Zero-carbon building energy control system based on artificial intelligence

Abstract

The present invention provides an artificial intelligence-based zero-carbon building energy control system, comprising a system controller that electrically controls a power generation module, a chemical energy storage module, a physical energy storage module, an electric vehicle module, and a building energy consumption management module via a data bus; wherein the power generation module includes a photovoltaic power supply unit and a wind power supply unit; the chemical energy storage module includes a battery; the physical energy storage module includes a water storage device used as an energy storage device for air conditioning equipment; and the electric vehicle module controller includes an electric vehicle and a charging station used as the system's discharge and / or charging equipment. Thus, the present invention achieves higher energy conversion efficiency by employing water storage equipment; the configuration of the electric vehicle and charging station makes the configuration of the power generation module and the chemical energy storage module more accurate and improves the flexibility of the system; and the present invention employs artificial intelligence algorithms for repeated training, resulting in high reliability and self-learning capabilities, making it adaptable to different project applications.

Description

Technical Field

[0001] The present invention relates to the field of zero-carbon building technology, and in particular to a zero-carbon building energy control system based on artificial intelligence. Background Art

[0002] A zero-carbon building is a building that uses renewable energy and has an annual production capacity greater than or equal to the building's total annual energy consumption, and uses no primary energy at all. It can operate independently of the power grid and can rely on renewable energy such as solar or wind power.

[0003] In addition, there are still deficiencies in the existing research on zero-carbon building energy systems that need to be addressed:

[0004] First, air conditioning energy consumption cannot be effectively managed. Air conditioning is currently the primary energy consumer in buildings, accounting for approximately 70%. Current research primarily utilizes battery storage for energy storage, which is then used in air conditioning systems. This would require a very large battery system. Without effective allocation of air conditioning energy consumption, the efficiency of zero-carbon building energy systems will be very low, resulting in high system costs and difficulty in widespread implementation.

[0005] Second, electric vehicles are not considered in system deployment. The number of electric vehicles will be enormous in the future, and their electricity consumption will be significant. Existing research suggests that electric vehicles will not only be able to charge but also discharge energy to the grid, without affecting their battery life. Therefore, ensuring that electric vehicles charge during peak power generation periods and appropriately discharge energy to the grid during peak power consumption periods can reduce energy system capacity allocation and improve system economics.

[0006] Third, there's insufficient coordination between the subsystems of a zero-carbon building energy system. A zero-carbon building energy system consists of numerous subsystems, such as power generation modules, chemical energy storage modules, physical energy storage modules, and electric vehicle modules. These subsystems must closely collaborate with each other. Failure to consider these interoperability and instead configuring them for maximum capacity will waste energy-saving potential and lead to higher system costs. However, detailed consideration of the logical relationships between modules and the rational allocation of capacity data can improve system economics and enable the widespread adoption of zero-carbon buildings. Summary of the Invention

[0007] In view of the above situation, the purpose of the present invention is to provide an artificial intelligence-based zero-carbon building energy control system to improve the above technical problems.

[0008] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is to provide a zero-carbon building energy control system based on artificial intelligence, including a system controller, which electrically controls the power generation module, chemical energy storage module, physical energy storage module, electric vehicle module and building energy consumption management module through a data bus; wherein, the power generation module includes a power generation module controller connected to the data bus; the power generation module controller is also connected to a photovoltaic power supply unit and a wind power supply unit; the chemical energy storage module includes a chemical energy storage module controller connected to the data bus; the chemical energy storage module controller is also connected to a battery; the physical energy storage module includes a physical energy storage module controller connected to the data bus; the physical energy storage module controller is also connected to a water storage device; the electric vehicle module includes an electric vehicle module controller connected to the data bus; the electric vehicle module controller is also connected to an electric vehicle and a charging pile; the building energy consumption management module includes an energy consumption management module receiver connected to the data bus, and the energy consumption management module receiver obtains the energy consumption data of the zero-carbon building energy system through the data bus.

[0009] A further improvement of the zero-carbon building energy control system of the present invention is that the system controller calculates the installation capacity of the power generation module, the chemical energy storage module and the physical energy storage module by inputting the building's own active power calculation data and the meteorological data of the building's location.

[0010] A further improvement of the zero-carbon building energy control system of the present invention is that the building's own active power calculation data includes the transformer active power calculation power P0, the lighting active power calculation power P1, the air conditioning active power calculation power P2, the electric power active power calculation power P3, and the charging pile active power calculation power P4; wherein P0 = P1 + P2 + P3 + P4.

