Load assembly for energy storage systems

Abstract

A method, system, apparatus, and non-transient computer-readable medium are provided for using load sets in an energy storage system. In one embodiment, the computer-readable medium includes instructions which cause a processor to receive operational data related to an energy storage unit for a period of time, determine one or more charge and discharge cycles of the energy storage unit during that period, generate a plurality of load sets based on the operational data, determine one or more operational parameters of the energy storage unit for the period, provide a machine learning model with one or more operational parameters and one or more load sets from the plurality of load sets, generate a predicted capacity of the energy storage unit based on the machine learning model at the end of the period, and configure one or more energy storage units based on the predicted capacity.

Description

Technical Field

[0001] The present disclosure generally relates to the field of energy storage. More specifically, the present disclosure relates to an energy storage system using a load bank.

Background Art

[0002] An energy storage system can receive, store, and output energy. The energy storage system may be connected to, for example, a power grid, a power plant, a building, or any other type of facility, and can receive and store energy and later provide the energy. An operator of the energy storage system can configure, for example, the times and rates at which the energy storage system can input or output energy, which units (if any) of the energy storage system can input or output energy, or any other configuration of the energy storage system, how the energy storage system operates.

Summary of the Invention

[0003] Since energy storage is used over time, the capacity of the energy storage may decrease with use. By monitoring the capacity of the energy storage, better management of the energy storage can be enabled. For example, by monitoring the capacity of the energy storage, capacity enhancement can be enabled when the capacity drops below a threshold. As another example, information regarding how the capacity of the energy storage changes may help identify any overuse of the energy storage and may help determine how the energy storage can be used in the future (e.g., to reduce overuse). If the capacity of the energy storage is not determined efficiently or accurately, it can result in inefficient management of the energy storage, for example, with respect to decisions where there may be a benefit to considering the capacity of the energy storage.

[0004] The embodiments disclosed may relate to systems and methods aimed at improving the efficiency and / or accuracy of determining the capacity of energy storage, for example, by determining the capacity using the operating characteristics of the energy storage, as will be described in more detail herein.

[0005] The embodiments disclosed may relate to energy storage systems. Embodiments provided in this disclosure provide systems, methods, and apparatus related to energy storage.

[0006] The disclosed embodiments may include systems, methods, apparatus, and non-transient computer-readable media for using load sets in an energy storage system. For example, a disclosed embodiment may include, by means of a computing device, receiving operational data related to one of one or more energy storage units for a period of time; determining one or more charge and discharge cycles of that energy storage unit during that period; generating a plurality of load sets based on the operational data; determining one or more operational parameters of the energy storage unit during the period; providing a machine learning model with one or more operational parameters and one or more load sets from the plurality of load sets; generating a predicted capacity of the energy storage unit at the end of the period based on the machine learning model; and configuring one or more energy storage units based on the predicted capacity. In some embodiments, each load set of the plurality of load sets includes one or more criteria related to the operation of the energy storage unit and a number of cycles from one or more cycles that satisfy one or more criteria.

[0007] According to the disclosed embodiments, a non-temporary computer-readable medium may store instructions that, when executed by at least one processor, cause at least one processor to perform any of the processes described herein.

[0008] The general description above and the detailed description below are illustrative and explanatory only and do not limit the scope of the claims.

[0009] The accompanying drawings, incorporated into and constituting part of this disclosure, illustrate various embodiments disclosed. [Brief explanation of the drawing]

[0010] [Figure 1] This disclosure illustrates exemplary systems for managing energy storage systems according to several embodiments of this disclosure. [Figure 2] This disclosure describes exemplary computing devices according to several embodiments. [Figure 3] This disclosure illustrates an exemplary energy storage unit according to several embodiments. [Figure 4] A flowchart illustrating exemplary methods for using load sets in an energy storage system, according to some embodiments of this disclosure, is shown. [Figure 5] Examples of load sets according to some embodiments of this disclosure are shown below. [Figure 6] This disclosure presents exemplary user interfaces associated with the use of load sets in energy storage systems according to several embodiments of this disclosure. [Figure 7] Examples of diagrams for determining charge and discharge cycles according to some embodiments of this disclosure are shown. [Modes for carrying out the invention]

[0011] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numerals are used in the drawings and the following description to refer to identical or similar parts. While several exemplary embodiments are described herein, modifications, adaptations, and other embodiments are possible. For example, components shown in the drawings may be replaced, added, or modified, and exemplary methods described herein may be modified by replacing, rearranging, removing, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to specific embodiments and examples, but includes general principles described herein and shown in the drawings, in addition to the general principles encompassed by the accompanying claims.

[0012] Figure 1 shows an exemplary system 100 for managing an energy storage system according to some embodiments of the present disclosure. System 100 may include an energy storage system 110, a network 114, a user device 116, and one or more power lines (e.g., power line 118). Energy storage system 110 may include one or more energy storage units (e.g., 112A, 112B, and 112C).

[0013] Network 114 may include one or more of the various types of networks for communicating information, such as cellular networks (e.g., 2G, 3G, 4G, or 5G), satellite networks, Wi-Fi networks, WiMAX networks, Bluetooth networks, near-field communication (NFC) networks, low-power wide-area networks (LPWAN) networks, mobile networks, terrestrial microwave networks, wireless ad-hoc networks, Ethernet networks, telephone networks, power line communication (PLC) networks, coaxial cable networks, and fiber optic networks. Network 114 may include wired or wireless networks. Network 114 may include personal area networks, local area networks, metropolitan area networks, wide area networks, global area networks, space networks, or any other type of computer network that may use data connections between network nodes. In some examples, network 114 may include Internet Protocol (IP) based networks. Network 114 may use interconnected communication links to connect one or more user devices, such as energy storage units 112A, 112B, 112C, and / or user device 116.

[0014] The energy storage system 110 may refer to any system configured to store energy. The energy storage system 110 may include a centralized system or a distributed system. The energy storage system 110 may include one or more energy storage units (e.g., 112A, 112B, and 112C). In some examples, the energy storage units 112A, 112B, and 112C may be located in a single physical location, such as a site. In some examples, the energy storage units 112A, 112B, and 112C may be distributed across multiple physical locations. The energy storage units 112A, 112B, and 112C may be interconnected via a network that allows for the exchange of data and / or energy between one or more energy storage units 112A, 112B, and 112C, and may be configured to function as a system. Although only three energy storage units 112A, 112B, and 112C have been described above, the energy storage system 110 is intended to include any number of energy storage units.

[0015] The energy storage system 110 may be coupled to one or more power lines (e.g., power line 118). In some examples, power line 118 may be associated with a power grid. In some examples, power line 118 may be associated with a power plant (e.g., a solar power plant, solar farm, wind power plant, wind farm, hydroelectric power plant). In some examples, power line 118 may be associated with any type of facility (e.g., a building, factory, hospital, school, airport, or any other entity that uses energy). The energy storage system 110 may receive energy through power line 118, store the received energy, and / or output energy through power line 118. For example, the energy storage system 110 may include power grid energy storage within the power grid (e.g., energy storage that may be configured to store electrical energy when there is sufficient electricity in the power grid and to output electrical energy to the power grid when electricity demand is high). The energy storage system 110 can store electrical energy when electricity demand is low and output electrical energy to the power grid when electricity demand is high. As another example, the energy storage system 110 may be located next to a solar farm and configured to receive electrical energy from the solar farm and store it for later output. As yet another example, the energy storage system 110 may be located next to a facility and configured to store electrical energy and provide it to the facility when appropriate.

[0016] An energy storage system 110, including energy storage units 112A to 112C, can store energy in one or more of various forms, such as electrochemical, chemical, mechanical, electrical, electromagnetic, biological, and / or thermal. In some examples, an energy storage system 110, including energy storage units 112A to 112C, can store energy using rechargeable batteries. Examples of energy storage units are described in more detail in relation to Figure 3.

[0017] The user device 116 may include any type of computing device configured to perform one or more of the embodiments described herein (for example, to use a load set in an energy storage system). For example, the user device 116 may include at least one processor and memory for storing instructions, which, when executed by at least one processor, cause at least one processor to perform one or more of the embodiments described herein. The user device 116 may include, for example, a computer, laptop computer, desktop computer, mainframe computer, tablet, smartphone, mobile phone, mobile device, server device, client device, automotive electronic device, augmented reality headset, smartwatch, Internet of Things (IoT) device, or any other type of computing device. In some examples, the user device 116 may be configured to receive data from various sources (for example, via network 114) and / or to manage the energy storage system 110. For example, the user device 116 may receive operational data for energy storage units 112A, 112B, and 112C. Based on the received data, the user device 116 can manage the energy storage system 110. For example, as will be described in more detail herein, the user device 116 may determine the load sets of energy storage units 112A, 112B, and 112C, use the load sets to configure the energy storage units 112A, 112B, and 112C, and / or display a user interface(s) that may allow a user (e.g., an administrator or operator of the energy storage system 110) to interact with the energy storage system 110. Although only one user device 116 is shown in Figure 1 and described above, the system 100 is intended to include any number of user devices.

[0018] Figure 2 shows an exemplary computing device 210 according to several embodiments of the present disclosure. The computing device 210 may include, for example, at least one processor 212, at least one memory 214, at least one network interface 216, one or more input devices 218, and / or one or more output devices 220. Devices described herein (e.g., the user device 116 shown in Figure 1 and the computing device 312 shown in Figure 3) may similarly include these components and / or be implemented in a similar manner to the computing device 210. In some examples, the computing device 210 including one or more of the components may be implemented using virtualization and / or cloud computing technologies.

[0019] The processor 212 can execute instructions of a computer program to perform any of the functions described herein. The processor 212 may include, for example, an integrated circuit, a microchip, a microcontroller, a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), or other units suitable for executing instructions or performing logical operations. The processor 212 may include a single-core or multi-core processor (e.g., a dual-core, quad-core, or processor having any desired number of cores). The processor 212 may provide the ability to run, control, operate, or store multiple processes, applications, or programs. In some examples, the processor 212 may be configured to provide parallel processing capabilities that allow devices associated with the processor to run multiple processes simultaneously. In some examples, the processor 212 may consist of virtualization technology. Other types of processor configurations may be implemented to provide the functions described herein.

