond to a plurality of different demand events 410 and to continue providing resources 120 to store energy generated by different sources 420 throughout an energy distribution network 430 according to a previously determined ranking of the resources 120. Because the planning algorithm 400 utilizes constraints requiring that throughput meet a predetermined amount and latency be below a predetermined amount, the approach is referred to as constrained solving of an optimization problem.

[0078] After a plan to meet the demand has been built (step 360 ) or meeting the demand has begun (step 370 ), the scheduler 132 occupies the utilized resource 120 by communicating with the resource and requesting occupancy, and then ends the process at an end step 380 .

[0079] Continue to refer Figure 1-4 , Figure 5 A process 500 is shown for monitoring the resources 120 that have been occupied to meet the energy demand event 410 during the entire energy demand event 410. The process begins at a start block 510, and in a step 520 of monitoring KPI anomalies, the monitoring system within the resource 120 participates in any anomalies within the energy release of the monitoring resource 120. An anomaly is a deviation from the expected operation of one or more key performance indicator metrics 210, 220, 230 of the resource 120. When an anomaly occurs, the anomaly is assigned a weight, which is then added to the total anomaly value of the anomaly in the calculation anomaly score step 530. In one example, all types of anomalies are assigned a static value (e.g., 1), and the total anomaly score operates as a counter, counting the number of anomalies that have occurred. In other examples, the anomaly can have different values ​​depending on the type of anomaly, and the total anomaly score is the sum of all values ​​that have occurred.

[0080] Once the total anomaly score is determined at step 530, the total anomaly score is compared to a threshold score at comparison check 540. When the score does not exceed the threshold, process 500 continues to engage and process 500 returns to step 520.

[0081] Alternatively, when the total anomaly score exceeds a threshold, process 500 determines that resource 120 is no longer sufficient to satisfy energy demand event 410 and detaches resource 120 at detach step 550. At report anomaly to cloud step 560, the detachment is reported back to remote computer system 130, and scheduler 132 can reallocate a new resource 120 to satisfy ongoing energy demand event 410. Following the reporting, monitoring process 500 ends at end step 570.

[0082] When the energy demand event 410 ends naturally, either due to the energy demand being met (e.g., source 420 being fully charged), a condition causing the energy demand to cease (e.g., a faulted power line being repaired), or due to any other external reason, interruption 580 interrupts the monitoring process and provides normal resource 120 disengagement.

[0083] By using the above-described systems and processes, remote computer system 130 is able to continuously control and meet energy demands during demand events 410 and balance the throughput and latency of the various resources 120 available to meet the demand.

[0084] The terms "a" and "an" do not indicate a limitation of quantity, but rather indicate the presence of at least one of the referenced item. The term "or" means "and / or" unless the context clearly indicates otherwise. References to "an aspect" throughout this specification mean that a particular element (e.g., feature, structure, step, or characteristic) described in conjunction with that aspect is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in various aspects.

[0085] When an element such as a layer, film, region, or substrate is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present. In contrast, when an element is referred to as being "directly on" another element, there are no intervening elements present.

[0086] Unless otherwise indicated herein, all test standards are the most recent standards in effect as of the filing date of this application or, if priority is claimed, the filing date of the earliest priority application in which the test standards appear.

[0087] Unless defined otherwise, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0088] Although the above disclosure has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope thereof. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the present disclosure without departing from the essential scope of the present disclosure. Therefore, it is intended that the present disclosure is not limited to the particular embodiments disclosed, but is intended to include all embodiments falling within its scope.

Claims

1. A process for responding to an energy demand event, comprising: Identify energy demand events; ranking the plurality of distributed energy resources according to a dynamic health status of each distributed energy resource; allocating at least one distributed energy resource to satisfy an energy demand event; as well as An anomaly count of at least one of the at least one distributed energy resource is monitored throughout the energy demand event.

2. The process of claim 1, wherein: Ranking the plurality of distributed energy resources includes receiving a set of key performance indicator metrics from each resource, determining a key performance indicator value corresponding to each key performance indicator metric using a key performance indicator determiner, and determining a dynamic health status indicator value corresponding to the key performance indicator value of each key performance indicator metric using a dynamic health status determiner.

3. The process of claim 2, wherein: At least one of the key performance indicator determiner and the dynamic health status determiner is a software module local to the corresponding distributed energy resource.

4. The process of claim 2, wherein: At least one of the key performance indicator determiner and the dynamic health status determiner is one of a software module and a rule-based determiner that is local to the corresponding distributed energy resource and is remote from the corresponding distributed energy resource.

5. The process of claim 2, wherein: At least one of the key performance indicator determiner and the dynamic health state determiner is based at least in part on machine learning, and wherein the output of at least one of the key performance indicator determiner and the dynamic health state determiner is used to retrain the machine learning of at least one of the key performance indicator determiner and the dynamic health state determiner, and optionally wherein each of the key performance indicator determiner and the dynamic health state determiner is based at least in part on machine learning.

6. The process of claim 1, wherein: Allocating at least one distributed energy resource to satisfy the energy demand event includes applying a throughput versus latency optimization algorithm, where the throughput of a resource is the amount of energy provided by the resource and the latency of the resource is the time until delivery of the energy provided by the resource is completed.

7. The process of claim 6, wherein: Applying throughput versus latency optimization includes evaluating throughput and latency of each of the plurality of distributed energy resources, and allocating at least one distributed energy resource to satisfy the energy demand event includes allocating an optimal subset of the plurality of distributed energy resources to satisfy the energy demand event.

8. The process of claim 6, wherein: Allocating the optimal subset of the plurality of distributed energy resources includes instructing at least one mobile distributed energy resource to move from a first location to a second location.

9. The process of claim 6, wherein: Monitoring an anomaly count of at least one of the at least one distributed energy resource throughout the energy demand event includes monitoring each key performance indicator, incrementing the anomaly count in response to detecting an anomaly, comparing the anomaly count to a threshold, and disengaging the distributed energy resource from the energy demand event in response to the anomaly count exceeding the threshold.

10. The process of claim 9, further comprising responding to the end of the energy demand event by discontinuing monitoring of anomaly counts for at least one of the at least one distributed energy resource and disengaging the distributed energy resource from the energy demand event.

Images