Systems and methods for predicting one or more no-power conditions for a plurality of wind energy sites

Abstract

Provided are computer-implemented methods and systems for determining one or more no- power conditions for a plurality of wind energy sites, including: receiving a set of wind energy site characteristics for each wind energy site in the plurality of wind energy sites; receiving one or more weather data points from one or more weather data sources; simulating for each wind energy site in the plurality of wind energy sites, a digital representation of the wind energy site to produce a power generation schedule for the wind energy site; aggregating the power generation schedules for each wind energy site to produce an aggregate wind energy portfolio power generation schedule; determining one or more first time periods in which the aggregate wind energy portfolio power generation schedule indicates zero power generation; and determining a total number of hours corresponding to the one or more first time periods.

Description

TITLE: SYSTEMS AND METHODS FOR PREDICTING ONE OR MORE NOPOWER CONDITIONS FOR A PLURALITY OF WIND ENERGY SITESCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims priority to US Provisional Application 63 / 688,005 filed August 28th, 2024 the entire contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The present invention relates to computer-implemented systems and methods for simulating and analyzing energy generation projects, and more specifically, to analyzing a wind energy generation project using an wind energy site power model.BACKGROUND

[0003] In recent years, Canada and other countries have been decreasing their reliance on fossil fuels for energy generation. Correspondingly, the demand for renewable energy sources and the amount of energy generated through renewable sources has increased. This shift toward renewable energy sources has many environmental benefits, including reducing the effects of climate change. The demand for renewable energy is expected to continue growing.

[0004] One such renewable energy source is wind energy, which can be generated at wind energy sites. Wind energy sites are collections of wind turbines; these turbines are designed to generate energy mechanically, using the rotation of a rotor caused by wind to turn an electric generator.

[0005] However, wind energy sites may generate energy less reliably and consistently than other energy generation methods, including traditional methodsthat use fossil fuels. Wind turbines rely on meteorological conditions to supply sufficient levels of wind to rotate the rotor and generate power. When meteorological conditions are calm or lack wind, wind turbines may not generate energy, leading to potential energy outages for customers and losses in revenue for wind energy site operators.

[0006] It is therefore advantageous for wind energy site operators or developers to be able to analyze the viability of wind energy development projects to ascertain or predict favorable locations and times for energy generation, and to analyze the financial viability of a potential wind energy development project.

[0007] Conventional software systems for analysis of wind energy site energy data may produce outputs including power output, usage, grid output, wind speed at hub height, energy production, capital cost recovery, and profit. Conventional software systems may analyze different wind energy site scenarios including location, operations / maintenance, capital cost, size, and wind turbine characteristics, etc.

[0008] The simulation and analysis of wind energy projects using simulation software and models is necessarily a computer-based problem. The use of models to perform the simulation, and as well, to enable users to execute simulations for multiple scenarios, requires significant computer power.

[0009] Conventional systems do not provide models that can analyze a wind energy portfolio (i.e. including more than one location) to generate recommendations based on the number of low power conditions.

[0010] There remains a need for improved systems and methods directed to analyzing the energy generation capabilities and financial viability of wind energy projects, including networks of wind energy projects.SUMMARY

[0011] Provided herein are systems and methods for processing sensor information from one or more sensors, and other sources of meteorological information, in order to generate predictions related to wind energy site performance. This may include one or more machine learning models. These models support wind energy site diversity analysis.

[0012] The analysis of wind energy site energy data is necessarily a computer- based problem based on the nature of simulation including simulation using a wind energy site power model, the volume of data required, the incorporation of digital sensor devices that monitor the performance of individual wind generators within a wind energy site as well as other sources of digital information. Further, these software systems model performance under a variety of situations, and such simulation including predictive capabilities that model the meteorological conditions of a proposed site, the physical wind turbine device performance, as well as other simulated calculations. Such simulations are themselves a computer-based problem, since their existence is preconditioned on the use of high- performance computing. Furthermore, the simulations may be used to generate visualizations for a user who uses the simulation software.

[0013] The analysis enables a user to evaluate multiple scenarios in order to evaluate different site selections, or different technology configurations. The volume of computations necessary requires the use of a computer, and thus requires a solution to the above noted computer-based problems.

[0014] Wind energy site diversity analysis helps to select wind energy site locations to manage the problem of wind energy intermittency and improve power availability. Using multiple meteorological and cost data sources for a wind energy model enhances accuracy, resolution, reliability, and adaptability. It allows forimproved predictions of wind patterns, better resource assessment, and more effective decision-making in the planning and operation of wind energy systems.

[0015] In a first aspect, there is provided a computer-implemented method for predicting one or more no-power conditions for a plurality of wind-energy sites, the method comprising: providing, at a memory, a wind energy site power model; receiving, at a processor in communication with the memory, a set of wind energy site characteristics for each wind energy site in the plurality of wind energy sites; receiving, at the processor, one or more weather data points from one or more weather data sources; simulating, at the processor, for each wind energy site in the plurality of wind energy sites, a digital representation of the wind energy site to produce a power generation schedule for the wind energy site, the simulation based at least on at least one data point of the one or more weather data points, the set of wind energy site characteristics for the wind energy site, and the wind energy site power model; aggregating, at the processor, the power generation schedules for each wind energy site to produce an aggregate wind energy portfolio power generation schedule; determining, at the processor, one or more first time periods in which the aggregate wind energy portfolio power generation schedule indicates zero power generation; and determining, at the processor, a total number of hours corresponding to the one or more first time periods.

[0016] In one or more embodiments, the one or more weather data points may be received as a result of an API call made by the processor to the one or more weather data sources.