[0020] Memory 214 may include a non-temporary computer-readable medium capable of storing instructions, which, when executed by at least one processor, cause at least one processor to execute one or more processes described herein. The non-temporary computer-readable medium may include any type of physical memory capable of storing information or data readable by at least one processor. The non-temporary computer-readable medium may include, for example, random access memory (RAM), read-only memory (ROM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), non-volatile random access memory (NVRAM), volatile memory, non-volatile memory, hard drives, flash drives, disks, caches, registers, optical data storage media, patterned physical media, or networked versions thereof. The non-temporary computer-readable medium may include multiple structures, which may be located locally or remotely.

[0021] The network interface 216 may include, for example, a network card, a modem, etc., and may be configured to provide data communication (e.g., bidirectional data communication) with a network (e.g., network 114). The network interface 216 may be a wireless interface, a wired interface, or a combination of both. The specific design and implementation of the network interface 216 may depend on the communication network on which the computing device 210 is intended to operate. For example, the network interface 216 may include a wireless local area network (WLAN) card, an integrated services digital network (ISDN) card, a cellular modem, a satellite modem, a modem configured to provide data communication connectivity over the Internet, a network card with an Ethernet port, a device with a radio frequency receiver and transmitter, a device with an optical receiver and transmitter, etc. In some examples, the network interface 216 may be designed to operate over network 114. The network interface 216 may be configured to send and receive electrical signals, electromagnetic signals, or optical signals that can represent various types of data.

[0022] The input device 218 may include, for example, a keyboard, mouse, touchpad, touchscreen, one or more buttons, joystick, microphone, and / or any other device configured to detect and / or receive input. In some examples, the input device 218 may include one or more of various types of sensors, such as an image sensor, temperature sensor, humidity sensor, position sensor, or any other type of sensor. The output device 220 may include, for example, a light indicator, light source, display (e.g., light-emitting diode (LED) display, organic light-emitting diode (OLED) display, liquid crystal display (LCD), or dot matrix display), screen, touchscreen, speaker, headphones, device configured to provide haptic cues, vibrator, and / or any other device configured to provide output.

[0023] Memory 214 can store instructions that, when executed by at least one processor, cause the at least one processor to perform one or more processes described herein. The instructions can include, for example, software instructions, computer programs, computer code, executable instructions, source code, machine instructions, machine language programs, or any other type of instruction for a computing device. The instructions can be based on one or more of various types of desired programming languages and can include (e.g., embody) various processes for using a load set in an energy storage system as described herein.

[0024] FIG. 3 shows an exemplary energy storage unit 310 according to some embodiments of the present disclosure. The energy storage unit 310 can include, for example, a computing device 312, a cooling system 314, one or more sensors 316, and / or one or more batteries (e.g., 318A-318H). The energy storage unit 310 can be an example of one or more of the energy storage units 112A, 112B, 112C. In some examples, the energy storage unit 310 can have a housing, and the components of the energy storage unit 310 can be included within the housing. The housing can be of any desired shape and / or constructed using any desired material. For example, the housing can have a rectangular parallelepiped or cubic shape.

[0025] Computing device 312 can be implemented in a similar manner to computing device 210. Computing device 312 may be located locally with the energy storage unit 310 (for example, within the enclosure of the energy storage unit 310). Computing device 312 may be configured to manage other components of the energy storage unit 310. Computing device 312 may be configured to communicate with other computing devices (for example, user device 116) to manage the energy storage unit 310, either additionally or alternatively. For example, computing device 312 may transmit operational data of the energy storage unit 310 to other computing devices, receive instructions from other computing devices, and execute the received instructions.

[0026] A battery (for example, any of batteries 318A to 318H) may refer to a power source including one or more electrochemical cells with external connections. Batteries 318A to 318H may be rechargeable and can be discharged and recharged multiple times. Batteries 318A to 318H may include one or more of various types of batteries, such as lithium-ion batteries, lithium iron phosphate batteries, silver oxide batteries, nickel-zinc batteries, nickel-metal hydride batteries, lead-acid batteries, nickel-cadmium batteries, lithium nickel-manganese-cobalt oxide (NMC) batteries, lithium nickel-cobalt-aluminum oxide (NCA) batteries, lithium-ion manganese oxide (LMO) batteries, lithium-cobalt oxide batteries, fuel cells, or other types of batteries. Although the energy storage unit 310 is shown to include batteries 318A to 318H, more or fewer batteries may be included in the energy storage unit 310 as needed.

[0027] Batteries 318A to 318H may have associated control components. These control components may be configured, for example, to manage the charging and discharging of batteries 318A to 318H. The control components may include, for example, a battery management system (BMS). In some examples, each of batteries 318A to 318H may have its own control component (e.g., a battery management system). Each control component of batteries 318A to 318H may be implemented by a computing device and / or communicate with a central management component (e.g., implemented by a computing device 312 for the energy storage unit 310). Additionally or alternatively, the central management component may collectively manage the charging and discharging of batteries 318A to 318H. The charging and discharging of batteries 318A-318H can be controlled using appropriate technology such as a circuit with switch control, a charge or discharge controller, a charge or discharge regulator, or a battery regulator, so that batteries 318A-318H may be controlled to receive electricity from a power source at a specific rate, output electricity to a load at a specific rate, or be idle. In some examples, a power conversion system (e.g., to convert alternating current (AC) to direct current (DC), DC to AC, AC to AC, DC to DC, etc.) may be used to couple batteries 318A-318H to a power line (e.g., power line 118).

[0028] The cooling system 314 may include any type of device configured to remove heat from the energy storage unit 310. The cooling system 314 may remove heat using air, liquid, solid material, gaseous material, and / or any other type of suitable medium or material. In some examples, the cooling system 314 may include a heat sink and / or cooling fins. In some examples, the cooling system 314 may include a fan (e.g., for moving air in air cooling), a pump (e.g., for moving liquid in liquid cooling), a compressor (e.g., for vapor compression cooling), or any other type of device for cooling. The cooling system 314 may have any desired configuration (e.g., shape, size, weight, function, etc.) and / or may be arranged, oriented or distributed in relation to the energy storage unit 310 in any desired manner. In some examples, each of the batteries 318A-318H may have a cooling element individually associated with the battery as part of the cooling system 314.

[0029] One or more sensors 316 may include any type of sensor configured to collect information related to the energy storage unit 310 (e.g., to measure its operation). For example, sensor(s) 316 may include temperature sensors, humidity sensors, position sensors, current sensors, voltage sensors, and / or other types of sensors. Sensor(s) 316 may have any desired configuration (e.g., shape, size, weight, function, etc.) and / or may be arranged, oriented, or distributed in any desired manner in relation to the energy storage unit 310. In some examples, each of the batteries 318A to 318H may have a sensor(s) individually associated with it. For example, each of the batteries 318A to 318H may have an associated temperature sensor configured to measure the temperature of that battery. In some examples, the energy storage unit 310 may include a sensor(s) that may be collectively applicable to the batteries 318A to 318H. For example, a set of batteries 318A-318H may have an airflow sensor configured to measure the airflow rate across all batteries 318A-318H.

[0030] The computing device 312 can communicate with and control the batteries 318A-318H, the cooling system 314, and the sensor(s) 316 (for example, via the control components of each battery). In some examples, the computing device 312 can control the components based on instructions from other computing devices (e.g., user device 116). Additionally or alternatively, data related to the energy storage unit 310 may be collected, including, for example, data measured by the sensor(s) 316, data used by the energy storage unit 310 (e.g., parameters for controlling the batteries 318A-318H, or parameters for controlling the cooling system 314, such as fan speed, pump utilization, or compressor utilization). The collected data may be processed by the computing device 312 and / or other computing devices (e.g., user device 116) for one or more embodiments described herein.

[0031] Embodiments disclosed, including methods, systems, apparatus, and non-temporary computer-readable media, are good with respect to the use of load sets in an energy storage system. The disclosed embodiments include a system for using load sets in an energy storage system, the system including one or more energy storage units and a computing device including at least one processor and at least one memory, wherein instructions, when executed by at least one processor, cause the computing device to perform the functions described herein. An energy storage system may refer to any system configured to store energy. An example of an energy storage system is described in relation to Figure 1 (e.g., energy storage system 110). An energy storage system may include, for example, one or more energy storage units and / or other suitable components for using, managing, facilitating, or configuring energy storage. An energy storage unit may refer to a physical object for storing energy. An energy storage unit can store energy in one or more of various forms, such as electrochemical, chemical, mechanical, electrical, electromagnetic, biological, and / or thermal. In some examples, an energy storage unit can store energy using a rechargeable battery. An example of an energy storage unit is described in relation to Figure 3. In some embodiments, one or more energy storage units include one or more battery units. In some embodiments, each battery unit of one or more battery units includes a housing containing multiple batteries. The housing may be of any desired shape and / or may be constructed using any desired material. For example, the housing may have a rectangular parallelepiped or cubic shape.

[0032] A load set may refer to any information that can characterize, describe, indicate, or relate to one or more aspects of the operation of energy storage (e.g., an energy storage unit) during a period. A load set may include, for example, information items that can characterize one or more aspects of the load that an energy storage unit may experience during a period. In some examples, a load set may include information items aggregated over a period that can characterize one or more aspects of the load that an energy storage unit may experience during a period in a collective manner (for example, using the occurrence of a counted specific feature). One or more examples of load sets and one or more examples of using load sets are described in more detail below.

