WO2022001304A1 - 设备供电的方法、系统及相关设备 - Google Patents

设备供电的方法、系统及相关设备 Download PDF

Info

Publication number
WO2022001304A1
WO2022001304A1 PCT/CN2021/088668 CN2021088668W WO2022001304A1 WO 2022001304 A1 WO2022001304 A1 WO 2022001304A1 CN 2021088668 W CN2021088668 W CN 2021088668W WO 2022001304 A1 WO2022001304 A1 WO 2022001304A1
Authority
WO
WIPO (PCT)
Prior art keywords
power
storage device
electricity price
electricity
power supply
Prior art date
Application number
PCT/CN2021/088668
Other languages
English (en)
French (fr)
Inventor
姜炜祥
柴峰
王淑倩
刘春�
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21831506.7A priority Critical patent/EP4167417A4/en
Publication of WO2022001304A1 publication Critical patent/WO2022001304A1/zh
Priority to US18/147,389 priority patent/US20230148201A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
    • H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J9/00—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting
    • H02J9/04—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source
    • H02J9/06—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over, e.g. UPS systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems

Definitions

  • the present application relates to the field of energy technology, and in particular, to a method, system and related equipment for powering equipment.
  • the power system includes power stations and power grids that transmit power generated by the power stations (such as substations and transmission and distribution lines of various voltages), and the power system is used to supply power to equipment.
  • the grid transfers electricity according to the needs of equipment.
  • the load on the grid is often unbalanced, eg, the grid is heavily loaded during the day and the grid is less loaded at night.
  • the power generation capacity of the power station is usually relatively stable, and there will be no major fluctuations. Due to the unbalanced load of the power grid, the electricity demand is low during the valley period (ie the period when the grid load is low), and the power station has excess power generation capacity. Unavailable, the demand for electricity during peak hours (that is, when the grid load is high) is higher than the power supply capacity of the power station. By increasing the electricity price during peak hours, the power grid urges users to reduce electricity consumption during peak hours, so as to achieve the purpose of balancing the load on the grid. This electricity price method is also called tiered electricity price.
  • the power supply method of the equipment is to directly use the power sent by the power station through the power grid, and the equipment needs to maintain the power supply state all the time, and does not distinguish between the low-valley period and the peak period, resulting in high electricity costs for the equipment.
  • the present application discloses a method, system and related equipment for power supply to equipment, which can flexibly select the power supply mode to equipment according to the electricity price and reduce the power supply cost of equipment.
  • the present application provides a method for supplying power to a device, the method comprising: a power storage device controller predicting a power load of a device in an electricity price interval, where the electricity price interval is a period of time when the electricity price is the same and continuous; the electricity storage device controls The controller selects the power supply strategy for the device according to the power load of the device in the electricity price range, the stored power of the electricity storage device at the first moment, and the electricity price of the electricity price range at the first moment; the electricity storage device controller selects the power supply obtained by the selection The policy powers the device.
  • the power storage device controller may only predict the power load of the device in the next electricity price interval adjacent to the current electricity price interval, or the power load of the device in the next electricity price interval that is not adjacent to the current electricity price interval, or , the power load of the device in multiple electricity price intervals after the current electricity price interval, or the power load of the device in all electricity price intervals after the current electricity price interval.
  • the power storage device controller predicts the power load of the device in the electricity price range, and then combines the stored power of the power storage device at the first moment and the electricity price in the electricity price range at the first moment, so as to flexibly choose
  • the power supply strategy for the equipment can reduce the power supply cost of the equipment.
  • the power storage device controller calculates the power load of the power storage device according to the power load of the device in the electricity price range, the stored power of the power storage device at the first moment, and the electricity price in the electricity price range at the first moment. Redundant power; the power storage device controller determines a power supply mode for the device according to the redundant power of the power storage device, the power supply mode includes any one of selecting a power source to power the device and selecting an power storage device to power the device.
  • the power storage device controller determines the power supply mode for the device by calculating the redundant power of the power storage device, which can ensure that the power supply mode to the device can be flexibly selected, and avoids only selecting the power source to supply power to the device .
  • the power storage device controller selects a power source to supply power to the device; when the redundant power of the power storage device is greater than or equal to the first threshold At the second threshold, the electrical storage device controller selects the electrical storage device to supply power to the device.
  • the power storage device controller selects the power supply mode for the device according to the relationship between the redundant power of the power storage device and the first threshold and the second threshold, which can ensure that the selected power supply mode can reduce the number of devices. electricity cost.
  • the power storage device controller calculates the power consumption of the device in the power price range and the chargeable amount of the power supply in the power price range according to the power load of the device in the power price range;
  • the electricity consumption of the equipment in the electricity price range and the rechargeable quantity of the power supply in the electricity price range, and the low-price rechargeable quantity and the high-price electricity consumption are obtained from statistics.
  • the low-price rechargeable quantity is the power supply in the electricity price range.
  • the sum of the rechargeable capacity in the electricity price interval where the electricity price is low, and the high-price electricity consumption is the power consumption in the electricity price interval in which the device is higher than the electricity price interval in the electricity price interval at the first moment.
  • the sum of the power; the power storage device control calculates and obtains the redundant power of the power storage device according to the stored power of the power storage device at the first moment, the low-cost chargeable power and the high-price power consumption,
  • the redundant power of the power storage device is the sum of the stored power of the power storage device at the first moment and the low-cost chargeable power minus the high-price power consumption.
  • the power storage device controller obtains the power consumption of the device in the electricity price range by predicting the power load in the range, and then combines the rechargeable amount of the power supply in the electricity price range and the initial storage of the power storage device. In this way, the power storage device controller can correctly select the power supply strategy for the device in the subsequent decision-making process.
  • the power storage device controller selects the power supply to supply power to the device, and the power supply is used to power all When the device supplies power, the power storage device is charged, and the charging amount of the power storage device is the absolute value of the redundant power; when the redundant power of the power storage device is greater than or equal to the second threshold , the power storage device controller selects the power storage device to supply power to the device, and when the voltage of the power storage device is less than or equal to the voltage threshold, stops supplying power to the device, and selects the power source to continue powering the device. Power is supplied, and the discharge amount of the power storage device is the redundant power.
  • the power storage device controller flexibly selects the power supply mode for the device according to the relationship between the redundant power of the power storage device and the first threshold and the second threshold, so that the power storage device can be charged and Flexible switching between discharges can ultimately achieve the purpose of reducing the power supply cost of the device.
  • the power storage device controller calculates the charging power according to the redundant power of the power storage device and the duration of the electricity price interval at the first moment; the power storage device controller adjusts the power supply voltage according to the charging power , so that the power supply voltage is higher than the voltage of the power storage device, and the power supply charges the power storage device.
  • the electric storage device controller adjusts the power supply voltage to make it higher than the voltage of the electric storage device by calculating the charging power, and completes the charging of the electric storage device, which can ensure that the charging process of the electric storage device is simple High efficiency, improving the charging efficiency of the power storage device.
  • the electrical storage device controller calculates the discharge power according to the redundant power of the electrical storage device and the duration of the electricity price interval at the first moment; the electrical storage device controller adjusts the power supply voltage according to the discharge power , so that the power supply voltage is lower than the voltage of the power storage device, which supplies power to the device.
  • the electric storage device controller adjusts the power supply voltage to make it lower than the voltage of the electric storage device by calculating the discharge power, and completes the power supply of the electric storage device to the device, which can ensure the discharge process of the electric storage device.
  • the implementation is simple and efficient, and the discharge efficiency of the power storage device is improved.
  • the electric storage device controller obtains the current of the electric storage device; the electric storage device controller determines whether to adjust the charging power or the discharging power according to the obtained current of the electric storage device; In the case of the charging power or the discharging power, adjust the current limiting coefficient of the power supply and/or the current limiting coefficient of the power storage device.
  • the electric storage device controller calculates the charging power or discharging power of the electric device by obtaining the current of the electric storage device, and judges whether it is consistent with the expected charging power or discharging power. Under certain circumstances, by adjusting the current limiting coefficient of the power supply or the current limiting coefficient of the power storage device to increase the current value or reduce the current value passing through the power storage device, so as to ensure that the power storage device can be smoothly charged or discharged as expected. .
  • the power storage device controller determines an initial power prediction model, where the initial power prediction model includes a deep learning model; the power storage device controller obtains historical power load data of the device, and the historical power load data is obtained by the power storage device controller.
  • the power load data includes the power load recorded by the device before the first moment; the power storage device controller uses the historical power load data to train the initial power prediction model.
  • the power storage device controller uses the historical power load data of the device as sample data to train the initial power prediction model, so that the trained power prediction model has the ability to predict the power load of the device in the electricity price range , which can improve the accuracy of the power storage device controller to obtain the power load of the device in the electricity price range, and the accuracy of the selected power supply strategy for the device.
  • the present application provides a power supply control device, comprising: a power prediction module for predicting the power load of a device in an electricity price interval, where the electricity price interval is the same and continuous period of time; a processing module for The power load of the device in the electricity price range, the stored power of the power storage device at the first moment, and the electricity price of the electricity price range at the first moment, select the power supply strategy for the device; the communication module is used to send the power supply command Sent to a power source or the power storage device, so that the power source or the power storage device supplies power to the device.
  • the processing module is further configured to: according to the power load of the device in the electricity price interval, the stored electricity of the electricity storage device at the first moment, and the electricity price interval in which the first moment is located. electricity price, and calculate the redundant power of the power storage device; select a power supply mode according to the redundant power of the power storage device, and the power supply mode includes selecting the power source to supply power to the device and selecting the energy storage device to supply power to all any one of the above-mentioned equipment power supply.
  • the processing module is further configured to: when the redundant power of the power storage device is less than or equal to a first threshold, select the power source to supply power to the device; When the redundant power of the power storage device is greater than or equal to the second threshold, the power storage device is selected to supply power to the device.
  • the processing module is further configured to: according to the power load of the device in the electricity price range, calculate the electricity consumption of the device in the electricity price range and the power consumption of the power supply in the electricity price range.
  • the rechargeable amount in the electricity price range according to the electricity consumption of the device in the electricity price range and the rechargeable volume of the power supply in the electricity price range, the low price rechargeable volume and the high price electricity consumption are obtained by statistics, and the low price
  • the price chargeable amount is the sum of the chargeable amounts of the power supply in the electricity price interval in the electricity price interval that is lower than the electricity price of the electricity price interval at the first moment, and the high-priced electricity consumption is the device in the electricity price interval.
  • the electricity price interval the sum of the electricity consumption in the electricity price interval higher than the electricity price of the electricity price interval at the first moment; High-priced power consumption, the redundant power of the power storage device is calculated, and the redundant power of the power storage device is the sum of the stored power of the power storage device at the first moment and the low-cost chargeable power and then Subtract the high price of electricity usage.
  • the processing module is further configured to: when the redundant power of the power storage device is less than or equal to a first threshold, select the power supply to supply power to the device, and the power The power supply charges the power storage device while supplying power to the device, and the charging amount of the power storage device is the absolute value of the redundant power; when the redundant power of the power storage device is greater than or equal to At the second threshold, the power storage device is selected to supply power to the device, and when the voltage of the power storage device is less than or equal to the voltage threshold, the power supply to the device is stopped, and the power supply is selected to continue to supply power to the device , the discharge amount of the power storage device is the redundant power.
  • the processing module is specifically configured to: calculate the charging power according to the redundant power of the power storage device and the duration of the electricity price interval at the first moment; The power adjusts the power supply voltage so that the power supply voltage is higher than the voltage of the electrical storage device, and the power supply charges the electrical storage device.
  • the processing module is specifically configured to: calculate the discharge power according to the redundant power of the power storage device and the duration of the electricity price interval at the first moment; Power adjusts the supply voltage so that the supply voltage is lower than the voltage of the electrical storage device that powers the device.
  • the processing module is further configured to: obtain the current of the power storage device; and determine whether to adjust the charging power or the power according to the obtained current of the power storage device Discharge power; when it is determined to adjust the charging power or the discharging power, adjust the current limiting coefficient of the power supply and/or the current limiting coefficient of the power storage device.
  • the processing module is further configured to: determine an initial power prediction model, where the initial power prediction model includes a deep learning model; acquire historical power load data of the device, the historical power The load data includes the power load recorded by the device before the first moment; the initial power prediction model is trained by using the historical power load data.
  • the present application provides a computing device, the computing device includes a processor and a memory, the memory is used to store a program code, and the processor executes the program code in the memory to implement the above-mentioned first aspect and Combining the operation steps of the method of any one of the implementation manners of the first aspect above.
  • the present application provides an equipment power supply system, including a power module management device, a power storage device, and a power supply device control device.
