Interoperable communication of energy assets using digital twins

Abstract

Methods for providing communication for an energy asset and corresponding systems and computer-readable mediums. A method includes receiving (702) specification documents (312) for energy assets (324) and creating (704) hierarchical specification representations (314) corresponding to the energy assets (324) from the specification documents (312). The method includes creating (706) Thing Models (316) corresponding to the energy assets (324). The method includes performing a discovery process (708) to identify the energy asset (324) and creating (710) an initial digital twin of each energy asset (324) as a partial Thing Description (328). The method includes creating (712) a semantically mapped Thing Description and exposing (714) the semantically mapped Thing Description (332) to at least one application (202, 204) as a digital twin of the corresponding energy asset (324). The method includes acting (716) as a gateway between the at least one application (202, 204) and the energy assets (324) using the semantically mapped Thing Descriptions (332).

Description

INTEROPERABLE COMMUNICATION OF ENERGY ASSETS USING DIGITAL TWINSTECHNICAL FIELD

[0001] The present disclosure is directed, in general, to systems and methods for communication between energy assets, including energy sources and equipment, and applications that monitor or control them.BACKGROUND OF THE DISCLOSURE

[0002] As local and national energy infrastructures become more complex, it is increasingly difficult to assess and efficiently utilize energy assets on both micro and macro scales. There are significant challenges of interoperability and common representation for brownfield energy assets, including but not limited to distributed energy resources (DERs), behind the meter (BTM) assets, and electric vehicle supply equipment (EVSE). In the current context, it takes considerable amount of engineering effort to discover, represent and manage assets for the brownfield deployment of energy assets. Typically, these assets communicate using different protocols and have manually performed, fixed mapping to control algorithms and monitoring systems. This makes it extremely tedious and complex for new energy applications such as peak load shaving, load shifting, dynamic voltage control, etc. to have a pluggable design such that they can be mapped and utilize the existing assets. Further, every implementation is a point solution and needs to be reengineered for new applications and customers. Improved systems are desirable.SUMMARY OF THE DISCLOSURE

[0003] Various disclosed embodiments include methods for providing communication for an energy asset and corresponding systems and computer-readable mediums. A method includes receiving a specification document for energy assets and creating a hierarchical specification representation corresponding to the energy assets from the specification document. The method includes creating Thing Models corresponding to the energy assets. The method includes performing a discovery process to identify the energy asset and creating an initial digital twin of the energy asset as a partial Thing Description. The method includes creating a semantically mapped Thing Description and exposing the semantically mapped Thing Description to at least one application as a digital twin of the energy asset. The method includes acting as a gateway between the application and the energy asset using the semantically mapped Thing Description.

[0004] In various embodiments, the Thing Model is created based on one of the original specification or the hierarchical specification representation. In various embodiments, the discovery process includes identifying the energy asset as connected to or communicable with the system.

[0005] In various embodiments, the discovery process includes identifying asset properties of the energy asset. In various embodiments, creating an initial digital twin of the energy asset is based on the Thing Model.

[0006] In various embodiments, the hierarchical specification representation conforms to the IEEE 2030.5 Standard for Smart Energy Profile Application Protocol specification.

[0007] In various embodiments, the Thing Model represents the class of the energy asset, and the Thing Model is stored in a library Thing Models corresponding to different asset classes. In various embodiments, the system creates the semantically mapped Thing Description by using a large language model to map the energy asset and properties of the energy asset to the hierarchical specification representation.

[0008] The foregoing has outlined rather broadly the features and technical advantages of the present disclosure so that those skilled in the art may better understand the detaileddescription that follows. Additional features and advantages of the disclosure will be described hereinafter that form the subject of the claims. Those skilled in the art will appreciate that they may readily use the conception and the specific embodiment disclosed as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure. Those skilled in the art will also realize that such equivalent constructions do not depart from the spirit and scope of the disclosure in its broadest form.