[0033] The disclosed embodiments include receiving operational data related to one of one or more energy storage units over a period of time. For example, a computing device (e.g., user device 116, computing devices in energy storage units 112A, 112B, 112C, or any other computing device) may receive operational data related to one of one or more energy storage units over a period of time. The operational data related to an energy storage unit may include any data related to the operation of the energy storage unit. For example, the operational data may include time-series data points of the characteristics of the energy storage unit over a period of time (e.g., temperature, voltage level, charge state, current, etc.). The operational data may be collected and / or transmitted to a computing device in various ways as needed. For example, the operational data may be measured by a sensor (e.g., sensor 316), and the sensor may generate time-series measurement data. In some examples, the operational data may be calculated based on other data (e.g., measurement data). In some examples, the operational data may be extracted from a data storage device that can store data for the operation of the energy storage unit. The period can have any desired length (e.g., 1 day, 2 days, 5 days, 10 days, 20 days, 50 days, 100 days, 200 days, 300 days, etc.).

[0034] In some embodiments, the operating data includes one or more of the following: the temperature of the energy storage unit during each interval of a plurality of intervals in a period; the voltage level of the energy storage unit during each interval of a plurality of intervals in a period; the charge state of the energy storage unit during each interval of a plurality of intervals in a period; or the current of the energy storage unit during each interval of a plurality of intervals in a period. The temperature of the energy storage unit may include, for example, the temperature measured by a sensor (e.g., sensor 316) of the energy storage unit (e.g., 112A-112C, 310); the temperature calculated based on measurements from multiple sensors of the energy storage unit; or any other suitable metric indicating the degree of coldness or heat of the energy storage unit. In some examples, the energy storage unit may be configured to include multiple temperature sensors. For example, each of the multiple temperature sensors may be associated with one of the batteries (e.g., 318A-318H) of the energy storage unit. The temperature of the energy storage unit may be expressed as an aggregate of temperature measurements from the multiple temperature sensors (e.g., the average of the temperature measurements, the maximum temperature measurement, the minimum temperature measurement, or any other statistic or metric). The temperature of the energy storage unit may be determined for each of several intervals of time. In some examples, the operational data may include time-series data points showing the temperature of the energy storage unit for each of several intervals of time.

[0035] The voltage level of an energy storage unit may include, for example, the voltage level between points on the energy storage unit that can be measured by sensors (e.g., external connections, terminals, etc.), or any other suitable metric indicating the voltage associated with the energy storage unit (e.g., 112A-112C, 310). In some examples, the voltage level of an energy storage unit may be a metric determined based on voltage measurements from multiple sensors of the energy storage unit (e.g., sensor 316). For example, the energy storage unit may be configured to include multiple voltage sensors. Each of the multiple voltage sensors may be configured to measure the voltage level of one of the batteries of the energy storage unit (e.g., the voltage level between the terminals of the batteries). The voltage level of the energy storage unit may be expressed as an aggregate of voltage measurements from the multiple voltage sensors (e.g., the average of the voltage measurements, the maximum voltage measurement, the minimum voltage measurement, the sum of the voltage measurements, or any other statistic or metric). The voltage level of the energy storage unit may be determined for each of multiple intervals of time. In some examples, the operational data may include time-series data points showing the voltage level of the energy storage unit for each of several intervals of time.

[0036] The charge state of an energy storage unit (e.g., 112A-112C, 310) may refer to the charge level relative to the energy storage unit's capacity. The charge state of an energy storage unit may be measured in various ways as needed. For example, the charge state of an energy storage unit may be calculated based on the voltage level(s) associated with the energy storage unit (e.g., the voltage level of the energy storage unit, the voltage level of the energy storage unit's battery, etc.). The charge state of an energy storage unit may be determined using a mapping between the voltage level(s) associated with the energy storage unit and the energy storage unit's charge state. As another example, the charge state of an energy storage unit may be calculated based on measurements of current entering and leaving the energy storage unit (e.g., input current or output current). The charge state of an energy storage unit may be calculated based on current measurements and integration over time (e.g., using the Coulomb count method). In some examples, the charge state of an energy storage unit may be determined based on data used to control the energy storage unit to charge or discharge. For example, data related to energy delivery patterns may indicate that, during a given time segment, an energy storage unit may be configured to charge or discharge at a specific rate (e.g., volts per hour, volts per second, amperes per hour, amperes per second, watts per hour, watts per second, etc.). The data can be used to calculate or track the charge state of the energy storage unit. The charge state of the energy storage unit may be determined using any other suitable method, or using a combination of two or more of the methods described above. The charge state of the energy storage unit may be determined for each of several intervals of a period. In some examples, the operational data may include time-series data points indicating the charge state of the energy storage unit for each of several intervals of a period.

[0037] The current of an energy storage unit may include, for example, the amount of current that may flow out of the energy storage unit, the amount of current that may flow into the energy storage unit, or any other appropriate metric indicating the amount of current associated with the energy storage unit. The current of an energy storage unit may be measured, for example, by one or more sensors (e.g., current sensors). Sensors (or more) (e.g., sensor(or more) 316) can measure the current that may flow out of or into appropriate points (or more) on the energy storage unit (e.g., external connections(or more), terminals(or more)). In some examples, current sensors(or more) can measure the current that may flow out of or into each of the batteries of the energy storage unit. The current of an energy storage unit may be determined based on measurements from current sensors of multiple batteries (e.g., aggregated measurements, average of measurements, maximum measurement, minimum measurement, sum of measurements, or any other statistics or metric). The current of an energy storage unit may be determined for each of several intervals of time. In some examples, the operational data may include time-series data points showing the amount of current in the energy storage unit for each of several intervals of time.

[0038] The time intervals of measured, determined, or time-series data points of various aspects of an energy storage unit (e.g., temperature, voltage level, charge state, or current) may have any desired configuration. For example, time intervals of different aspects of an energy storage unit may be the same or have the same configuration (e.g., length). As another example, time intervals of different aspects of an energy storage unit may be different or have different configurations. In some examples, time intervals of particular aspects of an energy storage unit may have the same length or different lengths. Additionally or alternatively, time intervals within a period may have any desired length (e.g., 0.1 seconds, 0.5 seconds, 1 second, 2 seconds, 5 seconds, 10 seconds, 30 seconds, 1 minute, 2 minutes, 5 minutes, etc.). In some examples, time intervals may be determined by dividing the period into several consecutive time segments. In some examples, the operational data may include any other type of relevant data related to the energy storage unit (e.g., humidity in the area where the energy storage unit is located, or energy delivery patterns of the energy storage unit indicating the rate at which the energy storage unit may be configured to charge or discharge during each of multiple time segments). In some examples, the operational data may be collected with respect to any other type of device, component, or element for energy storage (on a scale larger or smaller than the energy storage unit, for example, by collectively collecting operational data for multiple energy storage units, or by individually collecting operational data for batteries within an energy storage unit), and the processes described herein (e.g., processes related to an energy storage unit) may be similarly applicable to any other type of device, component, or element for energy storage.

[0039] Figure 4 shows a flowchart of an exemplary method 400 for using a load set of an energy storage system according to some embodiments of the present disclosure. Referring to Figure 4, in step 410, a computing device may receive operational data related to one of one or more energy storage units for a period of time. Method 400 may be performed by any computing device (e.g., user device 116, computing devices in energy storage units 112A, 112B, 112C, computing device 210, computing device 312, computing devices associated with energy storage system 110, and / or any other computing device).

[0040] The disclosed embodiments include determining one or more charge and discharge cycles of an energy storage unit during a period. For example, a computing device may identify charge and discharge cycles of an energy storage unit during a particular period. A charge and discharge cycle may refer to a set of events including charging the energy storage, discharging the energy storage, and / or an idle state of the energy storage (e.g., neither charging nor discharging). Charging the energy storage may include, for example, the energy storage receiving energy. Charging the energy storage may also include, for example, the energy storage outputting energy. A cycle including a set of events of charging, discharging, and / or an idle state may have any desired number of events and / or events in any desired order. For example, a cycle may include a time segment of charging followed by a time segment of discharging. Another example is a cycle including a time segment of discharging followed by a time segment of charging. In some examples, a cycle may include charge and discharge time segments separated by an idle state time segment. In some examples, a cycle may include multiple time segments of charging, multiple time segments of discharging, and / or multiple time segments of an idle state.

[0041] A computing device may identify one or more charge and discharge cycles of an energy storage unit during a given period using one or more methods. One or more charge and discharge cycles may be determined based on operational data associated with the energy storage unit. For example, one or more charge and discharge cycles may be determined using time-series data points indicating the charge state of the energy storage unit. An increase in the charge state of the energy storage unit may indicate charging of the energy storage unit, and a decrease in the charge state of the energy storage unit may indicate discharging of the energy storage unit. As an example, a computing device may use charge state data to identify cycles, each cycle may include a time segment for charging and a time segment for discharging. By processing time-series charge state data, the occurrence of one or more charge and discharge cycles can be identified. In some examples, one or more charge and discharge cycles may be identified using other types of appropriate data associated with the energy storage unit (e.g., data indicating when the energy storage unit may be charged or discharged).

[0042] The disclosed embodiments include determining one or more charge and discharge cycles of an energy storage unit during a period using a rainflow counting algorithm. For example, a computing device may include determining one or more charge and discharge cycles of an energy storage unit during a period using a rainflow counting algorithm. The rainflow counting algorithm may use data indicating the charge state of the energy storage unit during a period (e.g., time-series data points indicating the charge state during a period). The rainflow algorithm may use the pagoda roof method, the four-point method, or any other desired method.