[0011] A further improvement of the zero-carbon building energy control system of the present invention is that the meteorological data of the building location includes building properties, meteorological data, and national holiday information; the system controller uses an artificial intelligence algorithm to calculate the annual energy consumption P e0 The curve diagram, and according to the annual energy consumption P e0 The curve graph uses artificial intelligence algorithm to calculate the lighting energy consumption P e1 , air conditioning energy consumption P e2 , power consumption P e3 , Charging pile energy consumption P e4 The curve graph of e0 =P e1 +P e2 +P e3 +P e4 .

[0012] A further improvement of the zero-carbon building energy control system of the present invention is that the system controller calculates the annual photovoltaic power generation P of the unit photovoltaic power supply unit based on the meteorological data of the building location. V0 The curve diagram and the annual wind power generation P of the unit wind power supply unit W0 's curve graph.

[0013] A further improvement of the zero-carbon building energy control system of the present invention is that the installation capacity P of the chemical energy storage module b Calculate according to the following formula: b =1.25(P e1 +P e3 -k g1 P g -k4P4); where P e1 is the lighting energy consumption, P e3 is the power consumption, k g1 P g is the power distribution coefficient (k g1 ) multiplied by the installed capacity of the power generation module (P g ), the product is the direct power used by the lighting load of the power generation module, k4P4 is the proportion coefficient (k4) multiplied by the active power calculation power of the charging pile (P4), and the product is the discharge power of the electric vehicle at peak time.

[0014] A further improvement of the zero-carbon building energy control system of the present invention is that the installation capacity P of the physical energy storage module s Calculate according to the following formula: s =(P e2 -k g2 P g ) / k s Among them, P e2 Calculate air conditioning energy consumption for artificial intelligence, k g2 P g is the power distribution coefficient (k g2 ) multiplied by the installed capacity of the power generation module (P g ), the product is the power directly used by the air conditioning load of the power generation module, k s is the water storage capacity (P s ) usage coefficient.

[0015] A further improvement of the zero-carbon building energy control system of the present invention is that the system controller is as follows: g =αP V +βP W Calculate the installed capacity P of the power generation module g ; Among them, α is the number of installed units of photovoltaic power supply units, P Vis the power generation of the photovoltaic power supply unit, β is the number of installed wind power supply units, P W The power generation of a unit wind power supply unit.

[0016] A further improvement of the zero-carbon building energy control system of the present invention is that the system controller calculates according to the following formula:

[0017] Annual energy consumption W0,

[0018] Lighting energy consumption W1,

[0019] Air conditioning energy consumption W2,

[0020] Power consumption W3,

[0021] Charging pile energy consumption W4,

[0022] A further improvement of the zero-carbon building energy control system of the present invention is that the system controller calculates according to the following formula:

[0023] The annual power generation capacity W of the power generation module G , W G =W V +W W ,

[0024] The annual power generation capacity W of the photovoltaic power supply unit V ,

[0025] The annual power generation W of the wind power supply unit W ,

[0026] The system controller uses the following formula: V +W W ≥k e W0 is calculated to ensure that the system's power generation is greater than or equal to the power consumption; V +W W is the power generation of the system, k e W0 is the power consumption of the system.

[0027] The present invention adopts the above technical solution, so it has the following beneficial effects:

[0028] (1) The present invention uses water energy storage equipment, which only requires one conversion, that is, electric energy to thermal energy; therefore, the energy conversion efficiency of the water energy storage equipment is higher.

[0029] (2) The zero-carbon building energy control system of the present invention utilizes the difference between the energy consumption characteristics of electric vehicles and other energy-consuming equipment by setting up the electric vehicle module. Then, on the basis of considering the characteristics of electric vehicles alone, the configuration of the photovoltaic power supply unit, wind power supply unit and battery of the chemical energy storage module of the power generation module is made more accurate and the flexibility of the system is improved.

[0030] (3) The calculation method of the zero-carbon building energy control system of the present invention adopts an artificial intelligence algorithm. The annual energy consumption data obtained through repeated training has high reliability, and through application in different projects, it has a self-learning function, thereby making the application accuracy of the zero-carbon building energy system increasingly higher.