[0009] Before undertaking the DETAILED DESCRIPTION below, it may be advantageous to set forth definitions of certain words or phrases used throughout this patent document: the terms “include” and “comprise,” as well as derivatives thereof, mean inclusion without limitation; the term “or” is inclusive, meaning and / or; the phrases “associated with” and “associated therewith,” as well as derivatives thereof, may mean to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, or the like; and the term “controller” means any device, system or part thereof that controls at least one operation, whether such a device is implemented in hardware, firmware, software or some combination of at least two of the same. It should be noted that the functionality associated with any particular controller may be centralized or distributed, whether locally or remotely. Definitions for certain words and phrases are provided throughout this patent document, and those of ordinary skill in the art will understand that such definitions apply in many, if not most, instances to prior as well as future uses of such defined words and phrases. While some terms may include a wide variety of embodiments, the appended claims may expressly limit these terms to specific embodiments.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] For a more complete understanding of the present disclosure, and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, wherein like numbers designate like objects, and in which:

[0011] FIG. 1 illustrates a block diagram of a computer system in which an embodiment can be implemented;

[0012] FIG. 2 illustrates an example of an energy system in accordance with disclosed embodiments;

[0013] FIG. 3 illustrates an example of a process for mapping energy assets to a standard specification, in accordance with disclosed embodiments;

[0014] FIG. 4 illustrates an example of one such partial representation of a hierarchical specification representation in accordance with disclosed embodiments;

[0015] FIG. 5 illustrates an example of a snippet of a Thing Model in accordance with disclosed embodiments;

[0016] FIG. 6 illustrates an example of a snippet of a semantically mapped Thing Description in accordance with disclosed embodiments; and

[0017] FIG.7 illustrates a flowchart of a process in accordance with disclosed embodiments.DETAILED DESCRIPTION

[0018] FIGS. 1 through 7, discussed below, and the various embodiments used to describe the principles of the present disclosure in this patent document are by way of illustration only and should not be construed in any way to limit the scope of the disclosure. Those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged device. The numerous innovative teachings of the present application will be described with reference to exemplary non-limiting embodiments.

[0019] The current generation of energy asset modeling solutions do not take a comprehensive approach to modeling and communication for brownfield assets. Further, the solutions are not automated and require high engineering effort. There are few existing solutions to automate the modeling process, and each of these have significant shortcomings.

[0020] To address the current problems related to energy assets that cannot be effectively assessed, managed, or integrated, disclosed embodiments include an automation system that can expose energy assets to a standard specification model and that can be consumed by energy system applications in an interoperable fashion. Disclosed embodiments include systems and methods to automatically discover, represent, map, and communicate with energy assets using well-known specifications such as IEEE 2030.5. Disclosed techniques enable the assets to be managed and monitored by energy system applications which can apply standard APIs to communicate without regard to the underlying devices and protocols and their implementation details.

[0021] Various embodiments can discover and autonomously create digital twins or thing descriptions (TD) of the assets using Web of Things (WoT) standards to abstract away the underlying protocols that the assets use. Various embodiments can manage the discovery and semantic representation of assets using a standard specification such as IEEE 2030.5.

[0022] Disclosed embodiments include processes and techniques for using large language models (LLMs) to match Thing Descriptions (TD) to the standard specifications.

[0023] FIG. 1 illustrates a block diagram of a computer system 100 in which an embodiment can be implemented, for example as a computer system particularly configured by software or otherwise to perform the processes as described herein, and in particular as each one of a plurality of interconnected and communicating systems as described herein to discover, manage, and interact with energy assets. The computer system depicted includes a processor 102 connected to a level two cache / bridge 104, which is connected in turn to a local system bus 106. Local system bus 106 may be, for example, a peripheral component interconnect (PCI) architecture bus. Also connected to local system bus in the depicted example are a main memory 108 and a graphics adapter 110. The graphics adapter 110 may be connected to display 111.

[0024] Other peripherals, such as local area network (LAN) / Wide Area Network / Wireless (e.g. WiFi) adapter 112, may also be connected to local system bus 106. Expansion bus interface 114 connects local system bus 106 to input / output (I / O) bus 116. I / O bus 116 is connected to keyboard / mouse adapter 118, disk controller 120, and I / O adapter 122. Disk controller 120 can be connected to a storage 126, which can be any suitable machine usable or machine readable storage medium, including but not limited to nonvolatile, hard-coded type mediums such as read only memories (ROMs) or erasable, electrically programmable read only memories (EEPROMs), magnetic tape storage, and user-recordable type mediums such as floppy disks, hard disk drives and compact disk read only memories (CD-ROMs) or digital versatile disks (DVDs), and other known optical, electrical, or magnetic storage devices.