[0017] In one or more embodiments, the weather data source may comprise at least one of: one or more hourly measured wind speed readings at a sampling station and an hourly modeled estimate of windspeed data based on satellite data.

[0018] In one or more embodiments, the weather data source may comprise data provided by a user through a spreadsheet.

[0019] In one or more embodiments, the set of wind energy site characteristics may comprise at least one characteristic received from a sensor device at a wind energy site.

[0020] In one or more embodiments, the set of wind energy site characteristics may comprise at least one of: one or more wind turbine power curves, one or more wind energy site capacity ranges, one or more a grid connection variability factors, and one or more equipment losses.

[0021] In one or more embodiments, the method may further comprise: receiving, at the processor, one or more economic input factors; and determining, at the processor, one or more feasibility assessment factors based on the economic input factors and the power generation schedules.

[0022] In one or more embodiments, the method may further comprise: determining, at the processor, one or more second time periods in which one or more of the wind energy portfolio power generation schedules indicates zero power generation.

[0023] In one or more embodiments, the method may further comprise generating, at the processor, one or more visualizations based at least on: the total number of hours corresponding to the one or more first time periods; and a total number of hours corresponding to the one or more second time periods.

[0024] In one or more embodiments, the one or more visualizations may comprise at least one of: a graphic, a table, and a graph.

[0025] In one or more embodiments, the set of wind energy site characteristics may be received from a user through inputs entered through a graphical user interface.

[0026] In one or more embodiments, the simulating a digital representation of the wind energy site may comprise: determining, at the processor, a wind energy site performance for each of one or more wind speed categories; determining, at the processor, an overall wind energy site performance for at least one wind energy site scenario based on the wind energy site performances for the one or more wind speed categories; determining, at the processor, a total overall production value for the at least one wind energy site scenario based on the wind energy site performance.

[0027] In a second aspect, there is provided a system for predicting one or more no- power conditions for a plurality of wind-energy sites, the system comprising a memory, and a processor in communication with the memory, the processor configured to perform any one of the methods provided herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0028] A preferred embodiment of the present invention will now be described in detail with reference to the diagrams, in which:FIG. 1 shows a system diagram in accordance with one or more embodiments.FIG. 2 shows a device drawing of the server of FIG. 1 in accordance with one or more embodiments.FIG. 3 shows a method diagram in accordance with one or more embodiments.FIG. 4 shows a user interface diagram in accordance with one or more embodiments.FIG. 5 shows a data input diagram in accordance with one or more embodiments.FIG. 6 shows another method diagram in accordance with one or more embodiments.FIG. 7 shows another method diagram in accordance with one or more embodiments.FIG. 8 shows a method diagram for generating a machine learning model in accordance with one or more embodiments.FIG. 9 shows a correlation matrix diagram for the model generation method in FIG. 8, in accordance with one or more embodiments.FIG. 10 shows a boxplot method diagram for removing outliers, in accordance with one or more embodiments.FIGs. 11 and 12 show performance result diagrams, in accordance with one or more embodiments.DETAILED DESCRIPTION

[0029] Various embodiments will now be described below to provide an example of the claimed subject matter. No example described below limits any claimed subject matter and any claimed subject matter may cover embodiments such as systems or methods that differ from those described below.

[0030] Furthermore, it will be appreciated that for simplicity and clarity of illustration, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements. In addition, numerous specific details are set forth in order to provide a thorough understanding of the examples described herein. However, it will be understood by those of ordinary skill in the art that the examples described herein may be practiced withoutthese specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the examples described herein. Also, the description is not to be considered as limiting the scope of the examples described herein.

[0031] It should also be noted that, as used herein, the wording "and / or" is intended to represent an inclusive-or. That is, "X and / or Y" is intended to mean X or Y or both, for example. As a further example, "X, Y, and / or Z" is intended to mean X or Y or Z or any combination thereof.

[0032] It should be noted that terms of degree such as "substantially", "about" and "approximately" as used herein mean a reasonable amount of deviation of the modified term such that the end result is not significantly changed. These terms of degree may also be construed as including a deviation of the modified term if this deviation would not negate the meaning of the term it modifies.

[0033] Furthermore, the recitation of numerical ranges by endpoints herein includes all numbers and fractions subsumed within that range (e.g., 1 to 5 includes 1 , 1.5, 2, 2.75, 3, 3.90, 4, and 5). It is also to be understood that all numbers and fractions thereof are presumed to be modified by the term "about" which means a variation of up to a certain amount of the number to which reference is being made if the end result is not significantly changed.

[0034] Some elements herein may be identified by a part number, which is composed of a base number followed by an alphabetical or subscript-numerical suffix (e.g., 112a, or 1121). Multiple elements herein may be identified by part numbers that share a base number in common and that differ by their suffixes (e.g., 1121 , 1122, and 1123). All elements with a common base number may be referred to collectively or generically using the base number without a suffix (e.g., 112).

[0035] The example systems and methods described herein may be implemented in hardware or software, or a combination of both. In some cases, the examples described herein may be implemented, at least in part, by using one or more computer programs, executing on one or more programmable devices comprising at least one processing element, a data storage element (including volatile and non-volatile memory and / or storage elements), and at least one communication interface. These devices may also have at least one input device (e.g., a keyboard, a mouse, a touchscreen, and the like), and at least one output device (e.g., a display screen, a printer, a wireless radio, and the like) depending on the nature of the device. For example, and without limitation, the programmable devices (referred to below as computing devices) may be a server, network appliance, embedded device, computer expansion module, a personal computer, laptop, personal data assistant, cellular telephone, smart-phone device, tablet computer, a wireless device or any other computing device capable of being configured to carry out the methods described herein.