  • the electricity price interval is the same and continuous period of time, and is based on the power load of the electrical equipment in the electricity price interval, the stored power of the electricity storage device at the first moment, and the electricity price in the electricity price interval at the first moment.
  • selects a power supply strategy for the electrical equipment the electrical storage equipment is used to store electricity and supply power to the electrical equipment; the power module management device is used to supply power to the electrical equipment and The electrical storage device is charged.
  • the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the processor executes the above-mentioned first aspect and in combination with the above-mentioned Operation steps of the device power supply method provided by any one of the implementation manners of the first aspect.
  • the present application provides a computer program product, the computer program product including instructions, when the computer program product is executed by a computer, the computer can execute the first aspect above and any one in combination with the first aspect above The flow of the device power supply method provided by the implementation.
  • FIG. 1 is a system architecture diagram of a device power supply system provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a device power supply method provided by an embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a back-propagation neural network provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of decision-making of a device power supply mode provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a power supply control device provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a computing device provided by an embodiment of the present application.
  • the quantity of electric charge indicates the amount of electric charge carried by an object.
  • the quantity of electric charge is called electric quantity, the symbol is Q, and the unit is coulomb (C).
  • Electric quantity can also refer to the quantity of electric energy required by electrical equipment. , which is also called electrical energy or electrical work.
  • Electric energy refers to the ability to use electricity to do work (ie, generate energy) in various forms, and the unit of electric energy is kilowatt-hour (kw*h).
  • the free charge in the conductor makes a regular directional movement under the action of the electric field force to form a current.
  • the amount of electricity passing through any cross-section of the conductor per unit time is called the current intensity, abbreviated as current, the symbol is I, and the unit is ampere (A).
  • Electric power refers to the work done by the current in a unit of time, which is used to indicate the speed of power consumption, the symbol is P, and the unit is watt (W). energy consumed over time.
  • the present application provides a method for supplying power to equipment, which can change the power supply mode of the equipment, reduce the power demand of the equipment on the power grid during peak hours, and effectively Reduce power supply costs for equipment.
  • FIG. 1 is a system architecture diagram of an equipment power supply system provided by the present application.
  • the power system is connected to the equipment power supply system, and supplies power to the equipment through the power module management device pool in the equipment power supply system, wherein , the power module management device may also be referred to as a power supply, and the power module management device pool may also be referred to as a power supply pool.
  • the device power supply system includes an electrical storage device control device 110 , an electrical storage device resource pool 120 , a power module management device pool 130 and an electrical device group 140 .
  • the power storage device control device 110 may be a chip with computing capability and communication capability (such as a field-programmable gate array (FPGA) chip) or a server node.
  • FPGA field-programmable gate array
  • a power prediction module 1110, a power supply strategy decision module 1120, a communication module 1130, and a data storage module 1140 are deployed. These modules are connected to each other through an internal bus, and cooperate with each other to realize external control functions.
  • the power module management device pool 130 includes one or more power module management devices, such as a power module management device 1310, a power module management device 1320, and a power module management device 1330, and each power module management device is deployed with one or more power supplies Modules and power management software, each power module can be composed of transformers, cells and related circuits, which are used to convert the electricity with standard voltage (such as 220 volts) input by the power system into suitable for the normal operation of electrical equipment and electrical storage equipment
  • the power supply module can directly supply power to the electrical equipment and adjust the voltage through the transformer to charge the power storage equipment.
  • the module 13113 and the power management software 13120 are connected to each other, and the power management software 13120 manages and controls the power module 13111 , the power module 13112 and the power module 13113 . All the power in the power module is directly provided by the power supply system, and supplies power to the power-consuming equipment group 140 or charges the power storage devices in the power storage device resource pool 120 , and the power module manages each power source in the device pool 130 .
  • the module management device can be connected to one or more power storage devices in the power storage device resource pool 120, and then supply power to the devices in the power device group 140, and the power device group can be composed of devices in multiple data centers A cluster of devices such as computing device 1410, network device 1420, and storage device 1430.
  • each power storage device in the power storage device resource pool 120 may also be connected to one or more power module management devices in the power module management device pool 130, and then supply power to the devices in the power consumption device group 140, In order to ensure stable power supply, in this application, it is preferred that the power storage devices in the power storage device resource pool 120 are connected one-to-one with the power module management devices in the power module management device pool 130, that is, each power storage device is connected to one Power module management device.
  • the communication module 1130 in the power storage device control device 110 may be a communication port, which is composed of a transceiver or transceiver-related circuit components, and is used for receiving power sent by the power management software deployed by the power module management device in the power module management device pool 130.
  • the load data and the data related to the power storage device in the power storage device resource pool 120 are stored in the data storage module 1140, and the data storage module 1140 may be an on-chip random access memory (random access memory). , RAM) or dynamic random access memory (DRAM) in servers.
  • the power prediction module 1110 may be an on-chip arithmetic and logic unit (ALU) or a generic array logic chip in the server, and is used to predict the power load data stored in the data storage module 1140 to obtain a power output.
  • ALU arithmetic and logic unit
  • the power load curve and the electricity price curve stored in the data storage module 1140 and the stored power of the power storage equipment so as to select the power supply strategy for the power consumption equipment group 140, and calculate the charge/discharge amount and the charge/discharge power of the power storage equipment. , and finally send the calculated charge/discharge amount and charge/discharge power to the power management software in the power module management device through the communication module 1130, so as to complete the charge and discharge of the power storage device.
  • the devices in the power-consuming equipment group 140 can be powered by the power modules in the power module management device battery 130, and can also be powered by the power storage devices in the power storage device resource pool 120, and The power module can charge the power storage device. Therefore, the power storage device control device 110 issues a charging command to the power supply module during the trough period, so that the power supply module charges the power storage device when the electricity price is low, and then uses the power stored in the power storage device to charge the power consumption during the peak period.
  • the devices in the device group 140 supply power, which can reduce the power demand of the devices on the power module during peak hours, reduce the power consumption of the power module when the price of electricity is high, and ultimately reduce the power supply cost of the device.
  • a maximum output power will be set, which is used to ensure the power supply demand of the equipment in the data center.
  • the power supply demand of the device does not exceed the maximum power.
  • the surplus power other than the power that meets the power supply demand of the device can be used to charge the power storage device.
  • the method includes but is not limited to the following steps:
  • the power storage device controller uses the power prediction model to predict the power load of the device in the electricity price range.
  • the electrical storage device controller may be deployed on any server or computing device with computing and communication capabilities, and the electrical storage device controller may be the electrical storage device control apparatus 110 shown in FIG. 1 above.
  • the electrical device in this application may be a computing device, a network device, a storage device, or other devices that need to consume power resources.
  • the price of electricity refers to the price of electricity used, which can be set artificially.
  • the price of electricity is not constant, but changes in steps, that is, the corresponding electricity price is different in different time periods, such as from 11:00 p.m. to 2:00 p.m. At 7:00 in the morning, there are fewer people using electricity, the load is smaller, and the electricity price is lower.
  • the electricity price range in this application refers to a period of time during which electricity prices are the same and continuous, for example, from 11:00 pm to 7:00 am as described above.
  • the power storage device controller needs to periodically read the electricity price curve.
  • the reading period can be set according to actual needs, for example, it can be set to 1 hour.
  • the power storage device controller obtains the current reading time (ie the first time) according to the electricity price curve ), and then determine the electricity price at the current reading time and the reading time in the previous cycle (the second time), that is, the electricity price range at the time before the current reading time is one cycle duration (1 hour). Whether the electricity price is the same, exemplarily, assuming that the reading period is 1 hour, the power storage device controller reads the electricity price curve at 9:00 in the morning, obtains the electricity price in the electricity price range at 9:00, and then judges that the electricity price is the same as the reading period of the previous cycle.
  • the electricity price of the electricity price range at the time (that is, 8:00 am) is the same. If they are the same, it means that there is no electricity price inflection point, that is, the electricity price range at the first moment and the electricity price range at the second time are the same electricity price range. At this time There is no need to adjust the power supply mode to the equipment. If it is not the same, it means that an electricity price inflection point has occurred, that is, the electricity price range at the first moment and the electricity price range at the second moment are different electricity price ranges. At this time, the power supply strategy needs to be re-determined. It is necessary to trigger the power storage device controller to use the power prediction model to predict the power load of the device in the future electricity price range, and further determine whether the power supply strategy of the device needs to be adjusted according to the prediction result.
  • the power storage device controller when the power storage device controller uses the power prediction model to make predictions, it may only predict the next electricity price interval in which the device is located at the current reading time (for example, the next electricity price adjacent to the current electricity price interval) interval, or, the next electricity price interval that is not adjacent to the current electricity price interval) the power load of the electricity price interval, or the power load of multiple electricity price intervals after the electricity price interval where the prediction device is at the current reading time, or the prediction device
  • This application does not limit the power loads of all electricity price intervals after the electricity price interval at the current reading time. For ease of description, this application takes the power load of the power storage device controller predicting all electricity price intervals at one time as an example for description.
  • the power storage device controller makes predictions, it needs to sample the historical power load of the device (for example, the power load in the last week), and the sampling period can be set according to actual needs, for example, it can be set to 10 seconds, that is, The power load of the device is collected every 10 seconds, and the collected data is stored. After collecting enough historical power load data, the power storage device controller can predict the power load of the device in each future electricity price interval according to the collected historical power load data. Optionally, the power storage device controller may also divide different time periods according to the electricity price interval, and sample the power load of each segment respectively.
  • the power storage device controller can predict the power load of the device by using a preset algorithm.
  • the preset algorithm is used to analyze the data dependent on the time series to obtain the results satisfying the specific characteristics.
  • Preset algorithms include extreme gradient boosting (eXtreme gradient boosting, XGBoost) algorithms, random forest algorithms, neural network algorithms, or other algorithms that forecast through time series to predict the power load of the device.
  • the power storage device controller can use a back-propagation neural network (BP) to predict the power load of the device.
  • BP back-propagation neural network
  • the error function descends in the direction of negative gradient and finally approaches the desired output.
  • Figure 3 is the architecture diagram of the BP network.
  • the BP network includes an input layer, a hidden layer and an output layer.
  • the hidden layer can have one or more layers, and the input layer
  • the number of neurons is 7, the number of neurons in the hidden layer is 4, and the number of neurons in the output layer is 1.
  • the initialization function to initialize the parameters of the BP network, or randomly select parameter values to initialize the network, for example, use a constant of 0.001 or a Gaussian distribution based on 0.001 to initialize, and then set the hidden layer and output layer. , the network performance function and the number of iterations.
  • the excitation function of the hidden layer can be set to the tansig function
  • the excitation function of the output layer can be set to the logsig function
  • the network performance function can be set to the trainingdx function
  • the number of iterations can be set to 5000 times.
  • the collected historical power load data is normalized as sample data and then input to the input layer.
  • the input layer is processed, it is transmitted to the hidden layer.
  • the hidden layer further processes it (convolution calculation), and the processing results It is transmitted to the output layer, and the output layer uses the back-propagation algorithm to update and adjust the parameters in the network according to the loss function as the objective function, and execute the above process iteratively until the loss function value converges.
  • the BP network training is completed, and the BP network has prediction equipment.
  • the power load capacity of the power storage device controller can use the BP network completed by the training to predict the power load of the device in each future electricity price interval.
  • the network transfer function can choose the sigmoid transfer function, for example.
  • T i is the expected output
  • O i is the calculated output of the network.
  • the error function E is minimized by continuously adjusting the network weights and thresholds, and finally the training is completed.
  • the power storage device controller can simultaneously use multiple prediction algorithms to predict the future power load of the device. After comparison, the most accurate and most realistic prediction algorithm is finally selected, and the prediction result of the algorithm is used as the final output result.
  • the power storage device controller calculates the redundant power of the power storage device according to the power load of the device in the electricity price range, the stored power of the power storage device at the first moment, and the electricity price in the electricity price range at the first moment .
  • the power storage device controller can calculate the electricity consumption of the device in the electricity price range.
  • the integral of the power load of the electricity price interval in the time period corresponding to the electricity price interval For example, if the electricity price interval is from 7:00 am to 8:00 am, and the power load of the equipment during this period is 10 kilowatts (kw), the electricity consumption of the equipment in this electricity price interval is 10 kilowatt hours (kw*h).
  • the power storage device controller further calculates the chargeable amount of the power module in the electricity price range, that is, when the maximum output power is set, the power provided by the power module in addition to the power that meets the power supply requirements of the device.
  • the power module can be the power module in the power module management device pool 130 shown in FIG. 1. Since the power facility itself has a physical upper limit, that is, the power facility is set with the maximum output power, the power of the equipment in the electricity price range is known. In the case of load, the chargeable amount of the power module in the electricity price range can be calculated. For example, if the maximum output power of a power facility is 15kw, and the power load of the equipment is 10kw in the electricity price range from 7:00 a.m.
  • the rechargeable capacity of the power module in this electricity price range is 5kwh, that is, in the electricity price range.
  • the rechargeable capacity of the power module is 5kwh.
  • the power storage device controller calculates the low-price rechargeable quantity and the high-price electricity consumption.