[0025] Storage 126 can store any data that is useful or necessary for performing processes as described herein. This can include, for example, program code 152, energy applications 154, interface adapters 156, application programming interfaces (APIs) 158, specification maps and representations 160, specifications and specification documents 162, Thing Models 164, Thing Descriptions 166, large language models 168, transformers 170, asset mapping rules 172, and other data 174.

[0026] Also connected to I / O bus 116 in the example shown is audio adapter 124, to which speakers (not shown) may be connected for playing sounds. Keyboard / mouse adapter 118provides a connection for a pointing device (not shown), such as a mouse, trackball, trackpointer, touchscreen, etc.

[0027] Those of ordinary skill in the art will appreciate that the hardware depicted in Figure 1 may vary for particular implementations. For example, other peripheral devices, such as an optical disk drive and the like, also may be used in addition or in place of the hardware depicted. The depicted example is provided for the purpose of explanation only and is not meant to imply architectural limitations with respect to the present disclosure.

[0028] A computer system in accordance with an embodiment of the present disclosure includes an operating system employing a graphical user interface. The operating system permits multiple display windows to be presented in the graphical user interface simultaneously, with each display window providing an interface to a different application or to a different instance of the same application. A cursor in the graphical user interface may be manipulated by a user through the pointing device. The position of the cursor may be changed and / or an event, such as clicking a mouse button, generated to actuate a desired response.

[0029] One of various commercial operating systems, such as a version of Microsoft Windows™, a product of Microsoft Corporation located in Redmond, Wash, may be employed if suitably modified. The operating system is modified or created in accordance with the present disclosure as described.

[0030] LAN / WAN / Wireless adapter 112 can be connected to a network 130 (not a part of computer system 100), which can be any public or private computer system network or combination of networks, as known to those of skill in the art, including the Internet. Computer system 100 can communicate over network 130 with server system 140, which is also not part of computer system 100, but can be implemented, for example, as a separate computer system 100.

[0031] FIG. 2 illustrates an example of an energy system 200 in accordance with disclosed embodiments. System 200 is an interoperable system where assets 240, both brownfield and greenfield, are abstracted by and communicate via a gateway system 210 that allowsenergy applications residing on the edge, such as on-premises applications 202a and 202b (together, applications 202), and energy applications residing in the cloud, such as cloud applications 204a and 204b (together, applications 204), to model and communicate with the assets in a flexible manner with minimal engineering cost.

[0032] Gateway 210 can include a plurality of device interface adapters 214, both physical and software / logical, that interface with energy assets 240 using any number of device interfaces. The device interface adapters 214 can communicate with energy assets using protocols such as (by way of example and not limitation) Modbus, SunSpec Modbus, OPC- UA, BACnet, OCPP, Matter, and IEEE 2030.5. Device interface adapters 214 can convert each of these protocols to a common format and interface, such as that described by the Web of Things (WoT) Architecture and Description by the World Wide Web Consortium (W3C) and found, at time of filing, at w3.org. Gateway 210 can be implemented, for example using one or more computer systems 100.

[0033] Gateway 210 can implement a model adapter API 212 to communicate between the common format, such as WoT, and each of the applications 202 and 204.

[0034] Assets 240 can include, but are not limited to, asset types such as distributed energy resources (DERs), industrial resources and consumers, commercial resources and consumers, EV chargers and similar consumers, residential resources and consumers, and others. Increasingly, a given type of energy asset can be, at different times, an energy producer / resource, an energy consumer, or both.

[0035] FIG. 3 illustrates an example of a process 300 for mapping energy assets to a standard specification, in accordance with disclosed embodiments. This mapping can then be utilized to generate the bindings needed for interoperable communication with the energy management applications.