[0036] In some examples, the communication interface may be a network communication interface. In examples in which elements are combined, the communication interface may be a software communication interface, such as those for inter-process communication (IPC). In still other examples, there may be a combination of communication interfaces implemented as hardware, software, and a combination thereof.

[0037] Program code may be applied to input data to perform the functions described herein and to generate output information. The output information is applied to one or more output devices, in known fashion.

[0038] Each program may be implemented in a high-level procedural, declarative, functional or object-oriented programming and / or scripting language, or both, to communicate with a computer system. However, the programs may beimplemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Each such computer program may be stored on a storage media or a device (e.g., ROM, magnetic disk, optical disc) readable by a general or special purpose programmable computer, for configuring and operating the computer when the storage media or device is read by the computer to perform the procedures described herein. Examples of the system may also be considered to be implemented as a non-transitory computer- readable storage medium, configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner to perform the functions described herein.

[0039] Furthermore, the example system, processes and methods are capable of being distributed in a computer program product comprising a computer readable medium that bears computer usable instructions for one or more processors. The medium may be provided in various forms, including one or more diskettes, compact disks, tapes, chips, wireline transmissions, satellite transmissions, internet transmission or downloads, magnetic and electronic storage media, digital and analog signals, and the like. The computer useable instructions may also be in various forms, including compiled and non-compiled code.

[0040] Various examples of systems, methods and computer programs products are described herein. Modifications and variations may be made to these examples without departing from the scope of the invention, which is limited only by the appended claims. Also, in the various user interfaces illustrated in the figures, it will be understood that the illustrated user interface text and controls are provided as examples only and are not meant to be limiting. Other suitable user interface elements may be used with alternative implementations of the systems and methods described herein.

[0041] Referring first to FIG. 1 , there is shown a system diagram 100 in accordance with one or more embodiments. The system 100 is for predicting one or more no-power conditions for a plurality of wind-energy sites.

[0042] System 100 includes one or more computer devices 102, a network 104, one or more servers 106, one or more data stores 110, and wind turbines 112 at two different wind energy sites 108.

[0043] The computer-implemented system 100 performs analysis and simulation to identify or predict one or more no-power conditions for a plurality of wind-energy sites 108. The prediction system may identify no-power conditions for each of the wind energy sites 108, or an aggregate no-power condition for the combination of the two or more wind energy sites 108.

[0044] The server 106 is configured to generate the predictions using a wind energy site power model, and may receive weather data and wind energy site characteristics. The weather data may be measured at each of the two or more wind energy sites 108 by a rain sensor, a wind direction and windspeed sensor, a barometric sensor, or another weather sensor as known. The wind energy site characteristics may be measured by a power sensing device which may be incorporated into one or more wind turbines 112 at each wind energy site. Alternatively, the power sensing device may measure the aggregate power delivered from the entire wind energy site 108 itself. Other wind energy site characteristics may be collected by sensors or provided by a user at a computer device 102. These can include site longitude, site latitude, energy export rates, grid connection limits, wind turbine heights, turbine energy capacities, turbine losses, turbine capital costs, ammonia plant power limits, ammonia plant product power, ammonia sale price, ammonia capital cost recovery data, project payment period, project discount rate, greenhouse gas (GHG) emission factors, GHG wind emissionfactors, wind energy site minimum capacity, and wind energy site maximum capacity.

[0045] The weather data and wind energy site characteristics may be collected once when a user generates a scenario for evaluation (whereby the user provides the information), or may be received from a sensor device generally in real time from a candidate energy site. The system 100 may use this data as input to a model running on server 106. The system 100 may store this data in data store 110. A software application running on the server 106 may provide one or more notifications, including analysis of the weather data and wind energy site characteristics in a report for a user at computer device 102. The notifications may provide the user with predictive insights into scenarios, including various configurations of wind energy sites 108. This may include an analysis of no-power conditions at the portfolio of two of more wind energy sites 108.

[0046] The one or more computer devices 102 may be used by a user such as an administrator, consultant, or energy professional to access a software application (not shown) running on server 106 over network 104. In one embodiment, the one or more computer devices 102 may access a web application hosted at server 106 using a browser for reviewing no-power condition scenarios.

[0047] No-power condition scenarios may allow for user input at computer device 102 that provides model-based analysis of "what if" questions that can inform the selection and positioning of the two of more wind energy sites 108. The system 100 may enable users to customize and analyze possible scenarios to evaluate outcomes that may be well suited to specific energy system configuration, while tracking emissions and economic key performance index. The analysis of scenarios for least-cost solutions that may satisfy the energy demand for a specified time period and may provide users such as renewable energy developers, government, utilities, researchers, etc. with the needed analysis to reduce emissions and reapeconomic benefit from the energy system transition. The scenario analysis may enable users to define model inputs and run a variety of cases to test which assumptions are necessary to create feasible model solutions.

[0048] The one or more computer devices 102 may be any two-way communication device with capabilities to communicate with other devices. A computer device 102 may be a mobile device such as mobile devices running the Google® Android® operating system or Apple® iOS® operating system. A computer device 102 may be a desktop or laptop computer such as one running Microsoft® Windows® or Mac® OS X®.

[0049] The computer device 102 may be the personal device of a user, or may be a device provided by an employer. The one or more computer devices 102 may be used by an end user to access the software application (not shown) running on server 106 over network 104. The computer device 102 may be in communication with server 106, and may allow a user to review current predictions of no-power conditions stored in a database at data store 110 or historical predictions of nopower conditions stored in a database at data store 110.