  • the sum of the rechargeable amounts of all the electricity price ranges of the electricity price range at the current reading time (the first time), and the high-priced electricity consumption is all electricity price ranges of the electricity price range higher than the electricity price range where the device is at the current reading time. the sum of electricity consumption.
  • the power storage device controller obtains the low-cost chargeable amount and high-priced power consumption, it can calculate the redundant power of the power storage device.
  • the redundant power of the power storage device is the stored power of the power storage device at the current reading time. The sum of the low-cost chargeable capacity and the result obtained by subtracting the high-priced power consumption.
  • the power storage device controller selects a power supply strategy for the device according to the calculated redundant power of the power storage device.
  • the power storage device controller makes a decision on the charging and discharging situation of the power storage device according to the result of the redundant power of the power storage device obtained by calculation, and then determines the power supply strategy for the device.
  • the power supply module is selected to supply power to the device, and the power module charges the power storage device while supplying power to the device, and the charging capacity of the power storage device is redundant
  • the absolute value of the remaining power when the calculated redundancy of the power storage device is greater than or equal to the second threshold, the power storage device is selected to supply power to the device, and the discharge amount of the power storage device is the redundant power.
  • the first threshold and the second threshold may be set to the same value, for example, both are set to 0, or may be set to different values, for example, the first threshold is set to 0.1, and the second threshold is set to 0.5.
  • the redundant power of the power storage device is the sum of the stored power of the power storage device at the current moment and the low-cost chargeable power, and the result of subtracting the high-cost power consumption
  • the first threshold and the second threshold are both. Set it to 0 as an example to illustrate. If the redundant power is less than 0, it means that in the power price range after the current price range, the sum of the low-cost chargeable power of the power module and the power stored by the power storage device at the current moment , still can not meet the high-priced electricity consumption of the equipment. Therefore, the power storage device controller selects the power module to supply power to the device, and charges the power storage device while supplying power, so that the power storage device is in the electricity price range at the current moment.
  • the electricity charged by the power supply module is stored in the system, so that the stored electricity can be supplied to the equipment for use in the subsequent higher electricity price range, and the high-priced electricity consumption of the equipment can be reduced. absolute value.
  • the redundant power is greater than 0, it means that in the power price range after the current price range, the sum of the low-cost chargeable power of the power module and the power stored by the power storage device at the current moment has exceeded the power price of the device. Therefore, the power storage device controller selects the power storage device to supply power to the device, so that the power storage device can release the stored power for the device to use within the electricity price range at the current moment, thereby reducing the power consumption of the device.
  • the power consumption of the power supply module within the electricity price range at the current moment, and the discharge amount of the power storage device is the redundant power.
  • the capacity of the power storage device to store power is limited.
  • the power storage device controller selects the power storage device to supply power to the device, the power stored by the power storage device is continuously consumed, resulting in the constant voltage of the power storage device.
  • the power stored by the power storage device is exhausted, that is, when the voltage of the power storage device is less than or equal to the voltage threshold, the power storage device stops supplying power to the device.
  • the module continues to supply power to the device.
  • the voltage of the power storage device is related to the amount of electricity it stores.
  • the power stored by the power storage device reaches the maximum value, its voltage also reaches the maximum value, which is generally 52 volts.
  • the power stored by the power storage device is exhausted. , its voltage reaches the minimum value, generally 48 volts. In this state, the power storage device will not continue to discharge, otherwise it may cause damage to the power storage device.
  • the electric storage device controller calculates the charging power according to the redundant power of the electric storage device and the duration of the electricity price interval in which the current reading time is located; and adjusts the power supply voltage according to the calculated charging power so as to make The power supply voltage is higher than the voltage of the power storage device, and the power storage device is charged.
  • the power storage device controller divides the calculated absolute value of the redundant power of the power storage device by the duration of the electricity price interval at the current reading time to obtain the charging power, and then adjusts the power supply voltage so that the power supply voltage is higher than
  • the voltage of the power storage device ensures that the power supply module charges the power storage device while supplying power to the device, so that the power storage device stores the electricity with the current lower electricity price.
  • the power storage device controller calculates the discharge power according to the redundant power of the power storage device and the duration of the electricity price interval in which the current reading time is located; adjusts the power supply voltage according to the calculated discharge power to The power supply voltage is made lower than the voltage of the power storage device to ensure that the power storage device supplies power to the device.
  • the power storage device controller divides the calculated absolute value of the redundant power of the power storage device by the duration of the electricity price interval at the current reading time to obtain the discharge power, and then adjusts the power supply voltage so that the power supply voltage is lower than
  • the voltage of the power storage device ensures that the power storage device supplies power to the device, and the device will not use the power provided by the power module until the power stored by the power storage device is consumed.
  • S204 The power storage device controller supplies power to the device according to the obtained power supply strategy.
  • the power storage device controller sends a corresponding instruction to the power module management apparatus, so that the power module or the power storage device supplies power to the device. For example, if the power storage device controller determines to select a power module to supply power to the device, it will issue an instruction to increase the power supply voltage to the power module management device, so that the power module management device increases the power supply voltage according to the command to ensure that the power supply voltage is higher than that of the power storage device.
  • the power supply module supplies power to the device and charges the power storage device at the same time; the power storage device controller determines that the power storage device is selected to supply power to the device, and will issue a command to reduce the power supply voltage to the power module management device, so that the power supply
  • the module management device reduces the power supply voltage according to the instruction to ensure that the power supply voltage is lower than the voltage of the power storage device, and the power storage device supplies power to the device.
  • the charging and discharging process of the power storage device controller for the power storage device is realized by controlling the power supply voltage.
  • the power storage device is completely passive and does not need to directly receive instructions from the power storage device controller.
  • the process of charging or supplying power to the device can be completed by corresponding transformation of the voltage change.
  • the electric storage device controller obtains the current of the electric storage device, and determines whether to adjust the charging power or the discharging power according to the obtained current of the electric storage device.
  • the power storage device controller may periodically query the current of the current power storage device, or the power storage device may periodically report itself
  • the current where the query period or the reporting period can be set according to actual needs, for example, it can be set to 5 seconds.
  • the power storage device controller adjusts the charging power or the discharging power of the power storage device by adjusting the current limiting coefficient of the power module or the current limiting coefficient of the power storage device.
  • the power storage device controller can adjust the current limiting coefficient of the power supply or the current limiting coefficient of the power storage device to increase the current value passing through the power storage device, thereby increasing the charging power and ensuring that the power storage device can perform smoothly as expected.
  • the power storage device controls The charger can also reduce the current value passing through the power storage device by adjusting the current limiting coefficient of the power supply or the current limiting coefficient of the power storage device, thereby reducing the charging power and ensuring that the power storage device can be smoothly charged as expected.
  • the power storage device controller can adjust the current limiting coefficient of the power storage device to increase the current value output by the power storage device, thereby increasing the discharge power and ensuring that the power storage device can discharge smoothly as expected; If the discharge power calculated by the electrical equipment controller according to the current of the electrical storage equipment obtained in the current period is greater than the expected discharge power (that is, the discharge rate of the electrical storage equipment is higher than the expected rate), the electrical storage equipment controller adjusts the limit of the electrical storage equipment.
  • the flow coefficient reduces the current value output by the power storage device, thereby reducing the discharge power and ensuring that the power storage device can discharge smoothly as expected.
  • the electricity price is not constant, but presents a ladder shape.
  • the electricity price in each time period is different, but the Electricity prices are the same.
  • the power load of the device is constantly changing, and its change is shown in the load curve in Figure 4.
  • the upper limit of the power load of the power module is fixed and will not change over time.
  • the chargeable amount and power consumption of each time period can be calculated. For example, the chargeable amount corresponding to the first electricity price interval is A1, the electricity consumption is B1; the chargeable quantity corresponding to the second electricity price interval is A2, and the electricity consumption is B2.
  • the power storage device controller traverses all subsequent electricity price ranges from the second electricity price range. If the current traversal of the second electricity price range and the electricity price p2 is less than p1, the low-price rechargeable amount L is updated and adjusted to A2, and continues to traverse the subsequent electricity price range. price range.
  • the power supply module should be selected to supply power to the device and charge the power storage device at the same time.
  • the power storage device should be selected. powered by. After the traversal is completed, for each power price interval higher than the current power price p1, a corresponding redundant power R of the power storage device can be calculated, and the minimum value is selected from the redundant power of all the calculated power storage devices. If the minimum value is less than 0, the power supply module is selected to supply power to the device and the power storage device is charged at the same time. The charged amount is the absolute value of the minimum value. If the minimum value is greater than 0, the power storage device is selected to supply power to the device. In order to make the electricity storage device release the stored electricity, the released electricity is the minimum value.
  • the above only takes the first electricity price interval as the initial electricity price interval as an example for illustration, and the initial electricity price interval can be any electricity price interval, and the decision-making process is similar to the above.
  • FIG. 5 is a schematic structural diagram of a power supply control device provided by an embodiment of the present application.
  • the power supply control device may be the power storage device controller in the method embodiment described in FIG. 2 above, and may execute the power supply control device shown in FIG.
  • the methods and steps in the embodiments of the device power supply method described above take the power storage device controller as the execution subject.
  • the power supply control apparatus 500 includes a power prediction module 510 , a processing module 520 and a communication module 530 . in,
  • a power prediction module 510 configured to predict the power load of the device in an electricity price interval, where the electricity price interval is the same and continuous period of time;
  • a processing module 520 configured to select a power supply strategy for the device according to the power load of the device in the electricity price interval, the stored power of the electricity storage device at the first moment, and the electricity price in the electricity price interval at the first moment;
  • the communication module 530 is configured to send a power supply command to the power supply or the power storage device, so that the power supply or the power storage device supplies power to the device.
  • the power prediction module 510 is configured to execute the aforementioned step S201, and optionally execute the optional method in the aforementioned step S201
  • the processing module 520 is configured to execute the aforementioned step S202 and step S203, and optionally execute the aforementioned steps S202 and S203.
  • the communication module 530 is configured to execute the foregoing step S204, and optionally execute the optional method in the foregoing step S204.
  • the above three modules can transmit data to each other through a communication channel. It should be understood that each module included in the power supply control device 500 may be a software module, a hardware module, or a part of a software module and a part of a hardware module.
  • the power prediction module 510 and the processing module 520 in this embodiment of the present application may be implemented by a processor or a circuit component related to the processor, and the communication module may be implemented by a transceiver or a circuit component related to the transceiver.
  • each module in the power supply control device may be added, reduced or combined as required.
  • the operation and/or function of each module in the power supply control device is to implement the corresponding flow of the method described in FIG. 2 , which is not repeated here for brevity.
  • FIG. 6 is a schematic structural diagram of a computing device provided by an embodiment of the present application.
  • the computing device 600 includes a processor 610 , a communication interface 620 and a memory 630 , and the processor 610 , the communication interface 620 and the memory 630 are connected to each other through an internal bus 640 .
  • the computing device 600 may be a server.
  • the computing device 600 may be the electrical storage device control apparatus in FIG. 1 , and the functions performed by the electrical storage device control apparatus in FIG. 1 are actually performed by the processor 610 of the computing device.
  • the processor 610 may be composed of one or more general-purpose processors, such as a central processing unit (central processing unit, CPU), or a combination of a CPU and a hardware chip.
  • the above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the above-mentioned PLD may be a complex programmable logic device (CPLD), a field programmable gate array (FPGA), a general array logic (generic array logic, GAL) or any combination thereof.
  • the bus 640 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus 640 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in FIG. 6, but it does not mean that there is only one bus or one type of bus.
  • the memory 630 may include volatile memory (volatile memory), such as random access memory (RAM); the memory 630 may also include non-volatile memory (non-volatile memory), such as read-only memory (read- only memory, ROM), flash memory (flash memory), hard disk drive (HDD) or solid-state drive (solid-state drive, SSD); the memory 630 may also include a combination of the above types.
  • volatile memory such as random access memory (RAM)
  • non-volatile memory such as read-only memory (read- only memory, ROM), flash memory (flash memory), hard disk drive (HDD) or solid-state drive (solid-state drive, SSD
  • ROM read-only memory
  • flash memory flash memory
  • HDD hard disk drive
  • SSD solid-state drive
  • the computing device 600 may correspond to the energy storage device controller in the above method embodiments
  • the memory 630 stores program codes corresponding to each module of the power supply control apparatus 500
  • the processor 610 executes these program codes to implement the power supply control apparatus The functions of each module of 500, that is, the methods of S201-S204 are executed.
  • the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any part of any one of the foregoing method embodiments can be implemented or all steps.
  • the embodiment of the present invention also provides a computer program, the computer program includes instructions, when the computer program is executed by the computer, the computer can execute part or all of the steps of any method for issuing regional resources.
  • the above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination.
  • the above-described embodiments may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center is by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server, a data center, or the like containing one or more sets of available media.
  • the usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media.
  • the semiconductor medium may be a solid state drive (SSD).