[0031] These and other objects, features and advantages of the present invention will be more fully reflected in the following detailed description and claims, and may be achieved by means of the means, devices and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the architecture of the zero-carbon building energy system of the present invention.

[0033] Figure 2 This is a schematic diagram of the system controller workflow of the zero-carbon building of the present invention.

[0034] Figure 3 It is a schematic diagram of the zero-carbon building energy control configuration architecture of the present invention.

[0035] Figure 4 It is a schematic diagram of the calculation process of the zero-carbon building energy system of the present invention.

[0036] Figure 5 It is a schematic diagram of the process of acquiring active power calculation data of a building according to the present invention.

[0037] Figure 6 It is a schematic diagram of the flow of acquiring meteorological data of buildings according to the present invention.

[0038] Figure 7 It is a schematic diagram of the process of obtaining the installed capacity of the power generation module of the present invention.

[0039] Figure 8 It is a schematic diagram of the process of obtaining the battery installation capacity of the present invention.

[0040] Figure 9 It is a schematic diagram of the process of obtaining the water storage energy installation capacity of the present invention.

[0041] The corresponding relationship between the reference numerals and components is as follows:

[0042] System controller 10; data bus 11; power generation module 200; power generation module controller 20; photovoltaic power supply unit 21; wind power supply unit 22; chemical energy storage module 300; chemical energy storage module controller 30; battery 31; physical energy storage module 400; physical energy storage module controller 40; water energy storage equipment 41; electric vehicle module 500; electric vehicle module controller 50; electric vehicle 51; charging pile 52; building energy consumption management module 600; energy consumption management module receiver 60; data design input stage A; energy configuration output stage B; building's own active power calculation data data1; building location meteorological data data2. DETAILED DESCRIPTION

[0043] Detailed embodiments of the present invention will be disclosed herein. However, it should be understood that the disclosed embodiments are merely exemplary of the present invention and that the present invention may be implemented in a variety of alternative forms. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but rather serve as a representative illustration of various embodiments to those skilled in the art, based on the principles of the claims.

[0044] In order to facilitate the understanding of the present invention, the following Figures 1 to 9 And examples are described.

[0045] like Figure 1 As shown, the zero-carbon building energy control system of the present invention includes a system controller 10, which electrically controls the power generation module 200, the chemical energy storage module 300, the physical energy storage module 400, the electric vehicle module 500 and the building energy consumption management module 600 through a data bus 11.

[0046] in:

[0047] The power generation module 200 includes a power generation module controller 20 connected to the data bus 11 ; the power generation module controller 20 is further connected to a photovoltaic power supply unit 21 and a wind power supply unit 22 .

[0048] The chemical energy storage module 300 includes a chemical energy storage module controller 30 connected to the data bus 11 ; the chemical energy storage module controller 30 is further connected to a battery 31 .

[0049] The physical energy storage module 400 includes a physical energy storage module controller 40 connected to the data bus 11 ; the physical energy storage module controller 40 is further connected to a water energy storage device 41 .

[0050] The electric vehicle module 500 includes an electric vehicle module controller 50 connected to the data bus 11 ; the electric vehicle module controller 50 is further connected to an electric vehicle 51 and a charging station 52 .

[0051] The building energy consumption management module 600 includes an energy consumption management module receiver 60 connected to the data bus 11 , and the energy consumption management module receiver 60 obtains energy consumption data of the zero-carbon building energy system through the data bus 11 .

[0052] like Figure 2 , which shows the workflow of the system controller 10 of the zero-carbon building energy control system of the present invention. The process begins with parameter setting, followed by sequential steps such as inputting basic parameters, acquiring historical data, acquiring predicted data, and randomly generating initial PSO particle data for the battery. After generating the initial PSO particle data for the battery, it is determined whether the particles meet the battery constraints. If the constraints are met, iteration begins. If the constraints are not met, the initial values (parameter settings and / or input of basic parameters) are adjusted to meet the constraints. After the adjustments are completed, iteration begins.

[0053] Next, the battery fitness value is calculated and the initial PSO particle data for water storage energy is randomly generated. After the initial PSO particle data for water storage energy is generated, it is determined whether the particles meet the water storage energy constraints. When the constraints are met, the iteration begins; when the constraints are not met, the initial values (parameter settings and / or basic parameters) are adjusted to meet the constraints. After the adjustment is completed, the iteration begins.