[0043] Figure 7 shows an example diagram for determining charge and discharge cycles according to some embodiments of the present disclosure. Referring to Figure 7, as an example, using the pagoda roof method, time-series data points indicating the charge state of an energy storage unit over a period of time can be represented using a two-dimensional coordinate system 700. The x-axis of the coordinate system 700 may represent time, and the y-axis of the coordinate system 700 may represent the charge state of the energy storage unit (e.g., 0% to 100%). The data on the charge state of the energy storage unit over a period of time may be represented as several line segments 710 (e.g., analogous to a series of piecewise linear functions) within the coordinate system 700, or processed to be represented as such. The line segments 710 may, for example, indicate an increase, decrease, or no change in the charge state of the energy storage unit over a time unit, and / or, for example, indicate a charge, discharge, or idle state of the energy storage unit over a time unit. Using the pagoda roof method, coordinate system 700 and line segment 710 within it (for example, grouped together as an image) can be rotated 90 degrees clockwise to generate Figure 750. Line segment 780 in Figure 750 (corresponding to line segment 710) may be treated as a series of pagoda roofs. The pagoda roof method may consider the flow of water flowing down a series of pagoda roofs. Areas where water may not flow may identify cycles that can be seen as interruptions to other cycles. The pagoda roof method may include considering the flow of water or rain starting from each consecutive extreme point (for example, a maximum or minimum point such as point A or point D in Figure 750). The pagoda roof method may include identifying load reversals (e.g., half-cycles) by allowing each rainflow to continue dripping from the roof until it falls opposite a larger maximum point (or a smaller minimum point), until it encounters a flow above or before it falls, or until the rainflow falls below the roof. The pagoda roof method may involve identifying each hysteresis loop (e.g., the entire cycle) by pairing identically counted inversions (e.g., inversions with the same magnitude and opposite direction).For example, water flow 760 starts at point A in Figure 750, drips down the roof through points B and D, and the reversal from point A to point D can be identified as a half-cycle. Water flow 766 starts at point D in Figure 750, drips down the roof through point E, and the reversal from point D to point E can be identified as a half-cycle. For example, water flow 762 starts at point B in Figure 750, drips down the roof through point C, and the reversal from point B to point C (reversal BC) can be identified as a half-cycle. Water flow 764 starts at point C in Figure 750, drips down the roof to a specific point in Figure 750 having a charge state of the same size as point B, and the reversal from point C to a specific point corresponding to point B (reversal CB) can be identified as a half-cycle. The entire cycle between one charge state (e.g., point B) and another charge state (e.g., point C) may be identified by pairing reversal BC and reversal CB.

[0044] A rainflow counting algorithm (e.g., the pagoda roof method) may be used to identify one or more charge and discharge cycles of an energy storage unit during a period. The identified one or more charge and discharge cycles may include one or more of the various types of cycles determined using the rainflow counting algorithm (e.g., a full cycle determined using the rainflow counting algorithm, a half cycle determined using the rainflow counting algorithm, etc.). For example, the identified one or more charge and discharge cycles may include a full cycle determined using the rainflow counting algorithm and a half cycle determined using the rainflow counting algorithm (e.g., each of these half cycles cannot be paired with other half cycles to form a full cycle, and / or is not included in any full cycle after all full cycles have been determined). As another example, the identified one or more charge and discharge cycles may include a full cycle determined using the rainflow counting algorithm. As yet another example, the identified one or more charge and discharge cycles may include a half cycle determined using the rainflow counting algorithm. Referring to Figure 4, in step 412, the computing device can determine one or more charge and discharge cycles of the energy storage unit that may occur during the period.

[0045] The disclosed embodiments include generating a plurality of load sets based on operational data. For example, a computing device can generate a plurality of load sets based on operational data related to an energy storage unit. A load set may refer to any information that can characterize, describe, indicate, or relate to one or more aspects of the operation of energy storage (e.g., an energy storage unit) over a period of time. A load set may include, for example, information items that can characterize one or more aspects of the load that the energy storage unit may experience over a period of time (e.g., the amount of energy or power input or output). In some examples, a load set may include information items aggregated over a period of time that can characterize one or more aspects of the load that the energy storage unit may experience over a period of time in a collective manner (e.g., using the occurrence of a particular feature(s) that has been counted).

[0046] In some embodiments, each load set of a plurality of load sets includes one or more criteria related to the operation of an energy storage unit, and a number of cycles among one or more determined charge and discharge cycles of the energy storage unit during a period that satisfy one or more criteria. The criteria related to the operation of the energy storage unit may refer to any type of rule, standard, pattern, or principle related to the operation of the energy storage unit. The characteristics, traits, or properties of one or more cycles (calculated, for example, based on operational data related to the energy storage unit during the time range of the cycle) may be compared to the criteria to determine whether the cycle satisfies the criteria.

[0047] In some embodiments, one or more criteria related to the operation of the energy storage unit include one or more of the following: a temperature range of the energy storage unit, a voltage level range of the energy storage unit, a minimum charge state range of the energy storage unit, a maximum charge state range of the energy storage unit, a total current range of the energy storage unit, a sum of the squares of the currents of the energy storage unit during a time segment, a current range of the energy storage unit, or a charge depth range of the energy storage unit. With respect to the temperature range of the energy storage unit, temperature may refer to any type of indication of the coolness or heat of the energy storage unit, such as the average temperature of the energy storage unit during a time range of the cycle, some or all of the (e.g., time-series) temperature data points of the energy storage unit during a time range of the cycle, or any other statistic or metric. Determining whether a charge-discharge cycle satisfies a criterion based on the temperature range of the energy storage unit may include determining whether the temperature of the energy storage unit during the cycle (determined, for example, based on operational data for the time range of the cycle) falls within the temperature range defined by the criterion.

[0048] With respect to the voltage level range of an energy storage unit, the voltage level may refer to any type of voltage representation of the energy storage unit, such as the average voltage level of the energy storage unit over a cycle time range, some or all of the (e.g., time-series) voltage level data points of the energy storage unit over a cycle time range, or any other statistics or metrics. Determining whether a charge and discharge cycle meets a criterion based on the voltage level range of the energy storage unit may include determining whether the voltage level of the energy storage unit during the cycle (determined, for example, based on operating data over a cycle time range) falls within the voltage level range defined by the criterion.

[0049] With respect to the range of minimum charge states of an energy storage unit, the minimum charge state may refer, for example, to the minimum value of the charge state of the energy storage unit during the cycle time range. Determining whether a charge and discharge cycle satisfies a criterion based on the range of minimum charge states of the energy storage unit may include determining whether the minimum charge state of the energy storage unit during the cycle (determined, for example, based on operational data during the cycle time range) falls within the range of minimum charge states defined by the criterion.

[0050] With respect to the range of maximum charge states of an energy storage unit, the maximum charge state may refer, for example, to the maximum value of the charge state of the energy storage unit during the cycle time range. Determining whether a charge and discharge cycle meets a criterion based on the range of maximum charge states of the energy storage unit may include determining whether the maximum charge state of the energy storage unit during the cycle (determined, for example, based on operational data during the cycle time range) falls within the range of maximum charge states defined by the criterion.

[0051] With respect to the range of the total current of the energy storage unit, the total current may refer, for example, to the sum of the data points (e.g., time series) of the energy storage unit's current, or to the sum of the absolute values ​​of each data point (e.g., time series) of the energy storage unit's current during the cycle's time range. Determining whether a charge and discharge cycle meets a criterion based on the range of the total current of the energy storage unit may include determining whether the total current of the energy storage unit during the cycle (determined, for example, based on operational data during the cycle's time range) falls within the range of the total current defined by the criterion.

[0052] With respect to the range of the sum of the squares of the currents of the energy storage unit in a time segment, the sum of the squares of the currents may refer, for example, to the sum of the squares of the currents of the energy storage unit at each data point (e.g., in a time series) during the time range of the cycle, and the sum of the squares of the currents in a time segment may refer, for example, to the sum (of the squares of the currents) divided by the length of the time range of the cycle. Determining whether a charge and discharge cycle satisfies a criterion based on the range of the sum of the squares of the currents of the energy storage unit in a time segment may include determining whether the sum of the squares of the currents of the energy storage unit in a time segment of the cycle (determined, for example, based on the operating data of the time range of the cycle) falls within the range of the sum of the squares of the currents defined by the criterion.

[0053] With respect to the current range of an energy storage unit, current may refer to any type of current representation related to the energy storage unit, such as the average of (e.g., time-series) data points of the current of the energy storage unit over a cycle time range, the average of the absolute values ​​of each (e.g., time-series) data point of the current of the energy storage unit over a cycle time range, some or all of the (e.g., time-series) data points of the current of the energy storage unit over a cycle time range, some or all of the absolute values ​​of the (e.g., time-series) data points of the current of the energy storage unit over a cycle time range, or any other statistic or metric. In some examples, two or more criteria related to current may be used separately for charging or discharging the energy storage unit. Determining whether a charge and discharge cycle satisfies a criterion based on the current range of the energy storage unit may include determining whether the current of the energy storage unit during the cycle (determined, for example, based on operating data over a cycle time range) falls within the current range defined by the criterion.

[0054] With respect to the range of the charge depth of an energy storage unit, the charge depth may refer, for example, to the difference between the maximum charge state of the energy storage unit during the cycle time range and the minimum charge state of the energy storage unit during the cycle time range. Determining whether a charge and discharge cycle meets a criterion based on the range of the charge depth of the energy storage unit may include determining whether the charge depth of the energy storage unit during the cycle (determined, for example, based on operational data during the cycle time range) falls within the charge depth range defined by the criterion.

[0055] One or more sets of criteria for each load set of a group of load sets may differ from one or more sets of criteria for other load sets of the group. In some embodiments, one or more criteria related to the operation of an energy storage unit for a first load set of the group of load sets may differ from one or more criteria related to the operation of an energy storage unit for a second load set of the group of load sets. For example, one or more sets of criteria for the first load set may include a temperature range of 20 to 22°C, a voltage level range of 720 to 740 volts, a maximum charge state range of 80% to 90%, a minimum charge state range of 0% to 10%, and / or a total current range of 1 to 1200 amperes. In contrast, one or more sets of criteria for the second load set may include a temperature range of 24 to 26°C, a voltage level range of 760 to 780 volts, a maximum charge state range of 80% to 90%, a minimum charge state range of 0% to 10%, and / or a total current range of 1200 to 2400 amperes. A computing device may determine one or more different sets of criteria for multiple load sets (for example, based on input from an operator of an energy storage unit).