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Power Engineering (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Emergency Management (AREA)
  • Educational Administration (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

一种设备供电方法、系统及相关设备，涉及能源技术领域。该方法包括：预测设备在电价区间的功率负载，该电价区间为电价相同且连续的一段时间；根据设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻的电价，选择对该设备的供电策略；按照选择获得的供电策略对设备进行供电。上述方法能够结合电价情况灵活选择对设备的供电方式，减少设备的供电成本。

Description

设备供电的方法、系统及相关设备 技术领域
本申请涉及能源技术领域，尤其涉及一种设备供电的方法、系统及相关设备。
背景技术
电力系统包括发电站和传输发电站产生电量的电网(如各种电压的变电所及输配电线路)，电力系统用于对设备进行供电。电网根据设备的需求传输电量。电网的负载通常是不平衡的，例如，白天电网的负载高，而晚上电网的负载比较低。而发电站的发电能力通常比较平稳，不会出现较大的起伏，由于电网的负载不平衡，导致在低谷时段(即电网负载低的时段)用电需求较低，发电站有多余的发电能力无法利用，在高峰时段(即电网负载高的时段)用电需求较高，超过发电站的供电能力。电网通过提高在高峰时段的电价，促使用户减少高峰时段的用电量，从而达到平衡电网负载的目的，这种电价方式也被称为阶梯电价。
而对于存在较多设备的数据中心中场景，电量需求较大，而且在不同时段设备的工作负载又不同，导致整个数据中心的电量需求也随之波动。目前，设备的供电方式都是直接利用发电站通过电网发送的电量，而设备需要一直保持供电状态，不会区分低谷时段和高峰时段，导致设备的电费成本较高。
因此，如何调整设备的供电方式，减少设备的电费开支成为亟待解决的技术问题。
发明内容
本申请公开了一种设备供电的方法、系统以及相关设备，能够根据电价灵活选择对设备的供电方式，减少设备的供电成本。
第一方面，本申请提供一种设备供电的方法，所述方法包括：储电设备控制器预测设备在电价区间的功率负载，该电价区间为电价相同且连续的一段时间；该储电设备控制器根据设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及第一时刻所在的电价区间的电价，选择对该设备的供电策略；该储电设备控制器按照选择获得的供电策略对设备进行供电。
可选的，储电设备控制器可以仅预测设备在与当前电价区间相邻的下一个电价区间的功率负载，或者，设备在与当前电价区间非相邻的下一个电价区间的功率负载，或者，设备在当前电价区间之后的多个电价区间的功率负载，或者，设备在当前电价区间之后的所有电价区间的功率负载。
在本申请提供的方案中，储电设备控制器通过预测设备在电价区间的功率负载，进而结合储电设备在第一时刻的储存电量以及第一时刻所在的电价区间的电价，可以灵活的选择对设备的供电策略，从而可以减少设备的供电成本。
在一种可能的实现方式中，该储电设备控制器根据设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及第一时刻所在的电价区间的电价，计算储电设备的冗余电量；该储电设备控制器根据储电设备的冗余电量确定对所述设备的供电模式，该供电模式包括选择电源对设备供电和选择储电设备对设备供电中任意一种。
在本申请提供的方案中，储电设备控制器通过计算储电设备的冗余电量从而确定对设备 的供电模式，可以保证能够灵活选择对设备的供电方式，避免只能选择电源对设备进行供电。
在另一种可能的实现方式中，当储电设备的冗余电量小于或等于第一阈值时，储电设备控制器选择电源对所述设备供电；当储电设备的冗余电量大于或等于第二阈值时，储电设备控制器选择储电设备对所述设备供电。
在本申请提供的方案中，储电设备控制器根据储电设备的冗余电量与第一阈值和第二阈值的大小关系，选择对设备的供电方式，可以保证所选择的供电方式能够减少设备的供电成本。
在另一种可能的实现方式中，储电设备控制器根据设备在电价区间的功率负载，计算设备在电价区间的用电量和电源在该电价区间的可充电量；储电设备控制器根据设备在电价区间的用电量和电源在该电价区间的可充电量，统计得到低价可充电量和高价用电量，该低价可充电量为电源在所述电价区间中比第一时刻所在的电价区间的电价低的电价区间的可充电量之和，该高价用电量为所述设备在所述电价区间中比所述第一时刻所在的电价区间的电价高的电价区间的用电量之和；储电设备控制根据所述储电设备在第一时刻的储存电量以及所述低价可充电量和所述高价用电量，计算得到所述储电设备的冗余电量，所述储电设备的冗余电量为所述储电设备在第一时刻的储存电量与所述低价可充电量之和再减去所述高价用电量。
在本申请提供的方案中，储电设备控制器通过预测得到的区间的功率负载，从而得到设备在电价区间的用电量，再结合电源在电价区间的可充电量以及储电设备的初始储存电量，进而可以计算得到储电设备的冗余电量，这样，可以保证在后续决策过程中，储电设备控制器能够正确的选择对设备的供电策略。
在另一种可能的实现方式中，当所述储电设备的冗余电量小于或等于第一阈值时，储电设备控制器选择所述电源对所述设备供电，且所述电源在对所述设备进行供电的同时对所述储电设备进行充电，所述储电设备的充电量为所述冗余电量的绝对值；当所述储电设备的冗余电量大于或等于第二阈值时，储电设备控制器选择所述储电设备对所述设备供电，且所述储电设备的电压在小于或等于电压阈值时停止对所述设备供电，选择所述电源继续对所述设备进行供电，所述储电设备的放电量为所述冗余电量。
在本申请提供的方案中，储电设备控制器根据储电设备的冗余电量与第一阈值和第二阈值的关系，灵活选择对设备的供电方式，从而可以使得储电设备能够在充电和放电之间进行灵活的切换，最终实现减少设备的供电成本的目的。
在另一种可能的实现方式中，储电设备控制器根据储电设备的冗余电量和第一时刻所在的电价区间的时长，计算充电功率；储电设备控制器根据该充电功率调整电源电压，以使得电源电压高于储电设备的电压，该电源对储电设备进行充电。
在本申请提供的方案中，储电设备控制器通过计算充电功率，从而调整电源电压使其高于储电设备的电压，完成对储电设备的充电，这样可以保证储电设备的充电过程简单高效，提高了储电设备的充电效率。
在另一种可能的实现方式中，储电设备控制器根据储电设备的冗余电量和第一时刻所在的电价区间的时长，计算放电功率；储电设备控制器根据该放电功率调整电源电压，以使得电源电压低于储电设备的电压，该储电设备对设备进行供电。
在本申请提供的方案中，储电设备控制器通过计算放电功率，从而调整电源电压使其低于储电设备的电压，完成储电设备对设备进行供电，这样可以保证储电设备的放电过程实现简单且高效，提高了储电设备的放电效率。
在另一种可能的实现方式中，储电设备控制器获取储电设备的电流；储电设备控制器根据获取得到的储电设备的电流，确定是否调整充电功率或放电功率；在确定调整所述充电功率或所述放电功率的情况下，调整电源的限流系数和/或储电设备的限流系数。
在本申请提供的方案中，储电设备控制器通过获取储电设备的电流，计算出电设备的充电功率或放电功率，并判断其与预期确定的充电功率或放电功率是否一致，在不一致的情况下通过调整电源的限流系数或储电设备的限流系数以提高通过储电设备的电流值或减小通过储电设备的电流值，从而保证储电设备能够按照预期进行平稳充电或放电。
在另一种可能的实现方式中，储电设备控制器确定初始功率预测模型，所述初始功率预测模型包括深度学习模型；储电设备控制器获取所述设备的历史功率负载数据，所述历史功率负载数据包括所述设备在所述第一时刻之前所记录的功率负载；储电设备控制器利用所述历史功率负载数据对所述初始功率预测模型进行训练。
在本申请提供的方案中，储电设备控制器利用设备的历史功率负载数据作为样本数据对初始功率预测模型进行训练，以使得训练完成的功率预测模型具备预测设备在电价区间的功率负载的能力，这样可以提高储电设备控制器获得设备在电价区间的功率负载的准确性，以及所选择的对设备的供电策略的准确性。
第二方面，本申请提供了一种供电控制装置，包括：功率预测模块，用于预测设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间；处理模块，用于根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述设备的供电策略；通信模块，用于将供电命令发送给电源或所述储电设备，以使得所述电源或所述储电设备对所述设备进行供电。
在一种可能的实现方式中，所述处理模块，还用于：根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，计算所述储电设备的冗余电量；根据所述储电设备的冗余电量选择供电模式，所述供电模式包括选择所述电源对所述设备供电和选择所述储能设备对所述设备供电中任意一种。
在另一种可能的实现方式中，所述处理模块，还用于：当所述储电设备的冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电；当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电。
在另一种可能的实现方式中，所述处理模块，还用于：根据所述设备在电价区间的功率负载，计算所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量；根据所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量，统计得到低价可充电量和高价用电量，所述低价可充电量为所述电源在所述电价区间中比所述第一时刻所在的电价区间的电价低的电价区间的可充电量之和，所述高价用电量为所述设备在所述电价区间中比所述第一时刻所在的电价区间的电价高的电价区间的用电量之和；根据所述储电设备在第一时刻的储存电量以及所述低价可充电量和所述高价用电量，计算得到所述储电设备的冗余电量，所述储电设备的冗余电量为所述储电设备在第一时刻的储存电量与所述低价可充电量之和再减去所述高价用电量。