[0054] Next, the water storage energy adaptability value is calculated and the initial PSO particle data of the electric vehicle is randomly generated. After the initial PSO particle data of the electric vehicle is generated, it is determined whether the particles meet the electric vehicle constraints. If the constraints are met, the iteration begins. If the constraints are not met, the initial values (parameter settings and / or basic parameters) are adjusted to meet the constraints. After the adjustment is completed, the iteration begins.

[0055] Next, the electric vehicle fitness value is calculated, the next iteration begins, and whether the number of iterations has been reached is determined. If the number of iterations has not been reached, the system controller 10 returns to the step of randomly generating the initial PSO particle data for the battery. If the number of iterations has been reached, the system controller 10 ends its operation.

[0056] PSO, or particle swarm optimization, is a population-based stochastic optimization technique. It mimics the swarming behavior of insects, herds of animals, flocks of birds, and schools of fish. These groups collaborate to find food, with each member continuously adapting its search pattern by learning from its own experience and that of other members.

[0057] like Figure 3As shown, the calculation method of the zero-carbon building energy control system of the present invention uses data input in the data design input stage A to further produce and output corresponding or required data in the energy configuration output stage B. Specifically, the data design input stage A includes inputting the building's own active power calculation data (data1) and the building's location meteorological data (data2). After obtaining these two pieces of data, the energy configuration output stage B begins to calculate the system energy configuration.

[0058] like Figure 3 The system configuration mainly includes a power generation module 200, a chemical energy storage module 300 and a physical energy storage module 400. Among them, the power generation module 200 includes the photovoltaic power supply unit 21 and the wind power supply unit 22. The configuration ratio of the two is detailed in the calculation method described below. The chemical energy storage module 300 adopts the battery 31 in the embodiment of the present invention, but is not limited to this. It can also adopt a lithium battery with mature technology and reasonable cost performance or other storage devices that meet the above conditions. The physical energy storage module 400 adopts the water storage device 41 in the embodiment of the present invention, but is not limited to this. For places with suitable climatic conditions, if there is a real advantage after economic and technical comparison, other energy storage devices that can play the same role, such as ice storage equipment, can be used.

[0059] like Figures 4 to 9 As shown, a flowchart showing the steps of the calculation method of the zero-carbon building energy control system based on artificial intelligence of the present invention.

[0060] like Figure 4 The calculation method of the zero-carbon building energy control system based on artificial intelligence of the present invention includes steps S10 to S50, wherein steps S10 and S20 correspond to Figure 3 In the data design input phase A, steps S30, S40, and S50 correspond to Figure 3 Energy configuration output in stage B.

[0061] Specifically, if Figure 4 As shown, the steps S10 to S50 include:

[0062] Step S10: Obtain the building's own active power calculation data data1;

[0063] Step S20: Acquire meteorological data data2 of the building location;

[0064] Step S30: Calculate the installed capacity P of the power generation module 200 (including the photovoltaic power supply unit 21 and the wind power supply unit 22). g .

[0065] Step S40: Calculate the installed capacity P of the chemical energy storage module 300 (ie, the battery 31) b .

[0066] Step S50: Calculate the installed capacity P of the physical energy storage module 400 (ie, the water storage device 41). s .

[0067] In the embodiment of the present invention, the electricity consumption of the zero-carbon building is divided into lighting electricity (referred to as lighting), air conditioning electricity (referred to as air conditioning), other electricity (referred to as electricity), and electricity used by charging piles 52 for charging electric vehicles 51 (referred to as charging piles).

[0068] Specifically, if Figure 5 As shown, the step S10 further includes sub-steps S11 to S12. The sub-steps include:

[0069] Step S11: extracting the transformer active calculated power P0 according to the transformer load rate calculation table.

[0070] Step S12: Obtain the active calculated power of lighting, air conditioning, electricity, and charging piles, and allocate the transformer active calculated power P0 according to the load rate calculation table; as shown in the following formula (1): P0 = P1 + P2 + P3 + P4. Where P0 is the transformer active calculated power, P1 is the lighting active calculated power, P2 is the air conditioning active calculated power, P3 is the electricity active calculated power, and P4 is the charging pile active calculated power.

[0071] The transformer load rate calculation table in step S11 is a building-related design document generated upon completion of the building design, in accordance with Article 3.6.5 of the "Regulations on the Depth of Preparation of Building Engineering Design Documents (2016 Edition)." The calculated active power for the building's lighting, air conditioning, electricity, and charging stations in step S12 can be directly obtained from the transformer load rate calculation table corresponding to the building.