[0036] In the process of FIG. 3, at 310, the system can create a hierarchical specification representation of an energy asset. This can be a specification map that can be used by different consuming applications and is populated with specification tokens and theircorresponding text and type. Specification tokens refer to the properties of the information model describing the specification.

[0037] FIG. 4 illustrates an example of one such partial representation of a hierarchical specification representation 400 for mapping in accordance with disclosed embodiments, that conforms to the IEEE 2030.5 Standard for Smart Energy Profile Application Protocol specification. The IEEE 2030.5 consists of function sets for the asset function categorization and within which there is a hierarchy of properties.

[0038] To create the representation illustrated in FIG. 4, at 310, the computer system employs a domain specific parser that converts the specification document 312 for a given asset 324, as may be provided as xml, xsd, json, pdf, or any other textual or other form, to a hierarchical representation 314 of the tokens and the associated text and types.

[0039] The computer system also creates Thing Models 316, as described by the WoT Architecture and Description, of each asset 324 based on the original specification or the hierarchical specification representation. Thing Models 316 represent classes of assets 324 that the system will discover and represent as digital twins. In order to create an accurate digital twin as TD representation of the assets that can be integrated with energy applications, the computer system creates and maintains a library of Thing Model templates for different classes of manufactures and device types that can be instantiated for individual devices.

[0040] FIG. 5 illustrates an example of a snippet of a Thing Model 500 in accordance with disclosed embodiments, in this example for a Modbus-based asset.

[0041] Returning to the process of FIG. 3, at 320, the computer system performs asset discovery and partial digital twin creation.

[0042] To discover assets 324 and their properties, the system uses protocol-specific probes that query the available properties of assets 324 for a range of locations and addresses. For example, SunSpec Modbus assets have the notion of registers. For such registers, there are well-known base addresses, e.g., starting at 400001 and then using offsets to find the next locations. The system queries these locations and collects a list ofavailable asset properties. Asset properties can include such information as asset identification, asset type, asset class, asset model, asset manufacturer information, asset capabilities, asset resources, asset configuration, and other information related to or defining the asset.

[0043] Based on the discovered asset properties such as class and manufacturer information of assets 324, and combining those with protocol specifications 326 and the Thing Model templates 316, the system instantiates and create asset-specific digital twins as partial Thing Descriptions 328. However, these TDs 328 are incomplete and do not have required asset classification based on the standard specification (e.g. a standard such as IEEE 2030.5 to transform all the other protocols to a common one) required by consuming applications. The system populates this information in the next step.

[0044] At 330, the system completes the partial Thing Descriptions 328 to created semantically mapped asset Thing Descriptions 332. To do so, the system semantically maps the assets 324 and their properties to the transformed standard specification represented as the hierarchical representation 314. For this purpose, the system can use one or more LLM-based encoder-decoder transformers 334, which can include pre-trained large language models such as RoBERTa , Llama 2, or GPT-4 based on encoder-decoder transformers. The system can trade-off using one model over the other based on computation resource availability and the required accuracy, and the models can be finetuned for a specific use-case over a period of time using the feedback data from the asset matching.

[0045] To produce the semantically mapped asset Thing Descriptions 332, which can be used as digital twins of the respective assets, the system starts with the list of asset properties and corresponding text for protocol description stored in the partial Thing Description 328. This information is fed into the LLM transformer 334. The LLM transformer 334 is trained to output the specification token that most closely matches the partial thing description 328 using asset mapping rules 336. The fields for the Thing Description 332 are then populated with additional tags (@type). Optionally, a user can inspect the populated Thing Description and provide feedback as user input 338 if anydiscrepancies are observed. The finalized semantically mapped TD 332 is used to populate and update the asset mapping rules 336 which are used for finetuning and refining the LLM transformer 334.

[0046] FIG. 6 illustrates an example of a snippet of a semantically mapped Thing Description 600 including asset property classifications and tags in accordance with disclosed embodiments.

[0047] The semantically mapped Thing Description 332 can be stored in asset repositories 344 for future use or can be consumed by energy applications 342 to communicate with the assets 324 using standard APIs. The underlying Web of Things implementation ensures that the bindings are available for each of the assets. It also ensures that the exposed APIs abstract out the implementation details. In other words, an energy storage device from Vendor A can be treated the same as an energy storage device from VendorN from an application perspective.