[0056] In some examples, outer boundaries may be specified for each type of one or more criteria (for example, a temperature-related criterion may have a lower limit of 20°C and an upper limit of 30°C, a voltage-level-related criterion may have a lower limit of 700 volts and an upper limit of 800 volts), and the span between the outer boundaries may be divided into several ranges (for example, the 20-30°C span of a temperature criterion may be divided into the ranges of 20-22°C, 22-24°C, 24-26°C, 26-28°C, and 28-30°C, and the 700-800 volts span of a voltage-level criterion may be divided into the ranges of 700-720 volts, 720-740 volts, 740-760 volts, 760-780 volts, and 780-800 volts). A variety of sets of one or more criteria may be generated by selecting range options for each type of criterion in the set, for each set of the variety of criteria, and each criterion type may have several range options (for example, a temperature criterion may have range options of 20-22°C, 22-24°C, 24-26°C, 26-28°C, and 28-30°C; a voltage level criterion may have range options of 700-720 volts, 720-740 volts, 740-760 volts, 760-780 volts, and 780-800 volts, etc.). In some examples, multiple types of criteria may be included in a set, so the total number of generated sets can be calculated according to the rules of multiplication. In some examples, some or all of the generated sets may be used for a load set.

[0057] To generate a specific load set, the computing device may, for example, determine the time range for each cycle (e.g., one or more determined cycles) of charging and discharging the energy storage unit during a period, and determine the operational data (e.g., temperature, voltage level, charge state, current) associated with the energy storage unit for each cycle's time range (e.g., the span between a first time instance and a second time instance). For each cycle, the computing device may, based on the cycle's operational data, determine metrics that can be compared with respect to one or more criteria associated with the specific load set. For example, based on the cycle's operational data, the computing device may determine the cycle's metrics (e.g., the temperature of the energy storage unit for the cycle, the voltage level of the energy storage unit for the cycle, etc.). The computing device may compare the determined metrics of the cycle with respect to one or more corresponding criteria of the specific load set to determine whether each of the determined metrics satisfies the corresponding criteria of the specific load set (e.g., by determining whether the value of the metric falls within the range of the corresponding criteria). If each of the determined metrics for a cycle satisfies the corresponding criterion of one or more criteria for a particular load set, the computing device may determine that the cycle satisfies one or more criteria for that particular load set and may increment the number of counted cycles that satisfy one or more criteria for that particular load set by one (1). If each of the determined metrics for a cycle does not satisfy the corresponding criterion of one or more criteria for a particular load set, the computing device may determine that the cycle does not satisfy one or more criteria for that particular load set and may not increment the number of counted cycles for that particular load set. The computing device may perform the above process for each cycle of one or more determined cycles of charging and discharging the energy storage unit during the period to determine the number (or quantity) of cycles that satisfy one or more criteria for a particular load set.A computing device may similarly determine other load sets among multiple load sets (for example, by determining the amount (or number) of cycles that satisfy one or more criteria for each of the other load sets).

[0058] Figure 5 shows examples of load sets 500 according to some embodiments of the present disclosure. Criteria 510 of load set 500 (for example, of an energy storage unit over a period of time) may include, for example, a range of temperatures of the energy storage unit (expressed in degrees Celsius), a range of voltage levels of the energy storage unit (expressed in volts), a range of minimum charge states of the energy storage unit (expressed in percentages), a range of maximum charge states of the energy storage unit (expressed in percentages), and a range of total currents of the energy storage unit (expressed in amperes). Indication 512 indicates the number of cycles (e.g., number or count) that can satisfy the corresponding criterion. Load set 500 may include several load sets (e.g., based on different combinations of each criterion having various options for range or value). Examples of load sets may include load sets 514A, 514B, 514C, 514D, 514E, 514F (e.g., shown as different rows in the table in Figure 5). For example, the criteria for load set 514D may include a temperature range of 24–26 degrees Celsius for the energy storage units, a voltage level range of 800–820 volts for the energy storage units, a minimum charge state range of 20%–30% for the energy storage units, a maximum charge state range of 50%–60% for the energy storage units, and a total current range of 4800–6000 amperes for the energy storage units. Load set 514D may also include a number of cycles (e.g., a number or count) (e.g., 95 cycles) that can satisfy the criteria for load set 514D (for example, each of the 95 cycles may have a metric that can be determined based on the operating data of the energy storage units for that cycle, and each of the metrics may fall within the range of the corresponding criterion among the criteria for load set 514D).

[0059] In some examples, one or more criteria for the load set may include a range of temperatures for the energy storage unit, a range of voltage levels for the energy storage unit, a range of minimum charge states for the energy storage unit, a range of maximum charge states for the energy storage unit, and a range of total current (absolute value of current) for the energy storage unit. One or more criteria for the load set may incorporate information about the energy storage unit's processing capacity.

[0060] In some examples, one or more criteria associated with a load set may include a range of temperatures for the energy storage unit, a range of voltage levels for the energy storage unit, a range of depths of charge for the energy storage unit, and a range of the sum of the squares of the currents of the energy storage unit during a given time segment (e.g., the sum of the squares of the currents divided by the length of the cycle time range).

[0061] Additionally or alternatively, the load set may be any other desired form. For example, the criteria associated with the load set may include, or consist of, ranges for temperature, voltage level, charge depth, current for charging, and current for discharging of the energy storage unit. In some examples, the load set may represent a cycle quantity that has a particular maximum charge state and a particular minimum charge state (or has a maximum charge state that falls within a particular range and a minimum charge state that falls within a particular range). In some examples, the load set may include one or more criteria and a counted quantity of time intervals or time instances, where for each time interval of a time interval, or for each time instance of a time instance, data points associated with the energy storage unit may satisfy one or more criteria (for example, data points may include time-series temperature data points and time-series voltage level data points, and one or more criteria may include temperature ranges and voltage level ranges). In some examples, the load set may represent a quantity of data points that can satisfy one or more criteria for one or more aspects associated with the energy storage unit (for example, a quantity of temperature data points that fall within a temperature range).

[0062] Referring to Figure 4, in step 414, the computing device may generate multiple load sets based on the operational data. Each load set may include one or more criteria related to the operation of the energy storage unit and one or more cycles that satisfy one or more criteria (e.g., one or more cycles from the total number of cycles identified in step 412 that satisfy one or more criteria).

[0063] The disclosed embodiments include determining one or more operating parameters of an energy storage unit for a given period. For example, a computing device may determine one or more operating parameters of an energy storage unit for a given period. One or more operating parameters may be determined, for example, based on operating data and / or other suitable data related to the energy storage unit for a given period. The operating parameters may include any type of information related to the operation of energy storage (e.g., an energy storage unit). In some embodiments, one or more operating parameters of an energy storage unit include one or more of the following, determined using a rainflow counting algorithm: the number of charge and discharge cycles of the energy storage unit during a period, the number of equivalent total charge and discharge cycles of the energy storage unit during a period, the total current of the energy storage unit during a period, the average charge state of the energy storage unit during a period, the length of the period, or the capacity of the energy storage unit at the beginning of the period. For example, a computing device may determine the charge and discharge cycles of an energy storage unit using a rainflow counting algorithm based on operating data related to the energy storage unit for a given period (e.g., data indicating the charge state of the energy storage unit during a given period). A computing device can count the determined number of cycles as an operating parameter (for example, it can determine the total number or count of determined cycles).

[0064] As another example, a computing device may determine the operating parameters of an energy storage unit as the amount of equivalent total cycles of charging and discharging the energy storage unit over a period of time. The amount of equivalent total cycles may refer, for example, to a measured value of the energy storage unit's capacity. The amount of equivalent total cycles may include the number of cycles in which the energy storage unit is fully charged to its capacity (e.g., charged to about 100% of its capacity) and fully discharged (e.g., discharged to about 0% of its capacity). Based on operating data related to the energy storage unit for a period of time (e.g., data indicating the charge state of the energy storage unit over a period of time), a computing device can determine the amount (e.g., number) of equivalent total cycles in which charging and discharging of the energy storage unit over a period of time may be equivalent. For example, a computing device can determine a first sum of the rate of change of the charge state of the energy storage unit for charging, and a second sum of the rate of change of the charge state of the energy storage unit for discharging. The computing device can determine the number of equivalent total cycles that may correspond to the first and second sums.

[0065] In some embodiments, the computing device can determine the operating parameters of an energy storage unit as the sum of the currents of the energy storage unit over a period of time (e.g., the sum of the absolute values ​​of the data points (e.g., time series) of the currents of the energy storage unit over a period of time). In some embodiments, the computing device can determine the operating parameters of an energy storage unit as the average charge state of the energy storage unit over a period of time (e.g., the average of the data points (e.g., time series) of the charge state of the energy storage unit over a period of time). In some embodiments, the computing device can determine the operating parameters of an energy storage unit as the length of a period (e.g., 1 day, 2 days, 5 days, 10 days, 20 days, 50 days, 100 days, 200 days, 300 days, etc.). The determined length of a period may be expressed in any desired way (e.g., seconds, minutes, hours, days, months, years, etc.).

[0066] In some embodiments, the computing device can determine the operating parameters of an energy storage unit as the capacity of the energy storage unit at the start of a period. The capacity of the energy storage unit at the start of a period may include, for example, the capacity of the energy storage unit measured at the start of the period. For example, at the start of a period, the energy storage unit may be fully charged (e.g., to 100% of its capacity) and then fully discharged (e.g., to 0% of its capacity), and the amount of energy output by the energy storage unit during this discharge may correspond to the measured capacity of the energy storage unit at the start of the period. The capacity of the energy storage unit at the start of a period may be measured by any other desired method. In some examples, the capacity of the energy storage unit at the start of a period may include the predicted capacity of the energy storage unit at the start of a period (a predicted capacity determined using any desired method, such as using the process described herein). For example, the predicted capacity of the energy storage unit at the start of a period may be determined using historical data from prior to the period. Referring to Figure 4, in step 416, the computing device may determine one or more operating parameters of the energy storage unit for a given period.