[0072] Specifically, if Figure 6 As shown, the step S20 further includes sub-steps S21 to S24. The sub-steps include:

[0073] Step S21: Calculate the annual energy consumption P using artificial intelligence algorithms based on building properties, meteorological data, and national holiday information. e0 's curve graph.

[0074] Furthermore, the present invention calculates the annual energy consumption P by artificial intelligence algorithm. e0The steps include: First, providing annual energy consumption data for various types of buildings. Second, dividing all data into three seasons based on climate: spring, autumn, summer, and winter. Third, combining the energy consumption data for each season with the corresponding meteorological data to classify them, providing weekday / rest day combinations and sunny / cloudy / rainy day combinations. Fourth, training the corresponding data through an artificial intelligence algorithm to achieve data fitting, and extracting different combinations for each quarter to obtain the annual energy consumption P for a typical 24-hour period. e0 's curve graph.

[0075] Step S22: Based on the annual energy consumption P e0 The curve chart of lighting energy consumption, air conditioning energy consumption, electricity energy consumption and charging pile energy consumption is obtained by using artificial intelligence algorithm. e0 The sum of is as follows (2): P e0 =P e1 +P e2 +P e3 +P e4 Among them, P e0 is the annual energy consumption, P e1 is the lighting energy consumption, P e2 is the air conditioning energy consumption, P e3 is the power consumption, P e4 is the energy consumption of the charging pile.

[0076] Step S23: Calculate the annual photovoltaic power generation P of the unit photovoltaic power supply unit 21 based on the meteorological data data2 of the building location. V0 's curve graph.

[0077] Step S24: Calculate the annual wind power generation capacity P of the unit wind power supply unit 22 based on the meteorological data data2 of the building location. W0 's curve graph.

[0078] In this embodiment of the present invention, both steps S22 and S21 utilize artificial intelligence algorithms to train existing data to generate graphs of lighting energy consumption, air conditioning energy consumption, electricity energy consumption, and charging station energy consumption. Furthermore, steps S21 and S22 are based on existing operational data from various regions and types of buildings. This approach utilizes existing big data to obtain new configuration data, and uses the operational data from the new project as foundational data for the next project, thereby achieving further accurate zero-carbon building energy system configuration data through a self-learning process.

[0079] Specifically, if Figure 7 As shown, the step S30 further includes sub-steps S31 to S34. The sub-steps include:

[0080] Step S31: According to the following formula (3): P g =αPV +βP W Calculate the installed capacity P of the power generation module 200 g ; Wherein, α is the number of installed units of photovoltaic power supply unit 21, P V is the power generation of the photovoltaic power supply unit 21, β is the number of installed wind power supply units 22, P W is the power generation of the unit wind power supply unit 22.

[0081] Step S32: Calculate the annual energy consumption data W0, as well as the annual lighting energy consumption W1, the annual air conditioning energy consumption W2, the annual electricity energy consumption W3, and the annual charging pile energy consumption W4 according to the following formulas (4) to (8).

[0082] Formula (4): Annual energy consumption W0,

[0083] Formula (5): Lighting energy consumption W1,

[0084] Formula (6): Air conditioning energy consumption W2,

[0085] Formula (7): Power consumption W3,

[0086] Formula (8): Charging pile energy consumption W4,

[0087] Step S33: Calculate the annual power generation W of the power generation module 200 according to the following equations (9) to (11): G , and the annual power generation W of the photovoltaic power supply unit 21 V , the annual power generation W of the wind power supply unit 22 W .in:

[0088] Formula (9): The annual power generation W of the power generation module 200 G , W G =W V +W W ,

[0089] Formula (10): The annual power generation W of the photovoltaic power supply unit 21 V ,

[0090] Formula (11): The annual power generation W of the wind power supply unit 22 W ,

[0091] Step S34: Ensure that the system's power generation is greater than or equal to the power consumption, and consider the installed capacity margin k e times, according to the following formula (12): W V +WW ≥k e W0 calculation. Where W V +W W is the power generation of the system, k e W0 is the power consumption of the system.

[0092] Among them, the installed capacity margin k e Times, based on the building electrical design principles, the installed capacity should not only ensure the power capacity, but also have a certain margin.