[0048] FIG. 7 illustrates a flowchart of a process 700 in accordance with disclosed embodiments, that can be performed by one or more computer systems 100 as disclosed herein, referred to generically as the “system.” The various actions described below can be performed using one or more of the processes described above.

[0049] At 702, the system receives a specification document for energy assets. “Receiving,” as used herein, can include loading from storage, receiving from another device or process, receiving via an interaction with a user, and otherwise. Such as specification document may, for example, describe functionalities of asset classes.

[0050] At 704, the system creates a hierarchical specification representation corresponding to the energy assets from the specification document.

[0051] At 706, the system creates Thing Models corresponding to the energy assets. This can be done based on the original specification or the hierarchical specification representation.

[0052] At 708, the system performs a discovery process to identify the energy asset. That is, the system discovers an energy asset that is connected to or communicable with the system that corresponds to the previously-received specification document or a Thing Model; this is the case where the system maintains a library of Thing Models for various assets and discovers a corresponding asset at a later time. The discovery process can include identifying asset properties of the asset.

[0053] At 710, the system creates an initial digital twin of the asset as a partial Thing Description. This can be based on the Thing Model.

[0054] At 712, the system creates a semantically mapped Thing Description based on the partial Thing Description and the hierarchical specification representation corresponding to the energy asset.

[0055] At 714, the system exposes the semantically mapped Thing Description to other applications and devices as a digital twin of the asset. The digital twin of the asset is usable by the other applications and devices to communicate with and control the asset, for example as the model adapter 212 of gateway 210.

[0056] At 716, the system uses the digital twin of the asset (or the semantically mapped Thing Description) to act as a gateway between the other applications and devices and the asset.

[0057] Disclosed embodiments provide significant technical advantages over other systems. Disclosed embodiments can automatically create semantically mapped asset digital twins as semantically mapped Thing Descriptions 332. Disclosed embodiments can leverage Web of Things Thing Descriptions as the representation for semantically mapped digital twins. TD offers semantics for representing each asset property as an element from standard specification. By using specifications such as IEEE 2030.5 for such representations, the digital twins / TDs can be easily understood and consumed by energy applications without knowing intricacies of the protocol implementation. Other protocols, such as IEC 61850, are used in other implementations. One great advantage of using suchan approach is the automatic bindings for the known protocols, provided by Web of Things implementation, and providing a reusable, cost-effective, and efficient solution.

[0058] Another distinct advantage is the process for autonomous asset mapping. The generalizable and repeatable processes disclosed herein can automates the process of discovery, representation, and mapping of assets to a common standard specification. These processes integrate several steps to generate a semantically mapped digital twin of energy assets and significantly increases speed and reduces the effort of other approaches.

[0059] Another distinct advantage is provided by the use of LLM-based specification matching for digital twin assets. The processes disclosed herein provide an intelligent process using large language models (LLMs) for matching Thing Description properties to a common standard specification. The technique is highly accurate in matching compared to other techniques such as fuzzy logic and Levenshtein distance-based approaches.

[0060] Of course, those of skill in the art will recognize that, unless specifically indicated or required by the sequence of operations, certain steps in the processes described above may be omitted, performed concurrently or sequentially, or performed in a different order.

[0061] Those skilled in the art will recognize that, for simplicity and clarity, the full structure and operation of all computer systems suitable for use with the present disclosure is not being depicted or described herein. Instead, only so much of a computer system as is unique to the present disclosure or necessary for an understanding of the present disclosure is depicted and described. The remainder of the construction and operation of computer system 100 may conform to any of the various current implementations and practices known in the art.

[0062] It is important to note that while the disclosure includes a description in the context of a fully functional system, those skilled in the art will appreciate that at least portions of the mechanism of the present disclosure are capable of being distributed in the form of instructions contained within a machine-usable, computer-usable, or computer-readable medium in any of a variety of forms, and that the present disclosure applies equally regardless of the particular type of instruction or signal bearing medium or storage mediumutilized to actually carry out the distribution. Examples of machine usable / readable or computer usable / readable mediums include: nonvolatile, hard-coded type mediums such as read only memories (ROMs) or erasable, electrically programmable read only memories (EEPROMs), and user-recordable type mediums such as floppy disks, hard disk drives and compact disk read only memories (CD-ROMs) or digital versatile disks (DVDs).