在另一种可能的实现方式中，所述处理模块，还用于：当所述储电设备的冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电，且所述电源在对所述设备进行供电的同时对所述储电设备进行充电，所述储电设备的充电量为所述冗余电量的绝对值；当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电，且所述储电设备的电压在小于或等于电压阈值时停止对所述设备供电，选择所述电源继续对所述设备进行 供电，所述储电设备的放电量为所述冗余电量。
在另一种可能的实现方式中，所述处理模块，具体用于：根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算充电功率；根据所述充电功率调整所述电源电压，以使得所述电源电压高于所述储电设备的电压，所述电源对所述储电设备进行充电。
在另一种可能的实现方式中，所述处理模块，具体用于：根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算放电功率；根据所述放电功率调整所述电源电压，以使得所述电源电压低于所述储电设备的电压，所述储电设备对所述设备进行供电。
在另一种可能的实现方式中，所述处理模块，还用于：获取所述储电设备的电流；根据获取得到的所述储电设备的电流，确定是否调整所述充电功率或所述放电功率；在确定调整所述充电功率或所述放电功率的情况下，调整所述电源的限流系数和/或所述储电设备的限流系数。
在另一种可能的实现方式中，所述处理模块，还用于：确定初始功率预测模型，所述初始功率预测模型包括深度学习模型；获取所述设备的历史功率负载数据，所述历史功率负载数据包括所述设备在所述第一时刻之前所记录的功率负载；利用所述历史功率负载数据对所述初始功率预测模型进行训练。
第三方面，本申请提供了一种计算设备，所述计算设备包括处理器和存储器，所述存储器用于存储程序代码，所述处理器执行所述存储器中的程序代码实现上述第一方面以及结合上述第一方面中的任意一种实现方式的方法的操作步骤。
第四方面，本申请提供了一种设备供电系统，包括电源模块管理装置、储电设备和供电设备控制装置，所述供电设备控制装置，用于预测用电设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间，并根据所述用电设备在电价区间的功率负载、所述储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述用电设备的供电策略；所述储电设备，用于储存电量以及对所述用电设备进行供电；所述电源模块管理装置，用于对所述用电设备进行供电以及对所述储电设备进行充电。
第五方面，本申请提供了一种计算机可读存储介质，所述计算机可读储存介质存储有计算机程序，当该计算机程序被处理器执行时，所述处理器执行上述第一方面以及结合上述第一方面中的任意一种实现方式所提供的设备供电方法的操作步骤。
第六方面，本申请提供了一种计算机程序产品，该计算机程序产品包括指令，当该计算机程序产品被计算机执行时，使得计算机可以执行上述第一方面以及结合上述第一方面中的任意一种实现方式所提供的设备供电方法的流程。
本申请在上述各方面提供的实现方式的基础上，还可以进一步组合以提供更多实现方式。
附图说明
图1是本申请实施例提供的一种设备供电系统的系统架构图；
图2是本申请实施例提供的一种设备供电方法的流程示意图；
图3是本申请实施例提供的一种反向传播神经网络的结构示意图；
图4是本申请实施例提供的一种设备供电模式的决策示意图；
图5是本申请实施例提供的一种供电控制装置的结构示意图；
图6是本申请实施例提供的一种计算设备的结构示意图。
具体实施方式
下面结合附图对本申请实施例中的技术方案进行描述。
首先，对本申请中所涉及的部分用语和相关技术进行解释说明，以便于本领域技术人员理解。
电量(quantity of electric charge)表示物体所带电荷的多少，一般来说，电荷的数量叫做电量，符号为Q，单位是库伦(C)，电量也可以指用电设备所需用电能的数量，这时又称为电能或电功。
电能(electric energy)是指使用电以各种形式做功(即产生能量)的能力，电能的单位是千瓦时(kw*h)。
导体中的自由电荷在电场力的作用下做有规则的定向运动形成了电流，单位时间内通过导体任一横截面的电量叫做电流强度，简称电流，符号为I，单位是安培(A)。
电功率(electric power)是指电流在单位时间内做的功，用来表示消耗电能的快慢，符号为P，单位是瓦特(W)，电功率的计算公式为：P＝W/t，表示在单位时间内所消耗的电能。
数据中心时刻不停的保持运行需要耗费大量的电量，由于数据中心的设备，例如计算设备、网络设备、存储设备等需要时刻保持供电状态以保证能够正常对外提供服务，所以在高峰时段将会产生大量的电费成本。为了减少数据中心在高峰时段对电网的电能需求，减少数据中心的电费成本，本申请提供了一种设备供电的方法，能够改变设备的供电方式，减少设备在高峰时段对电网的电能需求，有效减少设备的供电成本。
如图1所示，图1是本申请提供的一种设备供电系统的系统架构图，电力系统与设备供电系统进行连接，并通过设备供电系统中的电源模块管理装置池对设备进行供电，其中，电源模块管理装置也可以称为电源，电源模块管理装置池也可以称为电源池。设备供电系统包括储电设备控制装置110、储电设备资源池120、电源模块管理装置池130和用电设备群140。其中，储电设备控制装置110可以是一个具备计算能力和通信能力的芯片(例如现场可编程逻辑门阵列(field-programmable gate array，FPGA)芯片)或一个服务器节点，储电设备控制装置110中部署有功率预测模块1110、供电策略决策模块1120、通信模块1130、数据存储模块1140，这些模块之间通过内部总线相互连接，彼此协同，对外实现控制功能。储电设备资源池120中存在一个或多个储电设备，例如储电设备1210、储电设备1220、储电设备1230，每个储电设备可以是一个锂电池储能柜，用于储存供电系统输入的电量或者对用电设备群140进行供电。电源模块管理装置池130中包括一个或多个电源模块管理装置，例如电源模块管理装置1310、电源模块管理装置1320、电源模块管理装置1330，每个电源模块管理装置中部署有一个或多个电源模块和电源管理软件，每个电源模块可以由变压器、电芯及相关电路组成，用于将电力系统输入的具有标准电压(例如220伏特)的电量转换为适合用电设备和储电设备正常工作的电压(例如50伏特)的电量，电源模块可以直接对用电设备进行供电以及通过变压器调节电压对储电设备进行充电，例如电源模块管理装置1310中部署有电源模块13111、电源模块13112、电源模块13113以及电源管理软件13120，它们之间相互连接，由电源管理软件13120对电源模块13111、电源模块13112、电源模块13113进行管理和控制。电源模块中所有的电量都是由供电系统直接提供，并对用电设备群140进行供电或对储电设备资源池120中的储电设备进行充电，电源模块管理装置池130中的每个电源模块管理装置可以与储电设备资源池120中的一个或多个储电设备进行连接，然后对用电设备群140中的设备进行供电，用电设备群可以是由多个数据中心的设备组成的设备集群，例如计算设备1410、网络设备1420和存储设备1430。当然，储电设备资源池120中的每个储电设备也可以与电 源模块管理装置池130中的一个或多个电源模块管理装置进行连接，然后对用电设备群140中的设备进行供电，为了保证供电稳定，在本申请中，优选储电设备资源池120中的储电设备与电源模块管理装置池130中的电源模块管理装置进行一对一连接，即每个储电设备对应连接一个电源模块管理装置。
储电设备控制装置110中的通信模块1130可以是一个通信端口，由收发器或收发器相关电路组件组成，用于接收电源模块管理装置池130中电源模块管理装置部署的电源管理软件发送的功率负载数据和储电设备资源池120中储电设备相关数据(例如储电设备的储存电量)，并将其存储至数据存储模块1140，数据存储模块1140可以是片上随机存取存储器(random access memory，RAM)或者是服务器中的动态随机存取存储器(dynamic random access memory，DRAM)。功率预测模块1110可以是片上算术逻辑运算单元(arithmetic and logic unit，ALU)或服务器中的通用阵列逻辑(generic array logic)芯片，用于根据数据存储模块1140中存储的功率负载数据，预测得到用电设备群140中的设备在未来一段时间内(例如一天之内)的功率负载曲线，供电模式决策模块1120可以是由处理器或处理器相关电路组件组成，用于根据功率预测模块1110预测得到的功率负载曲线以及数据存储模块1140中存储的电价曲线和储电设备的储存电量，从而选择对用电设备群140的供电策略，并计算得到储电设备的充/放电量和充/放电功率，最后通过通信模块1130将计算得到的充/放电量和充/放电功率发送给电源模块管理装置中的电源管理软件，从而完成对储电设备的充放电。
可以看出，在本申请中，用电设备群140中的设备可以通过电源模块管理装置池130中的电源模块进行供电，也可以通过储电设备资源池120中的储电设备进行供电，且电源模块可以对储电设备进行充电。因此，储电设备控制装置110通过在低谷时段给电源模块下发充电命令，使得电源模块在电价较低时对储电设备进行充电，然后在高峰时段利用储电设备中储存的电量对用电设备群140中的设备进行供电，可以减少设备在高峰时段对电源模块的电量需求，减少在电价较高时对电源模块的电量消耗，最终实现减少设备的供电成本。
值得说明的是，数据中心的基础电力设施建好之后，会设置一个最大的输出功率，该最大输出功率用于保证数据中心中设备的供电需求，但是，由于处于工作状态的设备的数量或负载不同，通常设备的供电需求不会超过最大功率，此时，可以将满足设备的供电需求的功率以外的富余功率用于对储电设备进行充电。
下面结合图1所示的系统架构，具体描述如何进行设备供电的过程。如图2所示，该方法包括但不限于以下步骤：
S201：储电设备控制器利用功率预测模型预测得到设备在电价区间的功率负载。
具体地，储电设备控制器可以部署在任意一个具备计算通信能力的服务器或者计算设备上，该储电设备控制器可以是上述图1中所示的储电设备控制装置110。本申请中的用电设备可以是计算设备、网络设备、存储设备或其它需要消耗电力资源的设备。