[0093] Step S35: The constraints for the photovoltaic power supply unit 21 and the wind power supply unit 22 are to ensure optimal economic benefits. Specifically, assuming that the cost per photovoltaic power supply unit 21 over its service life is λ and the cost per wind power supply unit 22 over its service life is μ, the minimum cost per unit of the power generation module 200 over its service life is calculated according to the following equation (13): αλ + βμ. Here, α is the number of installed photovoltaic power supply units 21, and β is the number of installed wind power supply units 22.

[0094] Specifically, if Figure 8 As shown, the step S40 further includes sub-steps S41 to S45. The sub-steps include:

[0095] Step S41: The installation capacity P of the chemical energy storage module 300 is b On the basis of satisfying the use of electrical equipment other than air conditioning and excluding the use of charging pile 52 during peak hours, the following formula (14) is used: P b =P e1 +P e3 Calculate the installed capacity P of the chemical energy storage module 300 b Among them, P e1 is the lighting energy consumption, P e3 For electricity consumption.

[0096] Step S42: During the peak period, the electric vehicle 51 is considered to discharge to supplement the power usage of electrical equipment other than the air conditioner, wherein the ratio of the discharge equipment capacity to the installed capacity of the charging pile (discharge coefficient) is k4.

[0097] Step S43: The use of electrical equipment other than air conditioners, the installation capacity P of the chemical energy storage module 300 b Deduct the real-time power distribution of the power generation module 200, and consider the distribution coefficient k g1 . Partition coefficient k g1 According to the following formula (15): k g1 =(W1+W3) / W0, where W1 is lighting energy consumption and W3 is electricity energy consumption.

[0098] Step S44: The constraint condition of the battery 31 is the optimal usage range, that is, 60% to 80% of the installed capacity.

[0099] Step S45: Considering steps S41 to S44, the installed capacity P of the chemical energy storage module 300 is b Satisfies the following formula (16): P b =1.25(P e1 +P e3 -k g1 P g -k4P4); where P e1 is the lighting energy consumption, P e3 is the power consumption, k g1 P g is the power distribution coefficient (k g1 ) multiplied by the installed capacity of the power generation module 200 (P g ), the product is the direct use power of the lighting load of the power generation module 200, k4P4 is the proportion coefficient (k4) multiplied by the active power calculation power of the charging pile (P4), and the product is the discharge power of the electric vehicle 51 at the peak time.

[0100] Among them, in the formula (16), the battery constraint condition is the optimal usage range, that is, 60% to 80% of the capacity, then the calculated capacity should be 80% of the installed capacity, that is, the installed capacity is 1.25 times the calculated capacity. b For the calculation of , refer to steps S41 to S44.

[0101] Specifically, if Figure 9 As shown, the step S50 further includes sub-steps S51 to S54. The sub-steps include:

[0102] Step S51: Make the installed capacity P of the physical energy storage module 400 s Meet the air conditioning energy consumption P e2 .

[0103] Step S52: Excluding the use of air-conditioning electrical equipment, the installed capacity P of the physical energy storage module 400 s Deduct the real-time power distribution of the power generation module 200, and consider the distribution coefficient k g2 . Partition coefficient k g1 According to the following formula (17): k g2 =W2 / W0, where W2 is the air conditioning energy consumption and W0 is the annual energy consumption.

[0104] Step S53: The installation capacity P of the physical energy storage module 400 is s The service factor is set as k s .

[0105] Since all equipment has a utilization efficiency, energy losses include heat conduction, auxiliary equipment energy consumption, etc. The equipment utilization factor is the coefficient of the installed power minus these losses.

[0106] Step S54: Considering steps S51 to S53, the installation capacity P of the physical energy storage module 400 is set to s Satisfies the following formula (18): P s =(P e2 -k g2 P g ) / k s Among them, P e2 Calculate air conditioning energy consumption for artificial intelligence, k g2 P g is the power distribution coefficient (k g2 ) multiplied by the installed capacity of the power generation module 200 (P g ), the product is the power directly used by the air conditioning load of the power generation module, k s is the water storage capacity (P s ) usage coefficient.