[0063] Although an exemplary embodiment of the present disclosure has been described in detail, those skilled in the art will understand that various changes, substitutions, variations, and improvements disclosed herein may be made without departing from the spirit and scope of the disclosure in its broadest form.

[0064] None of the description in the present application should be read as implying that any particular element, step, or function is an essential element which must be included in the claim scope: the scope of patented subject matter is defined only by the allowed claims. Moreover, none of these claims are intended to invoke 35 USC §112(f) unless the exact words "means for" are followed by a participle. The use of terms such as (but not limited to) “mechanism,” “module,” “device,” “unit,” “component,” “element,” “member,” “apparatus,” “machine,” “system,” “processor,” or “controller,” within a claim is understood and intended to refer to structures known to those skilled in the relevant art, as further modified or enhanced by the features of the claims themselves, and is not intended to invoke 35 U.S.C. §112(f).

[0065] The following documents are incorporated by reference:• Quinn, C., Shabestari, A. Z., Misic, T., Gilani, S., Litoiu, M., & McArthur, J. J. (2020). Building automation system-BIM integration using a linked data structure. Automation in Construction, 118, 103257.• Demianenko, M., & De Gaetani, C. I. (2021). A procedure for automating energy analyses in the BIM context exploiting artificial neural networks and transfer learning technique. Energies, 14(10), 2956.Chen, S., Ebe, F., Morris, J., Lorenz, H., Kondzialka, C., & Heilscher, G. (2022). Implementation and Test of an IEC 61850-Based Automation Framework for theAutomated Data Model Integration of DES (ADMID) into DSO SCAD A. Energies, 15(4), 1552.

Claims

WHAT IS CLAIMED IS:

1. A method (700) for providing communication for an energy asset (324), the method performed by a computer system (100) and comprising: receiving (702) a specification document (312) for an energy asset (324); creating (704) a hierarchical specification representation (314) corresponding to the energy asset (324) from the specification document (312); creating (706) a Thing Model (316) corresponding to the energy asset (324); performing a discovery process (708) to identify the energy asset (324); creating (710) an initial digital twin of the energy asset (324) as a partial Thing Description (328); creating (712) a semantically mapped Thing Description; exposing (714) the semantically mapped Thing Description (332) to at least one application (202, 204) as a digital twin of the energy asset (324); and acting (716) as a gateway between the at least one application (202, 204) and the energy asset (324) using the semantically mapped Thing Description (332).

2. The method of claim 1, wherein the Thing Model (316) is created based on one of the specification document (312) or the hierarchical specification representation (314).

3. The method of claim 1, wherein the discovery process (708) includes identifying the energy asset (324) as connected to or communicable with the computer system (100).

4. The method of claim 1, wherein the discovery process (708) includes identifying asset properties of the energy asset (324).

5. The method of claim 1, wherein creating (710) an initial digital twin of the energy asset (324) is based on the Thing Model (316).

6. The method of claim 1, wherein the hierarchical specification representation (314). conforms to the IEEE 2030.5 Standard for Smart Energy Profile Application Protocol specification.

7. The method of claim 1 , wherein the Thing Model (316) represents the class of the energy asset (324), and the Thing Model (316) is stored in a library of Thing Models (316) corresponding to different asset classes.

8. The method of claim 1, wherein the system creates the semantically mapped Thing Description (332) by using a large language model to map the energy asset (324) and properties of the energy asset (324) to the hierarchical specification representation (314).

9. A computer system (100) comprising: a processor (102); and an accessible memory (108), the computer system (100) particularly configured to perform a process (700) as in any of claims 1-8.

10. A non-transitory computer-readable medium (126) encoded with executable instructions (152) that, when executed, cause one or more computer systems (100) to perform a process (700) as in any of claims 1-8.

Images