[0067] The disclosed embodiments include providing a machine learning model with one or more operating parameters and one or more load sets from a plurality of load sets. For example, a computing device may provide a machine learning model with one or more operating parameters and one or more load sets from a plurality of load sets. In some examples, a computing device may optionally provide a subset of one or more operating parameters and one or more load sets from a plurality of load sets. For example, a computing device may create data of operating parameters and load sets available to the machine learning model and / or make the machine learning model able to access the data. In some embodiments, the machine learning model includes a model based on a support vector machine (SVM), a relational vector machine (RVM), or extreme gradient boosting (XGBoost). In some examples, the machine learning model may include a support vector machine with a Gaussian kernel. In some examples, the machine learning model may include a linear relational vector machine (e.g., with a Gaussian kernel) or a nonlinear relational vector machine (e.g., with a Gaussian kernel). Additionally or alternatively, the machine learning model may include any type of suitable model for generating predictions related to energy storage units based on input data.

[0068] One or more load sets provided to a machine learning model for processing may comprise some or all of a plurality of generated load sets. In some embodiments, one or more load sets comprise a subset of a plurality of load sets. For example, some of the plurality of load sets may be provided to and / or processed by the machine learning model, while the remaining parts of the plurality of load sets may not be provided to and / or processed by the machine learning model. The disclosed embodiments include determining one or more load sets from a plurality of load sets based on a feature reduction technique. For example, a computing device may determine one or more load sets from a plurality of load sets based on a feature reduction technique. A feature reduction technique may refer to any method or process that can enable the reduction of data items (e.g., features) as input to a machine learning model. The machine learning model may receive data related to the load sets as input to the machine learning model (e.g., cycle quantities shown in a load set may be input to the machine learning model and used to set values ​​for input nodes of the machine learning model). A feature reduction technique may enable the determination of a reduced amount of load sets from a plurality of load sets to be used or processed by the machine learning model. Using feature reduction techniques, one or more loading sets provided to a machine learning model may be determined to be a reduced set (e.g., a subset) of loading sets from multiple loading sets. Feature reduction techniques can enable machine learning models to have fewer input variables, which can offer the advantage of reducing the computational complexity associated with the machine learning model.

[0069] Feature reduction techniques may include, for example, one or more of various types of appropriate processes. For example, a load set may not be included in the reduced set of load sets if it is considered insignificant in relation to the magnitude of its indicated cycle quantity. For example, a load set may not be included in the reduced set of load sets if the value of the quantity indicated by the load set (e.g., the number of cycles) (determined repeatedly, e.g., for each of the various periods or for each of the various energy storage units) does not meet (e.g., does not meet or exceed) a threshold (e.g., 2, 3, 5, 10, 20, or any other desired number).

[0070] In some examples, different types of feature reduction techniques may be used for different types of machine learning models. For example, the least absolute shrinkage and selection operator (LASSO) can be used as a regression analysis method. A penalty may be introduced to a linear regression model (e.g., based on L1 regularization) so that weak features have coefficients of zero (0). Additionally or alternatively, in the case of tree-based methods, when training a random forest or gradient boosted model, the amount by which each feature can reduce the weighted impurity (e.g., corresponding to the variance in the case of regression) of each tree may be calculated. The impurity reduction by each feature can then be averaged across all trees. This average may be considered the importance of the features and may be used to rank the features. The computing device may be configured to set a threshold (e.g., mean feature importance score) and remove any features below the threshold. This may be applicable to various types of models, such as random forest models or extreme gradient boosting (XGBoost) models. Additionally or alternatively, in the case of recursive methods, recursive feature elimination can remove features by testing a linear model with progressively fewer features. This may start with the complete dataset, train a linear model, compute coefficients, and then remove the least important features (e.g., those associated with the lowest coefficients). This procedure may be repeated recursively until the desired number of features to be selected is reached. In some examples, a support vector machine with a linear kernel may be used as the machine learning model.

[0071] The reduced set of load sets may be determined based on the use of one or more feature reduction techniques (e.g., those described above). In some examples, the reduced set of load sets may be determined based on the use of a single feature reduction technique. In some examples, the reduced set of load sets may be determined based on applying multiple passes of feature reduction techniques. In some examples, the reduced set of load sets may be determined based on selecting load sets that can be selected by two or more applied feature reduction techniques.

[0072] In some examples, a categorical variable may be created for the location of an energy storage unit (e.g., site) and may be used as input to a machine learning model. The categorical variable may, for example, represent the location of an energy storage unit. In some examples, one location may be mapped to the categorical variable. In some examples, multiple locations (e.g., associated with different energy storage units) may be mapped to the categorical variable. In some examples, one location may be mapped to multiple categorical variables (e.g., based on multiple characteristics that the location may be associated with, such as latitude, longitude, climate classification, meteorological statistics, type or configuration of energy storage). A machine learning model can accept categorical variables as input.

[0073] Referring to Figure 4, in step 418, the computing device can provide the machine learning model with one or more operating parameters and one or more load sets from a plurality of load sets.

[0074] The disclosed embodiments include generating a predicted capacity of an energy storage unit at the end of a period based on a machine learning model. For example, a computing device can generate a predicted capacity of an energy storage unit at the end of a period based on a machine learning model. The predicted capacity may be generated based on the machine learning model processing the data it receives (e.g., operating parameters, load sets, categorical variables, etc.). For example, the machine learning model may include several input nodes, one or more intermediate nodes, and an output node (relationships or interconnections between nodes may be configured during training of the machine learning model). Each of the input nodes may correspond to a specific item of the received data. In the case of an input node corresponding to a load set (e.g., a reduced set of load sets), the value of each input node may be set to the value of the cycle amount shown in the corresponding load set. Input nodes for other types of data items (e.g., operating parameters or categorical variables) may be set to the value associated with the corresponding data item. Based on the relationships or interconnections between the nodes of the machine learning model, input values ​​to input nodes may trigger other nodes of the machine learning model to cause an output node to generate a value corresponding to the predicted capacity of the energy storage unit at the end of a period. The capacity of the energy storage unit may refer to, for example, the maximum amount of energy that the energy storage unit can store at a given time (for example, the capacity may be expressed in any desired way, such as using megawatt-hours (MWh)). Referring to Figure 4, in step 420, the computing device can generate a predicted capacity of the energy storage unit at the end of the period based on a machine learning model.

[0075] The disclosed embodiments include configuring one or more energy storage units based on predicted capacity. For example, a computing device may configure one or more energy storage units based on predicted capacity. Configuring one or more energy storage units based on predicted capacity may include any desired process or action relating to one or more energy storage units. The disclosed embodiments include configuring one or more energy storage units by one or more of the following: adjusting the pattern of one or more energy storage units discharging electricity, or increasing the capacity of one or more energy storage units, based on predicted capacity. For example, a computing device may configure one or more energy storage units by one or more of the following: adjusting the pattern of one or more energy storage units discharging electricity, or increasing the capacity of one or more energy storage units, based on predicted capacity. In some embodiments, the pattern includes a plurality of time intervals in which one or more energy storage units are configured to charge or discharge at a particular rate. Additionally or alternatively, the pattern may illustrate how one or more energy storage units may be configured to input or output electricity. For example, if the predicted capacity indicates a decrease from the previous capacity of an energy storage unit, and that decrease meets a threshold for the rate of capacity reduction (e.g., it meets or exceeds the threshold), the computing device can determine that the energy storage unit may be overutilized and / or adjust the pattern for supplying electricity (e.g., input and / or output) to reduce the usage of the energy storage unit and / or reduce the rate at which the capacity of the energy storage unit may be reduced. In some examples, the computing device can trigger capacity increases in one or more energy storage units based on the predicted capacity of the energy storage units.For example, based on the determination that the predicted capacity is below a threshold capacity, the computing device may determine that one or more energy storage units can be increased in capacity. In some examples, the computing device may send a notification regarding the capacity increase (e.g., to the operator of the energy storage unit) and / or trigger the purchase or acquisition of additional energy storage (e.g., energy storage unit(s)) to be added to the group of one or more energy storage units so that the capacity can be increased. Referring to Figure 4, in step 422, the computing device may configure one or more energy storage units based on the predicted capacity.

[0076] The disclosed embodiments include training a machine learning model using historical data, which includes one or more of the following: load sets of energy storage units for previous periods prior to the current period, operating parameters of energy storage units for previous periods, or measured capacities of energy storage units at the end of previous periods. For example, a computing device can train a machine learning model using historical data. Training the machine learning model may use any suitable training algorithm. The dataset for training the machine learning model may be based, for example, on historical data relating to the operation of energy storage units for previous periods (which may be used to compute load sets, operating parameters, etc.) and measured capacities of energy storage units at the end of each previous period. Inputs to the machine learning model may include operating parameters, load sets, and / or categorical variables relating to energy storage units, and the machine learning model may output predicted capacities of energy storage units at the end of periods. Training the machine learning model may include, for example, supervised learning. Training a machine learning model may include, for example, modifying the parameters of the machine learning model so that the machine learning model can generate an output that approaches the capacity of the energy storage unit at the end of a period shown in the historical data (e.g., a predicted capacity at the end of a period) (e.g., an output that approaches the measured capacity of the energy storage unit at the end of a period) based on a particular input dataset. Additionally or alternatively, validation and testing of the trained machine learning model may be performed, for example, using a validation dataset or a test dataset. The validation dataset or test dataset may be established in a similar manner to the training dataset (e.g., using historical data related to the energy storage unit).