[0107] In an embodiment of the present invention, the water storage device 41 of the physical energy storage module 400 is used as an energy storage device for the air conditioning system. Specifically, the water storage device 41 is used to store the cooling energy of the air conditioning system during off-peak hours (when electricity rates are low), and to release the stored energy during peak hours (when electricity rates are high) for air conditioning. This improves the problem of high energy consumption in the air conditioning system. The method of using batteries to store energy and then convert it into the cooling and heating energy required for air conditioning results in a large battery installation and poor economic efficiency. It also avoids the risk of excessive battery installation, which increases the risk of battery equipment failure and fire safety issues. Furthermore, using batteries to provide energy for the air conditioning system requires three energy conversions: electrical energy to chemical energy to electrical energy to thermal energy. However, using the water storage device 41 as the energy storage device for the air conditioning system requires only one conversion: electrical energy to thermal energy. Therefore, the energy conversion efficiency of the water storage device is higher.

[0108] In an embodiment of the present invention, the electric vehicle module 500 is used to increase the accuracy and flexibility of the present invention's artificial intelligence-based zero-carbon building energy control system. Given the expected large number of electric vehicles in the future, their electricity consumption will be significant. Furthermore, according to existing research, electric vehicles will not only be able to charge but also discharge electricity to the grid, without affecting their battery life. Therefore, the present invention's zero-carbon building energy control system utilizes the electric vehicle module 500 to take advantage of the different energy consumption characteristics of electric vehicles 51 compared to other energy-consuming devices. This allows for more accurate configuration of devices such as the photovoltaic power supply unit 21, wind power supply unit 22, and battery 31 of the chemical energy storage module 300 in the power generation module 200, based on the individual considerations of the electric vehicle's characteristics. Furthermore, when building energy consumption is high, the electric vehicle module controller 50 can control the electric vehicle 51 and / or charging station 52 to discharge electricity, thereby replenishing their electrical energy into the present invention's zero-carbon building energy control system, thereby enhancing the system's flexibility.

[0109] Since the zero-carbon building energy system is composed of numerous modules, including power generation modules, chemical energy storage modules, physical energy storage modules, and electric vehicle modules, each module has completely different operating logic. Without finding the mathematical model and constraints of each module, as well as the constraint relationships between modules, it is impossible to form a mature and practically applicable system design. Therefore, in an embodiment of the present invention, the zero-carbon building energy control system of the present invention is based on the aforementioned system architecture and proposes a mathematical model for allocating energy data based on the logical relationships between modules. The mathematical model has high accuracy and reliability, and is a practical zero-carbon building energy control system calculation method that can be applied in specific projects.

[0110] Since different buildings have different annual energy consumption curves due to their architectural properties and the meteorological data of their locations, and the annual energy consumption data also changes due to changes in national holidays. Therefore, in the embodiment of the present invention, it is proposed to use an artificial intelligence algorithm, and the annual energy consumption data (annual energy consumption curve) obtained through repeated training has high reliability. Through the application of this algorithm in different projects, it has a self-learning function, thereby making the application accuracy in zero-carbon building energy systems increasingly higher. Specifically, the principle of the artificial intelligence algorithm adopted by the present invention is that under the guidance of a certain algorithm, the system automatically searches for the optimal result; the purpose of this algorithm is also to guide the system to automatically search for the optimal result that adapts to the retrieval of energy consumption data.

[0111] The present invention has been described in detail above with reference to the accompanying drawings and embodiments. A person skilled in the art can make various modifications to the present invention based on the above description. Therefore, certain details in the embodiments should not be construed as limiting the present invention. The scope of protection of the present invention shall be determined by the scope defined in the appended claims.