[0050] The browser running on the one or more computer devices 102 may communicate with server 106 using an Application Programming Interface (API) endpoint, and may send and receive weather data and wind energy site characteristics data using the API. The sensor data sent from the wind energy sites 108 may similarly be sent to server 106 using an API endpoint.

[0051] The browser running on the one or more computer devices 102 may display one or more user interfaces on a display device of the user device, including, but not limited to, the user interface shown in FIG. 4.

[0052] Network 104 may be any network or network components capable of carrying data including the Internet, Ethernet, fiber optics, satellite, mobile, wireless(e.g. Wi-Fi, WiMAX), SS7 signaling network, fixed line, local area network (LAN), wide area network (WAN), a direct point-to-point connection, mobile data networks (e.g., Universal Mobile Telecommunications System (UMTS), 3GPP Long-Term Evolution Advanced (LTE Advanced), Worldwide Interoperability for Microwave Access (WiMAX), etc.) and others, including any combination of these.

[0053] The server 106 is in network communication with the one or more computer devices 102 and sensor devices at the two or more wind energy sites 108. The server 106 may further be in communication with a database at data store 110. The database at data store 108 and the server 106 may be provided on the same server device, may be configured as virtual machines, or may be configured as containers. The server 106 and a database at data store 110 may run on a cloud provider such as Amazon® Web Services (AWS®).

[0054] The server 106 may host a web application or an Application Programming Interface (API) endpoint that the one or more computer devices 102 and sensor devices at the two or more wind energy sites 108 and may interact with via network 104. The server 106 may make calls to the database at data store 110 to query historical weather data and wind energy site characteristics data for the two or more wind energy sites 108. The requests made to the API endpoint of server 106 may be made in a variety of different formats, such as JavaScript Object Notation (JSON) or extensible Markup Language (XML). The weather data and wind energy site characteristics data may be transmitted to the server 106 may be in a variety of different formats, including binary data, CSV data, XML data, and other formats as known. The weather data and wind energy site characteristics data may be encrypted prior to transmission to server 106. The weather data and wind energy site characteristics data received by the data store 110 may be stored in the database at data store 110, or may be stored in a file system at data store 110. The file system may be a redundant storage device at the data store 110, or may be another service such as Amazon® S3, or Dropbox.

[0055] The database of data store 110 may store subject information including weather data and wind energy site characteristics data, scenario data and / or nopower condition predictions. The database of data store 110 may be a Structured Query Language (SOL) such as PostgreSQL or MySQL or a not only SOL (NoSQL) database such as MongoDB.

[0056] Referring next to FIG. 2, there is shown a device diagram 200 of the server 106 of FIG. 1 in accordance with one or more embodiments. The server device diagram 200 shows detail of the server 106 in FIG. 1. The server 200 includes one or more of a communication unit 204, a display 206, a processor unit 208, a memory unit 210, 1 / 0 unit 212, a user interface engine 214, and a power unit 216.

[0057] The communication unit 204 can include wired or wireless connection capabilities. The communication unit 204 can include a radio that communicates using standards such as IEEE 802.11a, 802.11 b, 802.11g, or 802.11 n. The communication unit 204 can be used by the server 200 to communicate with other devices or computers.

[0058] Communication unit 204 may communicate with a network, such as networks 104 (see FIG. 1).

[0059] The display 206 may be an LED or LCD based display, and may be a touch sensitive user input device that supports gestures.

[0060] The processor unit 208 controls the operation of the server 200. The processor unit 208 can be any suitable processor, controller or digital signal processor that can provide sufficient processing power depending on the configuration, purposes and requirements of the server 200 as is known by those skilled in the art. For example, the processor unit 208 may be a high performance general processor. In alternative embodiments, the processor unit 208 can includemore than one processor with each processor being configured to perform different dedicated tasks. The processor unit 208 may include a standard processor, such as an Intel® processor or an AMO® processor.

[0061] The processor unit 208 can also execute a user interface (III) engine 214 that is used to generate various Ills for delivery via a web application provided by the Web / API Unit 232, some examples of which are shown and described herein, such as interface shown in FIG. 4.

[0062] The memory unit 210 comprises software code for implementing an operating system 220, programs 222, database server 224, data collection unit 226, scenario unit 228, prediction unit 230, and Web / API Unit 232.

[0063] The memory unit 210 can include RAM, ROM, one or more hard drives, one or more flash drives or some other suitable data storage elements such as disk drives, etc. The memory unit 210 is used to store an operating system 220 and programs 222 as is commonly known by those skilled in the art.

[0064] The 1 / 0 unit 212 can include at least one of a mouse, a keyboard, a touch screen, a thumbwheel, a track-pad, a track-ball, a card-reader and the like again depending on the particular implementation of the server 200. In some cases, some of these components can be integrated with one another.

[0065] The user interface engine 214 is configured to generate interfaces for users to configure energy scenarios, view no-power predictions and associated notifications, view weather data and wind energy site characteristic data, etc. The various interfaces generated by the user interface engine 214 may be transmitted to a user device by virtue of the Web / AP I Unit 232 and the communication unit 204.

[0066] The power unit 216 can be any suitable power source that provides power to the server 200 such as a power adaptor or a rechargeable battery packdepending on the implementation of the server 200 as is known by those skilled in the art.

[0067] The operating system 220 may provide various basic operational processes for the server 200. For example, the operating system 220 may be a server operating system such as Ubuntu® Linux, Microsoft® Windows Server® operating system, or another operating system.