[0077] In some examples, multiple machine learning models (e.g., of the same or different types) can be trained, and one or more machine learning models may be selected for use from among the trained models based on their respective performance scores (e.g., selecting one or more machine learning models with the highest performance score(s)). The performance scores may include any appropriate metric for evaluating the performance of the machine learning models (e.g., mean absolute percentage error (MAPE), coefficient of determination (e.g., the R-squared metric)). In some examples, the hyperparameters of the machine learning model (e.g., aspects of the structure of the machine learning model, such as the number, composition, and / or structure of the nodes, layers, trees, and / or other elements the machine learning model may contain, or aspects of the learning process of the machine learning model, such as the learning rate, which may indicate the step size at each iteration while moving toward the minimum of the loss function) may be tuned to improve the performance score of the machine learning model. In some examples, a machine learning model (e.g., trained) may be tested, and its performance (e.g., performance score) may be evaluated based on comparing the predictions of the machine learning model with predictions generated using other suitable models (e.g., an autoregressive integral moving average (ARIMA) model that can predict the future capacity of energy storage units using time-series historical data of the capacity of energy storage units).

[0078] The disclosed embodiments include calculating the degree of influence of each of several input items to a machine learning model on the output of the machine learning model. For example, a computing device can calculate the degree of influence of each of several input items to a machine learning model on the output of the machine learning model. Input items to a machine learning model may include, for example, data corresponding to the input nodes of the machine learning model. Outputs of a machine learning model may include, for example, data corresponding to the output nodes of the machine learning model. The degree of influence may refer to, for example, the degree of any type of effect, influence, control, guidance, or direction that an input item to a machine learning model may have on the output of the machine learning model. In some examples, the change may be applied to each of several input items to the machine learning model, and the output change of the machine learning model corresponding to the change to each input item may be determined. The output change corresponding to the change to each input item may indicate the degree of influence of the input item on the output of the machine learning model (for example, compared to other input items of the several input items). In some examples, a Shapley value may be calculated for each input item to the machine learning model to determine the degree of influence of the input item on the output of the machine learning model. Other suitable methods may be used to determine the degree of influence.

[0079] Figure 6 shows an exemplary user interface 610 relating to the use of a load assembly in an energy storage system according to some embodiments of the present disclosure. In the user interface 610, display 612 may identify an energy storage unit (e.g., an energy storage unit identified as unit B located at site A). Display 614 may indicate a time range (e.g., 1.15.2022 to 4.15.2022) for which the predicted capacity of the energy storage unit (e.g., the predicted capacity of the energy storage unit at the end of the period) may be generated. Display 616 may indicate the predicted capacity of the energy storage unit at the end of the period (e.g., 756.32 kWh (kilowatt-hours)). Display 618 may indicate a model type (e.g., a support vector machine) of a machine learning model that can be used to generate the predicted capacity.

[0080] Display 620 may indicate the degree of influence of each input item to the machine learning model on the output of the machine learning model (e.g., predicted capacity). For example, Display 620 may indicate the degree of influence (e.g., Shapley value) for each input item to the machine learning model, such as operating parameters, load sets, or categorical variables. Operating parameters may include, for example, "total current" (e.g., total current of the energy storage unit during the period), "cycle amount" (e.g., the number of charge and discharge cycles of the energy storage unit during the period, determined using a rainflow counting algorithm), "average charge state" (e.g., the average charge state of the energy storage unit during the period), "equivalent total cycle amount" (e.g., the equivalent total charge and discharge cycle amount of the energy storage unit during the period), and "previous capacity" (e.g., the capacity of the energy storage unit at the beginning of the period). The load sets may include, for example, "24.0_780.0_50.0_90.0_2400.0", "24.0_800.0_0.0_90.0_0.0", "26.0_720.0_0.0_90.0_10000.0", or other labels similarly indicated. Each label may sequentially indicate the lower limit values ​​of each criterion for the load set (e.g., the lower limit of the energy storage unit temperature range, the lower limit of the energy storage unit voltage range, the lower limit of the energy storage unit minimum charge state range, the lower limit of the energy storage unit maximum charge state range, and the lower limit of the total current (e.g., absolute value of current) range of the energy storage unit). Categorical variables may include, for example, "Site A" (indicating the location of the energy storage unit).

[0081] Display 622 may indicate the magnitude of the degree of influence (e.g., Shapley value) for each input item to the machine learning model, or for each input item. In some examples, the influence of an input item (e.g., which may positively contribute to the output of the machine learning model) may be shown using, for example, one type of display (e.g., a filled bar), and / or other influences of an input item (e.g., which may negatively contribute to the output of the machine learning model) may be shown using, for example, any other type of display (e.g., an empty bar). Any other desired method of showing the influence of an input item may be used. User interface 610 is a unique interface that can bring together various items on a single display, allowing the user to view them comprehensively. In some examples, user interface 610 may be dynamic and / or may automatically update when the content of any of displays 612, 614, 616, 618, 620, or 622 changes. In some examples, the user interface 610 may include widgets, buttons, pull-down menus, etc., that may allow modification of displays 612, 614, 616, 618, 620, and 622. In some examples, the user interface 610 may include widgets, buttons, pull-down menus, etc., that may allow modification of the number of items shown in displays 620 and 622 (e.g., input items for a machine learning model).

[0082] The disclosed embodiments include determining the similarity between an energy storage unit and other energy storage units, and training a machine learning model of the other energy storage unit using training data for the machine learning model based on determining that the similarity meets a threshold. For example, a computing device may determine the similarity between an energy storage unit and other energy storage units. The similarity may be determined in a variety of ways (e.g., by analyzing properties, characteristics, or features associated with the energy storage unit, such as the manufacturer, model type, manufacturing time, and place of use of the energy storage unit). Additionally or alternatively, the similarity may be determined using available operational data of the energy storage unit, data showing the charge and discharge cycles of the energy storage unit, and / or data associated with the energy storage unit, such as temperature, voltage, charge state, and current (e.g., time-series data). The similarity may be determined using, for example, the distance between vectors of features of the energy storage unit, cosine distance, cosine similarity, mathematical methods, and / or other suitable methods. A computing device may train a machine learning model for other energy storage units using training data for a machine learning model (e.g., one associated with an energy storage unit) based on its determination that the similarity meets a threshold (e.g., the number of identical or similar features between energy storage units). The machine learning model for other energy storage units can then be used to generate predicted capacities for those other energy storage units (e.g., in a similar manner to the above).

[0083] The disclosed embodiments include a method for using load sets in an energy storage system, the method comprising: receiving operational data related to one of one or more energy storage units for a period of time by a computing device; determining one or more charge and discharge cycles of the energy storage unit during that period; generating a plurality of load sets based on the operational data; determining one or more operational parameters of the energy storage unit during the period; providing a machine learning model with one or more operational parameters and one or more load sets from the plurality of load sets; generating a predicted capacity of the energy storage unit at the end of the period based on the machine learning model; and configuring one or more energy storage units based on the predicted capacity. In some embodiments, each load set of the plurality of load sets includes one or more criteria related to the operation of the energy storage unit and a number of cycles from one or more cycles that satisfy one or more criteria. In some embodiments, the machine learning model includes a support vector machine (SVM), an association vector machine (RVM), or a model based on extreme gradient boosting. In some embodiments, the method further includes determining one or more load sets from the plurality of load sets based on a feature reduction technique.

[0084] The disclosed embodiments include a non-transient computer-readable medium for using load sets in an energy storage system, the non-transient computer-readable medium storing instructions, and when the instructions are executed by at least one processor, the instructions cause at least one processor to receive operational data relating to one of one or more energy storage units for a period of time, determine one or more charge and discharge cycles of that energy storage unit during that period, generate a plurality of load sets based on the operational data, determine one or more operational parameters of the energy storage unit during the period, provide a machine learning model with one or more operational parameters and one or more load sets from the plurality of load sets, generate a predicted capacity of the energy storage unit at the end of the period based on the machine learning model, and configure one or more energy storage units based on the predicted capacity. In some embodiments, each load set of the plurality of load sets includes one or more criteria relating to the operation of the energy storage unit and a number of cycles from one or more cycles that satisfy one or more criteria. In some embodiments, the machine learning model includes a support vector machine (SVM), an association vector machine (RVM), or a model based on extreme gradient boosting. In some embodiments, once an instruction is executed by at least one processor, at least one processor is prompted to further determine one or more load sets from a plurality of load sets based on a feature reduction technique.

[0085] Embodiments of the methods and systems of the present disclosure may include performing or completing certain selected tasks or steps manually, automatically, or in combination thereof. Furthermore, according to the actual instruments and apparatus of preferred embodiments of the methods and systems of the present disclosure, some selected steps may be performed by hardware (HW), by software (SW) on any operating system of any firmware, or in combination thereof. For example, as hardware, the selected steps of the present disclosure may be implemented as a chip or circuit. As software or algorithms, the selected steps of the present disclosure may be implemented as a set of software instructions executed by a computer using any suitable operating system. In either case, the selected steps of the methods and systems of the present disclosure may be described as being performed by a data processor, such as a computing device, to execute the set of instructions.

[0086] Various embodiments of the systems and technologies described herein can be implemented in digital electronic circuits, integrated circuits, specially designed ASICs (application-specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementation in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, the processor may be special-purpose or general-purpose, and coupled to a storage system, at least one input device, and at least one output device to receive data and instructions from and to them.

[0087] The systems and technologies described herein are computing systems that include backend components (e.g., as data servers), middleware components (e.g., application servers), or frontend components (e.g., client computers having a graphical user interface or web browser that allows users to interact with embodiments of the systems and technologies described herein), or can be implemented in any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communications (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), and the Internet. The computing system may include clients and servers. Clients and servers are generally far apart from each other and typically interact through communication networks. The client-server relationship arises from computer programs running on each computer and from the client-server relationship they have with each other.