应理解，电价指使用电能的价格，可以人为制定，电价并不是一直不变的，而是阶梯变化的，即在不同的时间段其所对应的电价是不相同的，例如晚上十一点至凌晨七点用电人数较少，负载较小，电价较低，早上九点至下午六点，用电人数较多，负载较大，电价较高。本申请中的电价区间是指电价相同且连续的一段时间，例如上述所描述的晚上十一点至凌晨七点。
储电设备控制器需要周期性的读取电价曲线，其读取周期可以根据实际需要进行设置，例如可以设置为1小时，储电设备控制器根据电价曲线获得当前读取时刻(即第一时刻)所在的电价区间的电价，然后判断当前读取时刻的电价与上一周期读取时刻(第二时刻)，即距 离当前读取时刻为一个周期时长(1小时)之前的时刻所在的电价区间的电价是否相同，示例性的，假设读取周期为1小时，储电设备控制器在早上九点读取电价曲线，得到九点所在的电价区间的电价，然后判断该电价与上一周期读取时刻(即早上八点)所在的电价区间的电价是否相同，若相同，则说明未产生电价拐点，即第一时刻所在的电价区间与第二时刻所在的电价区间为同一电价区间，此时不需要调整对设备的供电模式，若不相同，则说明产生了电价拐点，即第一时刻所在的电价区间与第二时刻所在的电价区间为不同的电价区间，此时需要重新确定供电策略，需要触发储电设备控制器利用功率预测模型预测设备在未来电价区间的功率负载，并根据预测结果进一步判断是否需要对设备的供电策略进行调整。
作为一种可能的实施例，储电设备控制器利用功率预测模型进行预测时，可以仅预测设备在当前读取时刻所在的电价区间的下一个(例如，与当前电价区间相邻的下一个电价区间，或者，与当前电价区间非相邻的下一个电价区间)电价区间的功率负载，或者是预测设备在当前读取时刻所在的电价区间之后的多个电价区间的功率负载，或者是预测设备在当前读取时刻所在的电价区间之后的所有电价区间的功率负载，本申请对此不作限定，为了便于叙述，本申请以储电设备控制器一次预测所有电价区间的功率负载为例进行说明。
进一步的，储电设备控制器在进行预测之前，需要对设备的历史功率负载(例如最近一周内的功率负载)进行采样，其采样周期可以根据实际需要进行设置，例如可以设置为10秒，即每隔10秒采集一次设备的功率负载，并将采集到的数据进行存储。在采集到足够的历史功率负载数据之后，储电设备控制器可以根据所采集到的历史功率负载数据预测得到该设备在未来各个电价区间内的功率负载。可选地，储电设备控制器也可以按照电价区间划分不同时间段，分别对每段的功率负载进行采样。
可选的，储电设备控制器可以利用预设算法预测设备的功率负载。其中，预设算法用于对采用数据依赖于时间序列进行分析获得满足特定特征的结果。预设算法包括极端的梯度增加(eXtreme gradient boosting，XGBoost)算法、随机森林算法、神经网络算法或其它通过时间序列进行预测的算法预测设备的功率负载。
示例性的，储电设备控制器可以利用反向传播神经网络(back-propagation network，BP)对设备的功率负载进行预测，BP网络通过对样本数据的训练，不断修正网络权值和阈值，使误差函数沿负梯度方向下降，最终逼近期望输出。下面对BP网络的训练过程进行具体描述，如图3所示，图3是BP网络的架构图，BP网络包括输入层、隐层和输出层，隐层可以有一层或多层，输入层神经元个数为7，隐层的神经元个数为4，输出层的神经元个数为1。首先利用初始化函数对BP网络的参数进行初始化操作，或者随机选取参数值对该网络进行初始化操作，例如使用0.001的常量或者基于0.001的高斯分布进行初始化，然后设定隐层和输出层的激励函数、网络性能函数和迭代次数，例如，隐层的激励函数可以设为tansig函数，输出层的激励函数可以设为logsig函数，网络性能函数可以设为traingdx函数，迭代次数可以设为5000次。
之后将采集获得的历史功率负载数据作为样本数据进行归一化操作之后输入至输入层，输入层经过处理之后传输至隐层，隐层对其进行进一步处理(卷积计算)，并将处理结果传送至输出层，输出层根据以损失函数为目标函数使用反向传播算法更新调整网络中的参数，迭代执行上述过程，直到损失函数值收敛，此时BP网络训练完成，BP网络具备了预测设备的功率负载的能力，储电设备控制器可以利用该训练完成的BP网络预测设备在未来各个电价 区间的功率负载。其中，在训练过程中，网络传递函数可以选用S型传递函数，例如
Figure PCTCN2021088668-appb-000001
Figure PCTCN2021088668-appb-000002
误差函数则为
Figure PCTCN2021088668-appb-000003
其中，T i为期望输出，O i为网络的计算输出，根据误差函数，通过不断调节网络权值和阈值使误差函数E达到极小，最终完成训练。
需要说明的是，储电设备控制器可以同时利用多种预测算法对设备未来的功率负载进行预测，例如同时使用XGBoot算法、随机森林算法和神经网络算法进行预测，然后对各个算法的预测结果进行比较，最终选取最准确、最符合实际情况的预测算法，并将该算法的预测结果作为最终输出结果。
S202：储电设备控制器根据设备在电价区间的功率负载、储电设备在第一时刻的存储电量以及所述第一时刻所在的电价区间的电价，计算得到所述储电设备的冗余电量。
具体地，储电设备控制器根据步骤S201得到设备在电价区间的功率负载之后，可以计算得到设备在电价区间的用电量，应理解，设备在某个电价区间的用电量为设备在该电价区间的功率负载在该电价区间所对应的时间段内的积分。例如，电价区间为早上七点至早上八点，设备在该时段内的功率负载为10千瓦(kw)，则该设备在该电价区间的用电量为10千瓦时(kw*h)。
储电设备控制器进一步计算电源模块在电价区间的可充电量，即在设置了最大的输出功率的情况下，电源模块除了满足设备的供电需求的功率之外的富余功率所提供的电量，该电源模块可以是上述图1中所示的电源模块管理装置池130中的电源模块，由于电力设施本身存在物理上限，即电力设施设置了最大的输出功率，因此在已知设备在电价区间的功率负载的情况下，可以计算出电源模块在电价区间的可充电量。例如，电力设施的最大输出功率为15kw，在早上七点至早上八点这个电价区间内设备的功率负载为10kw，则可以计算得到电源模块在该电价区间内的可充电量为5kwh，即在该电价区间内，除去给设备供电外，电源模块的可充电量为5kwh。
储电设备控制器在计算得到设备在电价区间的用电量以及电源在电价区间的可充电量之后，统计得到低价可充电量和高价用电量，低价可充电量为电源模块在低于当前读取时刻(第一时刻)所在的电价区间的电价的所有电价区间的可充电量之和，高价用电量为设备在高于当前读取时刻所在的电价区间的电价的所有电价区间的用电量之和。储电设备控制器在统计得到低价可充电量和高价用电量之后，可以计算得到储电设备的冗余电量，储电设备的冗余电量为储电设备在当前读取时刻的储存电量与低价可充电量之和，再减去高价用电量所获得的结果。
S203：储电设备控制器根据计算得到的储电设备的冗余电量，选择对所述设备的供电策略。
具体地，储电设备控制器根据计算得到的储电设备的冗余电量的结果，对储电设备的充放电情况做出决策，进而确定对设备的供电策略。当计算得到的储电设备的冗余电量小于第一阈值时，选择电源模块对设备进行供电，且电源模块在对设备进行供电的同时对储电设备进行充电，储电设备的充电量为冗余电量的绝对值；当计算得到的储电设备的冗余量大于或等于第二阈值时，选择储电设备对设备进行供电，储电设备的放电量为该冗余电量。
可选的，第一阈值和第二阈值可以设置为相同的值，例如都设置为0，也可以设置为不同的值，例如将第一阈值设置为0.1，将第二阈值设置为0.5。
值得说明的是，由于储电设备的冗余电量是储电设备当前时刻的储存电量与低价可充电 量之和，再减去高价用电量的结果，以第一阈值和第二阈值都设置为0为例进行说明，若冗余电量小于0，则说明在当前时刻所在的电价区间之后的电价区间中，电源模块的低价可充电量与当前时刻储电设备所储存的电量之和，仍不能满足设备的高价用电量，因此，储电设备控制器选择电源模块对设备进行供电，且在供电的同时对储电设备进行充电，以使得储电设备在当前时刻所在的电价区间内将电源模块充入的电量储存起来，以便在后续电价较高的电价区间内将储存的电量提供给设备使用，减少设备的高价用电量，储电设备的充电量为该冗余电量的绝对值。同理，若冗余电量大于0，则说明在当前时刻所在的电价区间之后的电价区间中，电源模块的低价可充电量与当前时刻储电设备所储存的电量之和，已经超过了设备的高价用电量，因此，储电设备控制器选择储电设备对设备进行供电，以使得储电设备在当前时刻所在的电价区间内将储存的电量释放出来以供设备使用，从而减少设备在当前时刻所在的电价区间内对电源模块的电量使用，储电设备的放电量为该冗余电量。
值得注意的是，储电设备储存电量的能力是有限的，当储电设备控制器选择储电设备对设备进行供电时，储电设备所储存的电量不断被消耗，导致储电设备的电压不断减小，当储电设备所储存的电量被消耗完毕时，即储电设备的电压小于或等于电压阈值时，储电设备停止对设备进行供电，此时，为了保证设备不断电，需要利用电源模块对设备继续进行供电。应理解，储电设备的电压与其所储存的电量有关，当储电设备所储存的电量达到最大值时，其电压也达到最大值，一般为52伏特，当储电设备储存的电量耗尽时，其电压达到最小值，一般为48伏特，在此状态下，储电设备不会继续放电，否则可能会对储电设备造成损害。
在一种可能的实现方式中，储电设备控制器根据储电设备的冗余电量和当前读取时刻所在的电价区间的时长，计算充电功率；根据计算得到的充电功率调整电源电压，以使得电源电压高于储电设备的电压，对储电设备进行充电。
具体地，储电设备控制器利用计算得到的储电设备的冗余电量的绝对值除以当前读取时刻所在的电价区间的时长，从而得到充电功率，然后调整电源电压，使电源电压高于储电设备的电压，保证电源模块在对设备进行供电的同时对储电设备进行充电，以使得储电设备将当前电价较低的电量储存起来。
在另一种可能的实现方式中，储电设备控制器根据储电设备的冗余电量和当前读取时刻所在的电价区间的时长，计算放电功率；根据计算得到的放电功率调整电源电压，以使得电源电压低于储电设备的电压，保证储电设备对所述设备进行供电。
具体地，储电设备控制器利用计算得到的储电设备的冗余电量的绝对值除以当前读取时刻所在的电价区间的时长，从而得到放电功率，然后调整电源电压，使电源电压低于储电设备的电压，保证储电设备对设备进行供电，设备在消耗完储电设备所储存的电量之前，不会使用电源模块所提供的电量。
S204：储电设备控制器按照获得的供电策略对所述设备进行供电。