[0068] The programs 222 include various user programs. They may include several hosted applications delivering services to users over the network, for example, energy tracking applications, energy modelling applications and the like.

[0069] In one or more embodiments, the programs 222 may provide a wind energy evaluation platform that is web-based, or client server based via a Web / API Unit 232 that provides for analysis and evaluation of scenarios for a user.

[0070] The database server 224 may be a database for storing received sensor data (including weather data and wind energy site characteristic data as well as historic data thereof) as well as user submitted scenario data (including historical scenarios), and no-power predictions (both current and historical). The database 224 may include weather data and wind energy site characteristic data from a broad range of wind energy sites including a range of wind turbine equipment. The database 224 may be referenced by a site identifier that corresponds to a particular wind energy site, or alternatively, a site turbine identifier and a site identifier, the site turbine identifier corresponding to a particular wind turbine within the identified wind energy site.

[0071] The data collection unit 226 may receive weather data and wind energy site characteristic data from one or more sensors located at two or more wind energy sites, as described in further detail in FIG. 5. The data received by data collection unit 226 may be stored in database server 224.

[0072] The scenario unit 228 may be, for example an energy model 310 in FIG. 3 and may perform, for example, step 608 in FIG. 6. The scenario unit 228 may provide for the simulation of each wind energy site, including a digital representation of the wind energy site to produce a power generation schedule for the wind energy site, the simulation based at least on at least one data point of the one or more weather data points, the set of wind energy site characteristics for the wind energy site, and the wind energy site power model.

[0073] The prediction unit 230 receives the output from the scenario unit 228, and may operate the method as described in FIG. 6 to generate predictions of nopower conditions for various scenarios for a user. This may include preparing visualizations in conjunction with user interface engine 214 that can be transmitted to a user at a computer device. This may further include operating the models described herein, which may be stored in the prediction unit 230 in the memory 210.

[0074] The Web / API Unit 232 may be a web-based application or Application Programming Interface (API) such as a REST (REpresentational State Transfer) API. The API may communicate in a format such as XML, JSON, or other interchange format.

[0075] The Web / API Unit 232 may receive a scenario prediction request to identify one or more no-power conditions for a plurality of wind energy sites. This request may include the input data identified in FIG. 5, data stored in database server 224 and may apply methods herein to predicted one or more no-power conditions for the plurality of wind energy sites, and then may provide the prediction in a no-power prediction response. The prediction may be associated with the corresponding scenario, and stored in the database 224.

[0076] Referring next to FIG. 3, there is shown a method diagram 300 in accordance with one or more embodiments. The method 300 may provide, at a highlevel, the method of FIG. 6. The method 300 includes input processing 302 for energy system data 304, an energy model 310, and output processing 320 including a feasibility model solution 322 and data visualization 324.

[0077] The input processing 302 may correspond to the input data processing described in FIG. 5.

[0078] The energy system data 304 may correspond to the weather data and the wind energy site characteristic data in FIG. 5.

[0079] The energy model 310 may operate in an inference or prediction mode according to the method in FIG. 7 using the inputs described in FIG. 5. The energy model 310 may improve upon conventional approaches in three main areas: by wind farm diversity analysis for two or more wind energy sites, by providing flexibility in using and analyzing meteorological and cost data from multiple sources, and providing real-time data integration using machine learning.

[0080] The energy model 310 may be a random forest model. The energy model 310 may be generated or trained based on the method described in FIG. 8 using the inputs described in FIG. 5.

[0081] Wind farm diversity analysis may assist with the selection of wind energy site locations to manage the problem of wind energy intermittency and improve power availability. Using multiple meteorological and cost data sources for a wind energy model may enhance accuracy, resolution, reliability, and adaptability. It may permit improved predictions of wind patterns, better resource assessment, and more effective decision-making in the planning and operation of wind energy systems.

[0082] The output 320 from the energy model 310 may be used to inform the scenarios submitted by a user and identify a predicted preferred scenario, as wellas a prediction of the number of no-power conditions, i.e. the feasibility model solution 322 which may be used to generate a visualization such as the one shown in FIG. 4.

[0083] Referring next to FIG. 4, there is shown a user interface diagram 400 in accordance with one or more embodiments. The user interface 400 is displayed on display device 410 and include an visualization title 420 (in this case, Model Diversity Results: Zero Power Hours), an analysis region 430 including no-power conditions for two wind energy sites: St. Lawrence 440, Stephenville 450, and a combined no-power condition 460 for both sites.

[0084] The user interface 400 may be transmitted to a browser on a computer device (such as device 102 in FIG. 1), and may provide for prediction data to be reported to a user. The analysis may include many more wind energy sites than just the two shown. Furthermore, the wind energy sites 440 and 450 may be user selectable, and upon user selection in the user interface, additional details about the prediction may be shown. This may include individual predictions for individual wind turbines at the site, explanatory details of the prediction, or other data stored in database 110 (see FIG. 1).

[0085] The no-power conditions displayed for each St. Lawrence site 440 and Stephenville 450 may represent the number of predicted hours per year that each site will see a no-power condition. The combined no power condition 460 may represent the number of hours that the combination of the St. Lawrence site 440 and the Stephenville 450 site may experience a no-power condition. In this manner, the present systems and methods provide for wind energy site diversity analysis and wind energy site selection in order to provide improved no-power conditions of sites when they are taken in combination.

[0086] Referring next to FIG. 5, there is shown a data input diagram 500 in accordance with one or more embodiments.