[0088] While the specific features of the embodiments described herein have been explained as described herein, many modifications, substitutions, changes, and equivalents will come to mind for those skilled in the art. Therefore, it should be understood that the appended claims are intended to include all such modifications and changes that fall within the scope of the embodiments. They are presented only as examples and not as limitations, and it should be understood that various changes in form and detail are possible. Any part of the apparatus and / or method described herein may be combined in any combination, except for mutually exclusive combinations. The embodiments described herein may include various combinations and / or subcombinations of the functions, components, and / or features of the different embodiments described herein.

[0089] The foregoing descriptions are presented for illustrative purposes only. They are not exhaustive and are not limited to the exact forms or embodiments disclosed. Modifications and adaptations of embodiments will become apparent from the specifications and practices of the disclosed embodiments. For example, while the described embodiments include hardware and software, systems and methods consistent with this disclosure may be implemented as hardware only.

[0090] It will be understood that the embodiments described above can be implemented by hardware, software (program code), or a combination of hardware and software. If implemented by software, the software can be stored in the computer-readable medium described above. When executed by a processor, the software can perform the disclosed methods. The computing units and other functional units described in this disclosure can be implemented by hardware, software, or a combination of hardware and software. Those skilled in the art will also understand that several of the above modules / units can be combined as a single module or unit, and each of the above modules / units can be further divided into several submodules or subunits.

[0091] The block diagrams in the figures illustrate the architecture, functionality, and operation of possible embodiments of systems, methods, and computer hardware or software products according to various exemplary embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for performing a defined logical function. It should also be understood that in some alternative embodiments, the functions shown in the blocks may occur in a different order than that shown in the figures. For example, two consecutively shown blocks may be executed or performed substantially simultaneously, depending on the functions involved, or sometimes the two blocks may be executed in reverse order. Some blocks may be omitted. It should also be understood that each block in the block diagram, and combinations of blocks, may be performed by a special-purpose hardware-based system or by a combination of special-purpose hardware and computer instructions to perform a defined function or action.

[0092] In the aforementioned specification, embodiments have been described with reference to numerous specific details that may vary by embodiment. Specific adaptations and modifications of the embodiments described may be made. Other embodiments will become apparent to those skilled in the art by considering the specifications and practices of the invention disclosed herein. This specification and examples are intended to be considered illustrative only, and the true scope and spirit of the invention are set forth by the following claims. Furthermore, the order of steps shown in the figures is for illustrative purposes only and is not intended to limit the order of any particular step. Therefore, those skilled in the art will understand that these steps may be performed in different orders while carrying out the same method.

[0093] The embodiments of this disclosure are not limited to the exact configurations described above and shown in the accompanying drawings, and it will be understood that various modifications and changes may be made without departing from their scope. Other embodiments will become apparent to those skilled in the art by considering the specifications and practices of the embodiments disclosed herein. This specification and examples are intended to be illustrative only, and the true scope and spirit of the embodiments disclosed are given by the following claims.

[0094] Furthermore, while exemplary embodiments are described herein, any and all embodiments having equivalent elements, modifications, omissions, combinations, adaptations, or changes based on this disclosure (e.g., in various embodiments) are included in the scope. The elements of the claims should be interpreted broadly based on the language used in the claims and are not limited to the examples described herein or described in the course of this application. These examples should be interpreted non-exclusively. Furthermore, the steps of the disclosed methods can be modified in any way, including changing the order of the steps or inserting or deleting steps. This specification and the examples are intended to be illustrative only, and the true scope and spirit are indicated by the entire scope of the following claims and their equivalents.

Claims

1. It is a system, One or more energy storage units, A computing device including at least one processor and at least one memory for storing instructions. The instructions, when executed by the at least one processor, are transmitted to the computing device. For a certain period of time, to receive operational data related to one of the energy storage units among the one or more energy storage units, To determine one or more charging and discharging cycles of the energy storage unit during the aforementioned period, Based on the aforementioned operational data, a plurality of load sets are generated, wherein each of the plurality of load sets is: One or more criteria related to the operation of the energy storage unit, The number of cycles among the one or more cycles that satisfy the one or more criteria and The process of generating the aforementioned multiple load sets, Determining one or more operating parameters of the energy storage unit for the aforementioned period, To provide a machine learning model with one or more operating parameters and one or more load sets from the plurality of load sets, At the end of the aforementioned period, the predicted capacity of the energy storage unit is generated based on the machine learning model, Based on the predicted capacity, one or more energy storage units are configured. The system that causes the following to happen.

2. The aforementioned operation data is, The temperature of the energy storage unit during each interval of the plurality of intervals in the aforementioned period, The voltage level of the energy storage unit during each of the plurality of intervals in the aforementioned period, The charge state of the energy storage unit during each of the plurality of intervals in the aforementioned period, or The amount of electricity of the energy storage unit in each of the plurality of intervals during the aforementioned period The system according to claim 1, comprising one or more of the following.

3. When the instruction is executed by the at least one processor, the computing device further: The system according to claim 1, wherein the one or more cycles of charging and discharging the energy storage unit during the aforementioned period are determined using a rainflow counting algorithm.

4. The one or more criteria related to the operation of the energy storage unit are: The temperature range of the energy storage unit, The voltage level range of the energy storage unit, The range of the minimum charge state of the energy storage unit, The range of the maximum charge state of the energy storage unit, The range of the total current of the aforementioned energy storage unit, The range of the sum of the squares of the currents of the energy storage unit during the time segment, The range of current amounts for the energy storage unit, or Range of charge depth of the energy storage unit The system according to claim 1, comprising one or more of the following.

5. The system according to claim 1, wherein one or more criteria relating to the operation of the energy storage unit with respect to a first load set among the plurality of load sets are different from one or more criteria relating to the operation of the energy storage unit with respect to a second load set among the plurality of load sets.

6. The one or more operating parameters of the energy storage unit are: The number of charge and discharge cycles of the energy storage unit during the aforementioned period, determined using a rainflow counting algorithm. The equivalent total amount of charge and discharge cycles of the energy storage unit during the aforementioned period, The total amount of current from the energy storage unit during the aforementioned period, The average charge state of the energy storage unit during the aforementioned period, The length of the aforementioned period, or Capacity of the energy storage unit at the start of the aforementioned period The system according to claim 1, comprising one or more of the following.

7. The system according to claim 1, wherein the machine learning model includes a support vector machine, an association vector machine, or a model based on extreme gradient boosting.

8. The system according to claim 1, wherein the one or more load sets include a subset of the plurality of load sets.

9. When the instruction is executed by the at least one processor, the computing device further: The system according to claim 1, which determines one or more of the plurality of load sets based on feature reduction technology.

10. When the instruction is executed by the at least one processor, the computing device further: The aforementioned machine learning model, Load set of the energy storage unit in a period prior to the aforementioned period, The operating parameters of the energy storage unit during the aforementioned prior period, or Measured capacity of the energy storage unit at the end of the aforementioned prior period The system according to claim 1, which is trained using historical data that includes one or more of the following.

11. When the instruction is executed by the at least one processor, the computing device further: The system according to claim 1, wherein the one or more energy storage units are configured by adjusting the pattern in which the one or more energy storage units deliver electricity based on the predicted capacity, or by increasing the capacity of the one or more energy storage units.

12. The system according to claim 11, wherein the pattern includes a plurality of time intervals in which one or more energy storage units are configured to charge or discharge at a specific rate.

13. When the instruction is executed by the at least one processor, the computing device further: The system according to claim 1, which calculates the degree of influence of each of the multiple input items to the machine learning model on the output of the machine learning model.

14. When the instruction is executed by the at least one processor, the computing device further: To determine the degree of similarity between the aforementioned energy storage unit and other energy storage units, Based on the determination that the similarity meets the threshold, the machine learning model of the other energy storage unit is trained using the training data of the machine learning model. The system according to claim 1, which causes the following to be performed.

15. It is a method, The operation data related to one of the one or more energy storage units for a certain period of time is received by a computing device, To determine one or more charging and discharging cycles of the energy storage unit during the aforementioned period, Based on the aforementioned operational data, a plurality of load sets are generated, wherein each of the plurality of load sets is: One or more criteria related to the operation of the energy storage unit, The number of cycles among the one or more cycles that satisfy the one or more criteria and The process of generating the aforementioned multiple load sets, Determining one or more operating parameters of the energy storage unit for the aforementioned period, To provide a machine learning model with one or more operating parameters and one or more load sets from the plurality of load sets, At the end of the aforementioned period, the predicted capacity of the energy storage unit is generated based on the machine learning model, Based on the predicted capacity, one or more energy storage units are configured. The method, including the method described above.

16. The method according to claim 15, wherein the machine learning model includes a support vector machine, an association vector machine, or a model based on extreme gradient boosting.

17. The method according to claim 15, further comprising determining one or more load sets from the plurality of load sets based on feature reduction techniques.

18. A non-temporary computer-readable medium for storing instructions, wherein when an instruction is executed by at least one processor, the instructions are stored in the at least one processor. For a certain period of time, to receive operational data related to one of the energy storage units among the one or more energy storage units, To determine one or more charging and discharging cycles of the energy storage unit during the aforementioned period, Based on the aforementioned operational data, a plurality of load sets are generated, wherein each of the plurality of load sets is: One or more criteria related to the operation of the energy storage unit, The number of cycles among the one or more cycles that satisfy the one or more criteria and The process of generating the aforementioned multiple load sets, Determining one or more operating parameters of the energy storage unit for the aforementioned period, To provide a machine learning model with one or more operating parameters and one or more load sets from the plurality of load sets, At the end of the aforementioned period, the predicted capacity of the energy storage unit is generated based on the machine learning model, Based on the predicted capacity, one or more energy storage units are configured. The non-temporary computer-readable medium that causes the following to occur.

19. The non-temporary computer-readable medium according to claim 18, wherein the machine learning model includes a support vector machine, an association vector machine, or a model based on extreme gradient boosting.

20. When the instruction is executed by the at least one processor, the at least one processor further: A non-temporary computer-readable medium according to claim 18, wherein one or more load sets from the plurality of load sets are determined based on feature reduction technology.

Images