具体地，储电设备控制器在确定对设备的供电策略之后，发送相应的指令至电源模块管理装置，以使得电源模块或储电设备对设备进行供电。例如，储电设备控制器确定选择电源模块对设备进行供电，则会下发提高电源电压的指令至电源模块管理装置，使得电源模块管理装置根据指令提高电源电压，保证电源电压高于储电设备电压，由电源模块对设备进行供电且同时对储电设备进行充电；储电设备控制器确定选择储电设备对设备进行供电，则会下发降低电源电压的指令至电源模块管理装置，使得电源模块管理装置根据指令降低电源电压，保证电源电压低于储电设备电压，由储电设备对设备进行供电。
可以看出，储电设备控制器对于储电设备的充放电过程是通过控制电源电压实现的，储 电设备是完全被动的，不需要直接接收储电设备控制器发出的指令，只需要根据电源电压的变化做出相对应的变换即可完成充电或对设备供电的过程。
在一种可能的实现方式中，储电设备控制器获取储电设备的电流，根据获取到的储电设备的电流，确定是否调整充电功率或放电功率。
具体地，在电源模块对设备进行供电的过程中或者储电设备对设备进行供电的过程中，储电设备控制器可以周期性查询当前储电设备的电流，或者储电设备周期性的上报自身的电流，其中，查询周期或上报周期可以根据实际需要进行设置，例如可以设置为5秒。
储电设备控制器获取到储电设备当前的电流之后，根据充电电压或放电电压，按照功率计算公式，即P＝I*U，计算出当前储电设备的充电功率或放电功率，然后判断储电设备是否按照预期确定的充电功率或放电功率进行充放电，若计算得到的储电设备当前的充电功率或放电功率偏离了预期，则储电设备控制器需要重新调整充电功率或放电功率，保证储电设备能够按照预期进行平缓充电或放电。
可选的，储电设备控制器通过调整所述电源模块的限流系数或所述储电设备的限流系数，以实现对所述储电设备的充电功率或放电功率的调整。
具体地，当电源模块对储电设备进行充电时，若储电设备控制器根据当前获取的储电设备的电流计算得到的充电功率小于预期确定的充电功率(即储电设备的充电速率低于预期速率)，则储电设备控制器可以调整电源的限流系数或储电设备的限流系数，提高通过储电设备的电流值大小，从而提高充电功率，保证储电设备能够按照预期进行平稳充电；同理，若储电设备控制器根据当前获取的储电设备的电流计算得到的充电功率大于预期确定的放电功率(即储电设备的充电速率高于预期速率)，则储电设备控制器也可以通过调整电源的限流系数或储电设备的限流系数，减小通过储电设备的电流值大小，从而减小充电功率，保证储电设备能够按照预期进行平稳充电。
类似的，当储电设备对设备进行供电时，若储电设备控制器根据当前获取的储电设备的电流计算得到的放电功率小于预期确定的放电功率(即储电设备的放电速率低于预期速率)，则储电设备控制器可以调整储电设备的限流系数，提高储电设备输出的电流值大小，从而提高放电功率，保证储电设备能够按照预期进行平稳放电；同理，若储电设备控制器根据当期获取的储电设备的电流计算得到的放电功率大于预期确定的放电功率(即储电设备的放电速率高于预期速率)，则储电设备控制器调整储电设备的限流系数，减小储电设备输出的电流值大小，从而减小放电功率，保证储电设备能够按照预期进行平稳放电。
为了进一步阐述对设备供电策略的决策过程，请参阅图4，如图4所示，电价并不是一直不变的，而是呈现阶梯状，每个时间段的电价不同，但同一时间段内的电价是一致的。设备的功率负载是不断变化的，其变化情况如图4中的负载曲线所示，电源模块的功率负载上限是固定的，不会随着时间的变化而发送改变。根据预测得到的功率负载曲线，以及电源模块的功率负载上限，可以计算得到每个时间段(即每个电价区间)的可充电量和用电量，例如第一电价区间对应的可充电量为A1，用电量为B1；第二电价区间对应的可充电量为A2，用电量为B2。
假设在第一电价区间，电价为p1，该时刻的储电设备的初始储存电量为s1，将该时刻的低价可充电量和高价用电量都设置为0，为了确定当前采取何种策略对设备进行供电，储电设备控制器从第二电价区间开始遍历后续所有电价区间，若当前遍历第二电价区间，电价p2小于p1，则低价可充电量L更新调整为A2，继续遍历后续的电价区间。若当前遍历第三电价区间，电价p3大于p1，则高价用电量H更新调整为B3，同时计算储电设备的冗余电量 R＝s1+L-H，即计算出储电设备的初始储存电量与低价可充电量(即第二电价区间的可充电量)之和相对于高价用电量(即第三电价区间的用电量)之间的差距，若小于0，则说明不够第三电价区间的用电量需求，则在第一电价区间内应该选择电源模块对设备进行供电且同时对储电设备进行充电，若大于0，则说明存在多余的电量，应选择储电设备对设备进行供电。遍历完成后，针对每一个比当前电价p1高的电价区间，都可以计算得到一个对应的储电设备的冗余电量R，从所有计算得到的储电设备的冗余电量之中选取最小值，若最小值小于0，则选择电源模块对设备进行供电且同时对储电设备进行充电，所充电量为该最小值的绝对值，若最小值大于0，则选择储电设备对设备进行供电，以使储电设备将储存的电量释放出来，所释放的电量为该最小值。
可以理解，上述只是以第一电价区间为起始电价区间为例进行说明的，起始电价区间可以为任意一个电价区间，其决策过程与上述类似，为了简洁，在此不再赘述。
值得说明的是，对于上述方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本发明所必须的。本领域的技术人员根据以上描述的内容，能够想到的其它合理的步骤组合，也属于本发明的保护范围内。
上述详细阐述了本申请实施例的方法，为了便于更好的实施本申请实施例的上述方案，相应地，下面还提供用于配合实施上述方案的相关设备。
参见图5，图5是本申请实施例提供的一种供电控制装置的结构示意图，该供电控制装置可以是上述图2所述的方法实施例中的储电设备控制器，可以执行图2所述的设备供电方法实施例中以储电设备控制器为执行主体的方法和步骤。如图5所示，该供电控制装置500包括功率预测模块510、处理模块520和通信模块530。其中，
功率预测模块510，用于预测设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间；
处理模块520，用于根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述设备的供电策略；
通信模块530，用于将供电命令发送给电源或所述储电设备，以使得所述电源或所述储电设备对所述设备进行供电。
具体地，所述功率预测模块510用于执行前述步骤S201，且可选的执行前述步骤S201中可选的方法，所述处理模块520用于执行前述步骤S202和步骤S203，且可选的执行前述步骤S202和步骤S203中可选的方法，所述通信模块530用于执行前述步骤S204，且可选的执行前述步骤S204中可选的方法。上述三个模块之间互相可以通过通信通路进行数据传输，应理解，供电控制装置500包括的各模块可以为软件模块、也可以为硬件模块、或部分为软件模块部分为硬件模块。
可以理解，本申请实施例中的功率预测模块510和处理模块520可以由处理器或处理器相关电路组件实现，通信模块可以由收发器或收发器相关电路组件实现。
需要说明的是，上述供电控制装置的结构仅仅作为一种示例，不应构成具体限定，可以根据需要对该供电控制装置中的各个模块进行增加、减少或合并。此外，该供电控制装置中的各个模块的操作和/或功能是为了实现上述图2所描述的方法的相应流程，为了简洁，在此不再赘述。
参见图6，图6是本申请实施例提供的一种计算设备的结构示意图。如图6所示，该计 算设备600包括：处理器610、通信接口620以及存储器630，所述处理器610、通信接口620以及存储器630通过内部总线640相互连接。应理解，该计算设备600可以是服务器。
所述计算设备600可以是图1中的储电设备控制装置，图1中的储电设备控制装置所执行的功能实际上是由所述计算设备的处理器610来执行。
所述处理器610可以由一个或者多个通用处理器构成，例如中央处理器(central processing unit，CPU)，或者CPU和硬件芯片的组合。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)、可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)、现场可编程逻辑门阵列(FPGA)、通用阵列逻辑(generic array logic，GAL)或其任意组合。
总线640可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。所述总线640可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但不表示仅有一根总线或一种类型的总线。
存储器630可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)；存储器630也可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory，ROM)、快闪存储器(flash memory)、硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；存储器630还可以包括上述种类的组合。
需要说明的是，计算设备600可以对应上述方法实施例中储能设备控制器，存储器630中存储了供电控制装置500的各个模块对应的程序代码，处理器610执行这些程序代码实现了供电控制装置500的各个模块的功能，即执行了S201-S204的方法。
本申请还提供一种计算机可读存储介质，其中，所述计算机可读存储介质存储有计算机程序，当该计算机程序被处理器执行时，可以实现上述方法实施例中记载的任意一种的部分或全部步骤。
本发明实施例还提供一种计算机程序，该计算机程序包括指令，当该计算机程序被计算机执行时，使得计算机可以执行任意一种发放区域资源的方法的部分或全部步骤。
上述实施例，可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时，上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载或执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质。半导体介质可以是固态硬盘(SSD)。
以上所述，仅为本申请的具体实施方式。熟悉本技术领域的技术人员根据本申请提供的具体实施方式，可想到变化或替换，都应涵盖在本申请的保护范围之内。