[0087] The systems and methods herein may receive and process different sources of data as a wind speed input data. For example, the system can accept wind data in the form of hourly measured readings of windspeeds at various sampling stations provided by Environment Canada. As another example, the system can also accept wind data via NASA's Earthdata platform, which provides an hourly modeled estimate of windspeed data at any point on Earth, to a resolution of a square of .5 degree. In general, the system may accept any source of data as input windspeed data as long as the data can be either accessed through a supported application programming interface or uploaded to the software in Excel / CSV file format.

[0088] In another embodiment, the wind speed data may be collected from a sensor at a candidate wind energy site.

[0089] The received meteorological data may be generated using correlation for data approximation or otherwise using modeled data. However, such approximations may affect results accuracy. Measured meteorological data is more accurate but limited in its available locations. Real-time data streams from different weather sources may be used and combined to assist with predictions including weather patterns, and market dynamics.

[0090] The inputs 510 to processor 530 which may be used as described in the methods in FIGs. 3, 6 and 7 may include weather data 512, wind speed data 514, wind turbine specification data 516, equipment and production cost data 518, wind farm capacity data 520, grid connection variability data 522, initial operation and maintenance cost data 524 and capital cost data 526. This data may be user supplied (i.e. by user input at computer device 102 in FIG. 1 , or received frommeteorological sources via network 104, or collected by sensors at wind energy site 108 and provided to the server 106).

[0091] The weather data 512 may include wind speed data 514 for a wind farm location. This may include weather data such as wind speed data and wind direction data associated with a wind farm location in a numerical format. The weather data may be for a single point in time, for an averaged time period, or may be timevarying throughout a time period. The data may be collected once per simulation cycle.

[0092] The wind turbine specification data 516 may include wind turbine power curve data, wind turbine heigh data, and wind turbine capacity data. This may be for a single type of wind turbine, or for several different types of wind turbines. The specification data 516 may be numerical representations about the performance of different types of wind turbines, and may be collected once per simulation cycle.

[0093] The equipment and production cost data 518 may include operational expenditure data (OPEX) data and capital expenditure data. This may be numerical cost data about the operation of equipment, and may be collected once per simulation cycle.

[0094] The wind farm capacity data 520may be a power metric in megawatts (MW), and may reflect the capacity of one or more wind turbines to generate power. This may be a numerical value that may be collected once per simulation cycle.

[0095] The grid connection variability data 522 may be a power metric in megawatts (MW), and may reflect the capacity of one or more wind turbines to supply a power grid. This may be a numerical value that may be collected once per simulation cycle.

[0096] The initial operation and maintenance cost data 524 may include operational expenditure data (OPEX) data and capital expenditure data (CAPEX). This may be numerical cost data reflecting the initial operation and maintenance of a wind farm location, and may be collected once per simulation cycle.

[0097] The capital cost data 526 may include capital expenditure data (CAPEX). This may be numerical cost data about the capital costs associated with the wind farm location, and may be collected once per simulation cycle.

[0098] Referring next to FIG. 6, there is shown another method diagram 600 in accordance with one or more embodiments. The computer-implemented method 600 is for predicting one or more no-power conditions for a plurality of wind-energy sites.

[0099] The method 600 may provide a wind farm diversity analysis on the proposed project or scenario. This may include first producing individual wind farm calculations to estimate energy generation by time at each proposed wind farm location. The system may then combine the predicted energy generation data across all proposed wind farm locations to determine a total output power time series that contains data about the combined power output of all wind farm locations. This may produce data that provides a broader view of project performance. A user may, for instance, use this information to determine whether there might be any zero power hours across the entire portfolio of wind farms rather than just one single farm, which may be important to a determination of feasibility. The system may also produce visualizations of this data in the form of graphs or tables, which may be displayed into the user interface.

[0100] At 602, a wind energy site power model is provided at a memory.

[0101] At 604, a set of wind energy site characteristics for each wind energy site in the plurality of wind energy sites is received at a processor in communication with the memory.

[0102] At 606, one or more weather data points from one or more weather data sources are received at the processor.

[0103] At 608, for each wind energy site in the plurality of wind energy sites, a digital representation of the wind energy site is simulated at the processor to produce a power generation schedule for the wind energy site, the simulation based at least on at least one data point of the one or more weather data points, the set of wind energy site characteristics for the wind energy site, and the wind energy site power model.

[0104] At 610, the power generation schedules for each wind energy site are aggregated at the processor to produce an aggregate wind energy portfolio power generation schedule.

[0105] At 612, one or more first time periods in which the aggregate wind energy portfolio power generation schedule indicates zero power generation are determined at the processor.

[0106] At 614, a total number of hours corresponding to the one or more first time periods is determined at the processor.

[0107] In one or more embodiments, the one or more weather data points may be received as a result of an API call made by the processor to the one or more weather data sources.

[0108] In one or more embodiments, the set of wind energy site characteristics may comprise at least one characteristic received from a sensor device at a wind energy site.

[0109] In one or more embodiments, the weather data source may comprise at least one of: one or more hourly measured wind speed readings at a sampling station and an hourly modeled estimate of windspeed data based on satellite data.

[0110] In one or more embodiments, the weather data source may comprise data provided by a user through a spreadsheet.

[0111] In one or more embodiments, the set of wind energy site characteristics may comprise at least one characteristic received from a sensor device at a wind energy site.

[0112] In one or more embodiments, the set of wind energy site characteristics may comprise at least one of: one or more wind turbine power curves, one or more wind energy site capacity ranges, one or more a grid connection variability factors, and one or more equipment losses.

[0113] In one or more embodiments, the method may further comprise: receiving, at the processor, one or more economic input factors; and determining, at the processor, one or more feasibility assessment factors based on the economic input factors and the power generation schedules.