Claims

1. A zero-carbon building energy control system based on artificial intelligence, characterized by It includes a system controller, which electrically controls the power generation module, the chemical energy storage module, the physical energy storage module, the electric vehicle module and the building energy consumption management module through a data bus; wherein: The power generation module includes a power generation module controller connected to the data bus; the power generation module controller is further connected to a photovoltaic power supply unit and a wind power supply unit; The chemical energy storage module includes a chemical energy storage module controller connected to the data bus; the chemical energy storage module controller is further connected to a battery; The physical energy storage module includes a physical energy storage module controller connected to the data bus; the physical energy storage module controller is further connected to the water energy storage equipment; The electric vehicle module includes an electric vehicle module controller connected to the data bus; the electric vehicle module controller is further connected to the electric vehicle and the charging pile; The building energy consumption management module includes an energy consumption management module receiver connected to the data bus, and the energy consumption management module receiver obtains energy consumption data of the zero-carbon building energy control system through the data bus; The system controller calculates the installation capacity of the power generation module, the chemical energy storage module and the physical energy storage module by inputting the active power calculation data of the building itself and the meteorological data of the building location; The installed capacity P of the chemical energy storage module b Calculate according to the following formula: b =1.25(P e1 +P e3 -k g1 P g -k4P4); where P e1 is the lighting energy consumption, P e3 is the power consumption, k g1 P g is the first power distribution coefficient k g1 Multiply by the installed capacity P of the power generation module g , the product is the direct power used by the lighting load of the power generation module, k4P4 is the proportion coefficient k4 multiplied by the active power calculation power P4 of the charging pile, and the product is the discharge power of the electric vehicle at peak time; During peak periods, electric vehicle discharge is considered to supplement the power consumption of electrical equipment other than air conditioners. The ratio of the discharge equipment capacity to the installed capacity of the charging pile is k4. In addition to the use of electrical equipment other than air conditioning, the installation capacity of the chemical energy storage module P b Deduct the real-time power distribution of the power generation module and consider the first power distribution coefficient as k g1 , the first power distribution coefficient k g1 According to the following formula: g1 = (W1 + W3) / W0, where W1 is the annual lighting energy consumption and W3 is the annual electricity energy consumption; Excluding the use of air-conditioning electrical equipment, the installation capacity of the physical energy storage module P s Deduct the real-time power distribution of the power generation module and consider the second power distribution coefficient as k g2 , the second power distribution coefficient k g2 According to the following formula: g2 =W2 / W0, where W2 is the annual energy consumption of the air conditioner and W0 is the annual energy consumption; The installed capacity P of the physical energy storage module s Calculate according to the following formula: s =(P e2 -k g2 P g ) / k s Among them, P e2 Calculate air conditioning energy consumption for artificial intelligence, k g2 P g is the second power distribution coefficient k g2 Multiply by the installed capacity P of the power generation module g , the product is the power directly used by the air conditioning load of the power generation module, k s is the utilization coefficient of water storage capacity.

2. The artificial intelligence-based zero-carbon building energy control system according to claim 1 is characterized by: The building's own active power calculation data includes transformer active power calculation P0, lighting active power calculation P1, air conditioning active power calculation P2, electric power active power calculation P3, and charging pile active power calculation P4; Among them, P0=P1+P2+P3+P4.

3. The artificial intelligence-based zero-carbon building energy control system according to claim 1 is characterized by: The meteorological data of the building location includes the nature of the building, meteorological data, and national holiday information; The system controller uses artificial intelligence algorithm to calculate the total energy consumption P e0 The curve diagram, and according to the total energy consumption P e0 The curve graph uses artificial intelligence algorithm to calculate the lighting energy consumption P e1 , air conditioning energy consumption P e2 , power consumption P e3 , Charging pile energy consumption P e4 Graph of Among them, P e0 =P e1 +P e2 +P e3 +P e4 .

4. The artificial intelligence-based zero-carbon building energy control system according to claim 3 is characterized by: The system controller calculates the photovoltaic power generation P of the unit photovoltaic power supply unit according to the meteorological data of the building location. V0 The curve diagram and the wind power generation P per unit wind power supply unit W0 's curve graph.

5. The artificial intelligence-based zero-carbon building energy control system according to claim 1 is characterized by: The system controller is as follows: g =αP V0 +βP W0 Calculate the installed capacity P of the power generation module g ; Among them, α is the number of installed units of photovoltaic power supply units, P V0 is the power generation of the photovoltaic power supply unit, β is the number of installed wind power supply units, P W0 The power generation of a unit wind power supply unit.

6. The artificial intelligence-based zero-carbon building energy control system according to claim 5 is characterized in that: The system controller is calculated according to the following formula: Annual energy consumption W0, Lighting annual energy consumption W1, The annual energy consumption of air conditioner is W2, Annual electricity consumption is W3, The annual energy consumption of charging pile is W4, Among them, P e0 is the total energy consumption, P e4 is the energy consumption of the charging pile.

7. The artificial intelligence-based zero-carbon building energy control system according to claim 6 is characterized in that: The system controller is calculated according to the following formula: The annual power generation capacity W of the power generation module G , W G =W V +W W , The annual power generation of the photovoltaic power supply unit is W V , The annual power generation of the wind power supply unit is W W , The system controller uses the following formula: V +W W ≥k e W0 is calculated to ensure that the system's power generation is greater than or equal to the power consumption; V +W W is the power generation of the system, k e W0 is the power consumption of the system.

Images