Claims (20)

  1. 一种设备供电的方法，其特征在于，所述方法包括：
    预测设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间；
    根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述设备的供电策略；
    按照选择获得的所述供电策略对所述设备进行供电。
  2. 如权利要求1所述的方法，其特征在于，根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述设备的供电策略，包括：
    根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，计算所述储电设备的冗余电量；
    根据所述储电设备的冗余电量确定对所述设备的供电模式，所述供电模式包括选择所述电源对所述设备供电和选择所述储电设备对所述设备供电中任意一种。
  3. 如权利要求2所述的方法，其特征在于，所述根据所述储电设备的冗余电量确定对所述设备的供电模式包括：
    当所述储电设备的所述冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电；
    当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电。
  4. 如权利要求2所述的方法，其特征在于，根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，计算所述储电设备的冗余电量，包括：
    根据所述设备在电价区间的功率负载，计算所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量；
    根据所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量，统计得到低价可充电量和高价用电量，所述低价可充电量为所述电源在所述电价区间中比所述第一时刻所在的电价区间的电价低的电价区间的可充电量之和，所述高价用电量为所述设备在所述电价区间中比所述第一时刻所在的电价区间的电价高的电价区间的用电量之和；
    根据所述储电设备在第一时刻的储存电量以及所述低价可充电量和所述高价用电量，计算得到所述储电设备的冗余电量，所述储电设备的冗余电量为所述储电设备在第一时刻的储存电量与所述低价可充电量之和再减去所述高价用电量。
  5. 如权利要求3或4所述的方法，其特征在于，所述方法还包括：
    当所述储电设备的冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电，且所述电源在对所述设备进行供电的同时对所述储电设备进行充电，所述储电设备的充电量为所述冗余电量的绝对值；
    当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电，且所述储电设备的电压在小于或等于电压阈值时停止对所述设备供电，选择所述电源继续对所述设备进行供电，所述储电设备的放电量为所述冗余电量。
  6. 如权利要求5所述的方法，其特征在于，
    所述电源对所述储电设备进行充电包括：
    根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算充电功率；
    根据所述充电功率调整所述电源电压，以使得所述电源电压高于所述储电设备的电压，所述电源对所述储电设备进行充电。
  7. 如权利要求5所述的方法，其特征在于，
    所述储电设备对所述设备进行供电包括：
    根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算放电功率；
    根据所述放电功率调整所述电源电压，以使得所述电源电压低于所述储电设备的电压，所述储电设备对所述设备进行供电。
  8. 如权利要求6或7所述的方法，其特征在于，所述方法还包括：
    获取所述储电设备的电流；
    根据获取得到的所述储电设备的电流，确定是否调整所述充电功率或所述放电功率；
    在确定调整所述充电功率或所述放电功率的情况下，调整所述电源的限流系数和/或所述储电设备的限流系数。
  9. 如权利要求1-8任一项所述的方法，其特征在于，在预测设备在电价区间的功率负载之前，所述方法还包括：
    确定初始功率预测模型，所述初始功率预测模型包括深度学习模型；
    获取所述设备的历史功率负载数据，所述历史功率负载数据包括所述设备在所述第一时刻之前所记录的功率负载；
    利用所述历史功率负载数据对所述初始功率预测模型进行训练。
  10. 一种供电控制装置，其特征在于，包括：
    功率预测模块，用于预测设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间；
    处理模块，用于根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述设备的供电策略；
    通信模块，用于将供电命令发送给电源或所述储电设备，以使得所述电源或所述储电设备对所述设备进行供电。
  11. 如权利要求10所述的供电控制装置，其特征在于，所述处理模块，还用于：
    根据所述设备在电价区间的功率负载、储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，计算所述储电设备的冗余电量；
    根据所述储电设备的冗余电量选择供电模式，所述供电模式包括选择所述电源对所述设备供电和选择所述储能设备对所述设备供电中任意一种。
  12. 如权利要求11所述的供电控制装置，其特征在于，所述处理模块，还用于：
    当所述储电设备的冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电；
    当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电。
  13. 如权利要求11所述的供电控制装置，其特征在于，所述处理模块，还用于：
    根据所述设备在电价区间的功率负载，计算所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量；
    根据所述设备在所述电价区间的用电量和所述电源在所述电价区间的可充电量，统计得到低价可充电量和高价用电量，所述低价可充电量为所述电源在所述电价区间中比所述第一时刻所在的电价区间的电价低的电价区间的可充电量之和，所述高价用电量为所述设备在所述电价区间中比所述第一时刻所在的电价区间的电价高的电价区间的用电量之和；
    根据所述储电设备在第一时刻的储存电量以及所述低价可充电量和所述高价用电量，计算得到所述储电设备的冗余电量，所述储电设备的冗余电量为所述储电设备在第一时刻的储存电量与所述低价可充电量之和再减去所述高价用电量。
  14. 如权利要求11所述的供电控制装置，其特征在于，所述处理模块，还用于：
    当所述储电设备的冗余电量小于或等于第一阈值时，选择所述电源对所述设备供电，且所述电源在对所述设备进行供电的同时对所述储电设备进行充电，所述储电设备的充电量为所述冗余电量的绝对值；
    当所述储电设备的冗余电量大于或等于第二阈值时，选择所述储电设备对所述设备供电，且所述储电设备的电压在小于或等于电压阈值时停止对所述设备供电，选择所述电源继续对所述设备进行供电，所述储电设备的放电量为所述冗余电量。
  15. 如权利要求14所述的供电控制装置，其特征在于，所述处理模块，具体用于：
    根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算充电功率；
    根据所述充电功率调整所述电源电压，以使得所述电源电压高于所述储电设备的电压，所述电源对所述储电设备进行充电。
  16. 如权利要求14所述的供电控制装置，其特征在于，所述处理模块，具体用于：
    根据所述储电设备的冗余电量和所述第一时刻所在的电价区间的时长，计算放电功率；
    根据所述放电功率调整所述电源电压，以使得所述电源电压低于所述储电设备的电压，所述储电设备对所述设备进行供电。
  17. 如权利要求15或16所述的供电控制装置，其特征在于，所述处理模块，还用于：
    获取所述储电设备的电流；
    根据获取得到的所述储电设备的电流，确定是否调整所述充电功率或所述放电功率；
    在确定调整所述充电功率或所述放电功率的情况下，调整所述电源的限流系数和/或所述储电设备的限流系数。
  18. 如权利要求10-17任一项所述的供电控制装置，其特征在于，所述处理模块，还用于：
    确定初始功率预测模型，所述初始功率预测模型包括深度学习模型；
    获取所述设备的历史功率负载数据，所述历史功率负载数据包括所述设备在所述第一时 刻之前所记录的功率负载；
    利用所述历史功率负载数据对所述初始功率预测模型进行训练。
  19. 一种计算设备，其特征在于，所述计算设备包括存储器和处理器，所述处理器执行所述存储器存储的计算机指令，使得所述计算设备执行权利要求1-9任一项所述的方法的操作步骤。
  20. 一种设备供电系统，其特征在于，包括电源模块管理装置、储电设备和供电设备控制装置，
    所述供电设备控制装置，用于预测用电设备在电价区间的功率负载，所述电价区间为电价相同且连续的一段时间，并根据所述用电设备在电价区间的功率负载、所述储电设备在第一时刻的储存电量以及所述第一时刻所在的电价区间的电价，选择对所述用电设备的供电策略；
    所述储电设备，用于储存电量以及对所述用电设备进行供电；
    所述电源模块管理装置，用于对所述用电设备进行供电以及对所述储电设备进行充电。
PCT/CN2021/088668 2020-06-30 2021-04-21 设备供电的方法、系统及相关设备 WO2022001304A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21831506.7A EP4167417A4 (en) 2020-06-30 2021-04-21 APPARATUS POWER SUPPLY METHOD, SYSTEM AND ASSOCIATED APPARATUS
US18/147,389 US20230148201A1 (en) 2020-06-30 2022-12-28 Method and system for supplying power to device, and related device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010615072.2 2020-06-30
CN202010615072.2A CN113872180A (zh) 2020-06-30 2020-06-30 设备供电的方法、系统及相关设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/147,389 Continuation US20230148201A1 (en) 2020-06-30 2022-12-28 Method and system for supplying power to device, and related device

Publications (1)

Publication Number Publication Date
WO2022001304A1 true WO2022001304A1 (zh) 2022-01-06

Family

ID=78981320

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/088668 WO2022001304A1 (zh) 2020-06-30 2021-04-21 设备供电的方法、系统及相关设备

Country Status (4)

Country Link
US (1) US20230148201A1 (zh)
EP (1) EP4167417A4 (zh)
CN (1) CN113872180A (zh)
WO (1) WO2022001304A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114204575A (zh) * 2022-02-16 2022-03-18 北京迪蒙数控技术有限责任公司 基于Windows的工业放电控制系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104716693A (zh) * 2013-12-13 2015-06-17 华为技术有限公司 一种分布式储能电池的能量管理方法及控制器、系统
US20150170080A1 (en) * 2013-12-18 2015-06-18 International Business Machines Corporation Energy management costs for a data center
CN107994595A (zh) * 2017-11-15 2018-05-04 中国电力科学研究院有限公司 一种削峰填谷控制方法和系统以及应用该控制方法的系统
CN108898282A (zh) * 2018-06-06 2018-11-27 华北电力大学 数据中心资源优化调度方法及计算机存储介质
CN109752953A (zh) * 2018-10-08 2019-05-14 国网天津市电力公司电力科学研究院 一种集成电制冷机的楼宇供能系统模型预测调控方法
CN111311031A (zh) * 2020-03-27 2020-06-19 天合光能股份有限公司 一种户用光伏储能供电系统的能量管理方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9312698B2 (en) * 2012-12-19 2016-04-12 Robert Bosch Gmbh System and method for energy distribution
JP7051856B2 (ja) * 2016-11-29 2022-04-11 ピーク パワー インコーポレイテッド 動的エネルギーストレージシステム制御のためのシステムおよび方法
US10734811B2 (en) * 2017-11-27 2020-08-04 Ihi Inc. System and method for optimal control of energy storage system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104716693A (zh) * 2013-12-13 2015-06-17 华为技术有限公司 一种分布式储能电池的能量管理方法及控制器、系统
US20150170080A1 (en) * 2013-12-18 2015-06-18 International Business Machines Corporation Energy management costs for a data center
CN107994595A (zh) * 2017-11-15 2018-05-04 中国电力科学研究院有限公司 一种削峰填谷控制方法和系统以及应用该控制方法的系统
CN108898282A (zh) * 2018-06-06 2018-11-27 华北电力大学 数据中心资源优化调度方法及计算机存储介质
CN109752953A (zh) * 2018-10-08 2019-05-14 国网天津市电力公司电力科学研究院 一种集成电制冷机的楼宇供能系统模型预测调控方法
CN111311031A (zh) * 2020-03-27 2020-06-19 天合光能股份有限公司 一种户用光伏储能供电系统的能量管理方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4167417A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114204575A (zh) * 2022-02-16 2022-03-18 北京迪蒙数控技术有限责任公司 基于Windows的工业放电控制系统
CN114204575B (zh) * 2022-02-16 2022-05-20 北京迪蒙数控技术有限责任公司 基于Windows的工业放电控制系统

Also Published As

Publication number Publication date
EP4167417A4 (en) 2024-01-03
CN113872180A (zh) 2021-12-31
EP4167417A1 (en) 2023-04-19
US20230148201A1 (en) 2023-05-11

Similar Documents

Publication Publication Date Title
Morstyn et al. Scalable energy management for low voltage microgrids using multi-agent storage system aggregation
US20180116070A1 (en) Datacenter power management using ac and dc power sources
US9948119B2 (en) Control of parallel battery utilization
Alavi et al. Forecast-based consensus control for DC microgrids using distributed long short-term memory deep learning models
US20220140625A1 (en) Machine Learning -Based Method For Increasing Lifetime Of A Battery Energy Storage System
WO2017149618A1 (ja) 制御装置、発電制御装置、制御方法、システム、及び、プログラム
Yue et al. Reinforcement learning based dynamic power management with a hybrid power supply
TWI674729B (zh) 提供多服務之蓄電池之充放電控制裝置及方法
WO2022001304A1 (zh) 设备供电的方法、系统及相关设备
WO2017149617A1 (ja) 制御装置、需給調整制御装置、蓄電装置、出力制御装置、需給調整システム、制御方法、需給調整方法及びプログラム
CN116404683B (zh) 一种柔直互联系统的能量调控方法、装置、终端和介质
CN111325423A (zh) 一种区域多能源互联运营优化方法和计算设备
US20190033946A1 (en) Battery architecture for variable loads and output topologies in an information handling system
KR20140038622A (ko) 전력저장시스템의 충방전 분배장치 및 그 방법
JP6702408B2 (ja) 電力制御装置、電力制御システム、電力制御方法、及び、プログラム
Hazra et al. Congestion relief using grid scale batteries
CN114142460B (zh) 综合能源系统中储能双层目标优化配置方法及终端
CN115800418A (zh) 电池控制方法、储能系统、装置、计算机设备和存储介质
CN111884243B (zh) 储能调控方法、储能系统及计算机存储介质
Li et al. Real-time energy storage management: Finite-time horizon approach
Fan et al. Distributed equalisation strategy for multi‐battery energy storage systems
CN114498697A (zh) 储能电池系统调整方法、装置、电子设备及系统
Bedi et al. Optimal utilization of storage systems under real-time pricing
CN112467774A (zh) 基于全局能效寻优和soc自适应的储能系统管控方法及装置
CN113516306B (zh) 飞轮储能系统的功率配置方法、装置、介质和电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21831506

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021831506

Country of ref document: EP

Effective date: 20230116

NENP Non-entry into the national phase

Ref country code: DE