[0114] In one or more embodiments, the method may further comprise: determining, at the processor, one or more second time periods in which one or more of the wind energy portfolio power generation schedules indicates zero power generation.

[0115] In one or more embodiments, the method may further comprise generating, at the processor, one or more visualizations based at least on: the total number of hours corresponding to the one or more first time periods; and a total number of hours corresponding to the one or more second time periods.

[0116] In one or more embodiments, the one or more visualizations may comprise at least one of: a graphic, a table, and a graph.

[0117] In one or more embodiments, the set of wind energy site characteristics may be received from a user through inputs entered through a graphical user interface.

[0118] In one or more embodiments, the simulating a digital representation of the wind energy site may comprise: determining, at the processor, a wind energy site performance for each of one or more wind speed categories; determining, at the processor, an overall wind energy site performance for at least one wind energy site scenario based on the wind energy site performances for the one or more wind speed categories; determining, at the processor, a total overall production value for the at least one wind energy site scenario based on the wind energy site performance.

[0119] Referring next to FIG. 7, there is shown another method diagram 700 in accordance with one or more embodiments. The operation of energy model 310 (see e.g. FIG. 3) may include part or all of method 700.

[0120] Parameters such as the wind speed data, wind turbine specification, equipment and production losses, wind farm capacity, grid connection variability, initial operation and maintenance costs, and capital costs, are entered as input parameters. The model calculation was implemented in the model section (see e.g. 310 in FIG. 3), where variables such as power output, plant usage, grid supply, grid variability, wind speed at hub height, energy production, capital cost recovery, and profit / loss are determined.

[0121] Three main sets of input parameters may be provided, including economic input parameters 726, wind energy site input parameters 728, and ammonia input parameters 730.

[0122] The economic input parameters 726 can include initial operating and maintenance cost data 702, capital cost data 704, and electricity export rate data 706.

[0123] The wind energy site input parameters 728 can include wind speed data 708 and 710, wind turbine specification data 714, wind turbine power curve data 712, wind farm capacity range 716, grid connection variability 718, and loss data 720.

[0124] The ammonia input parameters 730 can include ammonia plant size 722 and power per tonne of ammonia data 724.

[0125] The economic processing of economic input parameters 726 may include capital cost recovery calculations 732, total capital cost recovery calculations 734, ammonia capital cost recovery calculations 738, and profits / loss calculation 736.

[0126] This economic processing may generate economic output 780 including sales amount data 774, capital recovery data 776, profit / loss determination data 778, energy production cost data 782, potential revenue from grid supply data 784, and potential revenue from various interconnection capacities 786.

[0127] The wind energy site processing of wind energy site input parameters 726 may include power output calculations at a plurality of wind speeds 740, power output calculations for each scenario 742, total energy output calculation for each scenario 744, ammonia plant usage calculations for a plurality of wind speeds 746, ammonia plant usage calculations for each scenario 748, total ammonia plant usage calculations for each scenario 750, grid supply calculations for a plurality of wind speeds 752, grid supply calculation for each scenario 754, total grid supply calculation for each scenario 756, grid variability calculations for a plurality of wind speeds, grid variability for each scenario 760, total grid variability calculations for each scenario 762, and wind speed calculations for a plurality of heights 764.

[0128] The output from wind energy site processing 794 may include total energy production 788, plant energy usage 790, potential energy supply to the grid 792, zero power hours 796, energy output from various interconnection capacities 797, power factor 799, and results and visualization 798.

[0129] The ammonia plant processing of ammonia input parameters 730 may include ammonia production calculations for each scenario 766.

[0130] The output from the ammonia plant processing may include a power factor 770 and ammonia production 772.

[0131] Referring next to FIG. 8, there is shown a method 800 for generating or training a machine learning model in accordance with one or more embodiments.

[0132] The model generation method creates a machine learning model to forecast wind speed in various locations. The data generated by the machine learning model may be further analyzed and used for energy systems modeling, providing insights for energy production, storage, and consumption. The model generation process 800 may include several steps such as data cleaning, data visualization, feature selection, data processing (data normalization and denormalization), and ensemble learning modeling. The primary objective of the machine learning model is to predict real time wind speed to enhance energy management strategies as described herein.

[0133] At 802, a dataset may be provided. The dataset may be, for example, the data stored in the database 110 (e.g. FIG. 1) including a historical dataset of inputs 510 (e.g. FIG. 5).

[0134] At 804, at least one feature may be selected based on an analysis of the dataset 802. Feature selection is performed in order to identify particular features of the dataset that are correlated with windspeed prediction (see e.g. examplecorrelation matrix in FIG. 9). Feature selection may improve model performance by reducing overfitting through the elimination of irrelevant or redundant features, and may enhance the model's accuracy and generalization. Feature selection may reduce complexity and simplify the model by making it easier and faster to train. Feature selection may enhance model interpretability by focusing on the most important features and decreases training time by reducing the computational cost associated with processing fewer features. As such, feature selection in this context is an improvement to the machine learning model system, which reduces the processing required when the model is used in inference mode.

[0135] The selected features 804 for machine learning model training may include: Wind speed (initially in km / h, converted to mis for uniformity), temperature, wind direction, station pressure (adjusted for altitude and current weather conditions), relative humidity, and date.

[0136] The correlation matrix for windspeed prediction based on the selected features 804 is shown in FIG. 9.

[0137] At 806, data cleaning and normalization may be performed. The data cleaning may include the removal of outliers, for example using the boxplot method (lower bound = Q1 - 1.5 * IQR, upper bound = Q3 + 1.5 * IQR) as described in FIG. 10.

[0138] The data normalization at 806 may include scaling input features to a standard range, which may improve the model's learning efficiency, may improve convergence speed, and may provide that all features contribute equally to the model. This may help in providing more accurate and reliable predictions.

[0139] At 808, a plurality of model types may be assessed by training a plurality of candidate models using different methods as are known. For example, a Neural Network may be trained, or a Random Forest model may be trained. The modelmay be assessed to select the final model. The performance assessment of the plurality of different types of models may include converting the predicted hourly wind speed data 810 into an energy metric 812 (for example, converting the wind speed using a pre-existing wind turbine model to determine the power produced by a particular wind turbine). Then, the Mean Absolute Percentage Error (MAPE) may be used to quantify the difference between the actual generated energy and the predicted energy:

[0140] At 808, after converting the predicted wind speed 810 to energy metric 812 produced by a particular wind turbine, for example, non-linear regressors may be selected as the model type, and more specifically, the RandomForestRegressor from scikit-learn may be selected. This selection may be based in part on the performance during the assessment (including the MAPE) as compared with other candidate models such as other non-linear regressors. The Random Forest model type in this example may exhibit the least errors in the assessment, making it the preferred model type for use in inference and prediction tasks. This conclusion may be based on the assessment, other experimentation and on model validation, including cross-validation on data from multiple locations (for example, various geographic locations may be used in comparison such as St. Lawrence, Stephenville, and Argentia) and spanning a significant period of time.

[0141] The present invention has been described here by way of example only. Various modification and variations may be made to these exemplary embodiments without departing from the spirit and scope of the invention, which is limited only by the appended claims.Example 1

[0142] In a first example of the performance of the random forest model, 14 randomly selected locations were selected from both NASA and Environment Canada datasets. The model was trained based on the methods described herein on data from 2006 to 2019 and experimental predictions were made using the methods described herein for the years 2020 to 2024.

[0143] Referring to FIG. 11 , the performance data diagram 1100 shows the performance of the random forest model using the NASA dataset. The graph shows actual (i.e. measured) energy generation vs. predicted energy generation for the 14 randomly selected locations. As well, the overall percentage difference 1102 for all 14 locations.

[0144] Referring to FIG. 12, another performance data diagram 1200 shows the performance of the random forest model using the Environment Canada dataset. The graph shows actual (i.e. measured) energy generation vs. predicted energy generation for the 14 randomly selected locations. As well, the overall percentage difference 1202 for all 14 locations.

Claims

CLAIMS1. A computer-implemented method for predicting one or more no-power conditions for a plurality of wind-energy sites, the method comprising:- providing, at a memory, a wind energy site power model;- receiving, at a processor in communication with the memory, a set of wind energy site characteristics for each wind energy site in the plurality of wind energy sites;- receiving, at the processor, one or more weather data points from one or more weather data sources;- simulating, at the processor, for each wind energy site in the plurality of wind energy sites, a digital representation of the wind energy site to produce a power generation schedule for the wind energy site, the simulation based at least on at least one data point of the one or more weather data points, the set of wind energy site characteristics for the wind energy site, and the wind energy site power model;- aggregating, at the processor, the power generation schedules for each wind energy site to produce an aggregate wind energy portfolio power generation schedule; determining, at the processor, one or more first time periods in which the aggregate wind energy portfolio power generation schedule indicates zero power generation; and- determining, at the processor, a total number of hours corresponding to the one or more first time periods.

2. The method of claim 1 , wherein the one or more weather data points is received as a result of an API call made by the processor to the one or more weather data sources.

3. The method of claim 2, wherein the weather data source comprises at least one of: one or more hourly measured wind speed readings at a sampling station and an hourly modeled estimate of windspeed data based on satellite data.

4. The method of claim 1 , wherein the weather data source comprises data provided by a user through a spreadsheet.

5. The method of any one of claims 1 to 4, wherein the set of wind energy site characteristics comprises at least one characteristic received from a sensor device at a wind energy site.

6. The method of claim 5, wherein the set of wind energy site characteristics comprises at least one of: one or more wind turbine power curves, one or more wind energy site capacity ranges, one or more a grid connection variability factors, and one or more equipment losses.

7. The method of any one of claims 1 to 5, further comprising: receiving, at the processor, one or more economic input factors; and determining, at the processor, one or more feasibility assessment factors based on the economic input factors and the power generation schedules.

8. The method of any one of claims 1 to 7, further comprising: determining, at the processor, one or more second time periods in which one or more of the wind energy portfolio power generation schedules indicates zero power generation.

9. The method of claim 8, further comprising generating, at the processor, one or more visualizations based at least on:- the total number of hours corresponding to the one or more first time periods; and- a total number of hours corresponding to the one or more second time periods.

10. The method of claim 9, wherein the one or more visualizations comprise at least one 20 of: a graphic, a table, and a graph.11 . The method of any one of claims 1 to 10, wherein the set of wind energy site characteristics is received from a user through inputs entered through a graphical user interface.

12. The method of any one of claims 1 to 11 , wherein the simulating a digital representation of the wind energy site comprises:- determining, at the processor, a wind energy site performance for each of one or more wind speed categories;- determining, at the processor, an overall wind energy site performance for at least one wind energy site scenario based on the wind energy site performances for the one or more wind speed categories;- determining, at the processor, a total overall production value for the at least one wind energy site scenario based on the wind energy site performance.

13. A system for predicting one or more no-power conditions for a plurality of windenergy sites, the system comprising a memory, and a processor in communication with the memory, the processor configured to perform the method of any one of claims 1 to 12.

Images