Virtual power plant load aggregation method based on subway photovoltaic power supply and air conditioning adjustment coupling

Abstract

A virtual power plant load aggregation method based on subway photovoltaic power supply and air conditioner adjustment coupling comprises the steps that photovoltaic output characteristics of subway distributed photovoltaic under different sunshine conditions are collected, and power supply load data of a subway air conditioner at different environment temperatures, working days, non-working days and special holidays and festivals are collected; modeling simulation and big data technologies are combined with historical meteorological data to build a rail transit photovoltaic and air conditioner digital twin model, a machine learning technology is utilized to improve the precision and accuracy of the rail transit photovoltaic and air conditioner digital twin model, and a dispatching load curve issued by an urban power grid virtual power plant platform is combined. A polymerization method for coupling metro photovoltaic power supply and air conditioner regulation is constructed, control strategy design is optimized, intelligent operation of metro photovoltaic and air conditioner whole-process self-optimization and self-diagnosis is achieved, and efficient management of all links of an energy chain is achieved.

Description

Technical Field

[0001] This invention relates to the field of virtual power plant technology, and in particular to a virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation. Background Technology

[0002] In recent years, as my country's virtual power plants have entered a period of comprehensive construction, subways have carried out exploratory work including photovoltaic access, shared main transformers, and networked power supply. These attempts have made demand-side response and the construction of virtual power plants possible, and can also become a technological breakthrough point.

[0003] The prerequisite for subways to participate in the regulation of virtual power plants is accurate load forecasting. Currently, most load forecasting methods use time series methods and are mostly short-term forecasts, which do not meet the accuracy requirements.

[0004] The information disclosed in the background section is only for enhancing the understanding of the background of this invention, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical issues, this invention considers the randomness and volatility of photovoltaic power generation. When photovoltaic power is used in the regulation of the subway virtual power plant, it is significantly affected by weather. Unexpected factors can lead to substandard regulation and deviations from the predicted curve, necessitating timely adjustments to meet the standards of the sampling points. Furthermore, underground station air conditioning accounts for a large proportion of the overall subway system's power and lighting load, and its operation is relatively stable and regular. Therefore, this invention considers coupling the subway's photovoltaic and dynamic lighting systems for adjustment. When the subway's photovoltaic power supply fails to meet the load aggregation margin of the virtual power plant, emergency compensation is provided using the subway's air conditioning system, achieving joint scheduling of subway photovoltaic power supply and air conditioning.

[0006] Therefore, this invention discloses a virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation, comprising:

[0007] S100: Collect data on the photovoltaic output characteristics of distributed photovoltaic systems in the subway under different sunshine conditions, and collect data on the power supply load of subway air conditioning under different ambient temperatures, on weekdays and non-working days, and on special holidays, and establish a database.

[0008] S200, based on a database of measured loads of subway photovoltaic and air conditioning, utilizes modeling simulation and big data technologies, combined with historical meteorological data to build a digital twin model of rail transit photovoltaic and air conditioning;

[0009] S300 utilizes machine learning technology to improve the accuracy and precision of digital twin models of photovoltaic and air conditioning systems in rail transit.

[0010] S400, based on the digital twin model and combined with the dispatch load curve issued by the urban power grid virtual power plant platform, constructs an aggregation method that couples subway photovoltaic power supply with air conditioning regulation.

[0011] The aforementioned virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes,

[0012] S500, optimize control strategy design, study adaptive control technology with real-time optimization and autonomous judgment function of overall operation efficiency, design integrated energy management platform for metro photovoltaic power supply and air conditioning interaction, realize intelligent operation of metro photovoltaic and air conditioning with self-optimization and self-diagnosis throughout the process, and realize efficient management of all links of the energy chain.

[0013] Compared with the prior art, the present invention has the following advantages:

[0014] This invention studies the coupling capability between photovoltaic power supply and air conditioning regulation in subways. It analyzes the load characteristics of photovoltaic power supply and the power consumption characteristics of subway air conditioning. Through simulation analysis, a digital twin model of rail transit photovoltaics and air conditioning is established. The problem of emergency compensation for subway air conditioning participating in the subway virtual power plant when photovoltaic output is insufficient is analyzed in detail. Based on the research results, a virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation is proposed, which enables the subway to participate in the regulation of the virtual power plant based on accurate load aggregation and prediction. Attached Figure Description

[0015] Various other advantages and benefits of the present invention will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The drawings are for illustrative purposes only and are not intended to limit the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can derive other drawings from these drawings without creative effort. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0016] Figure 1 This is a schematic flowchart of a virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation in one embodiment of the present invention. Detailed Implementation

[0017] Specific embodiments of the present invention will now be described in detail with reference to the figures. While specific embodiments of the invention are shown in the figures, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0018] It should be noted that certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that different terms may be used to refer to the same component. This specification and claims do not distinguish components based on differences in terminology, but rather on differences in function. The terms "comprising" or "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising but not limited to." The following descriptions are preferred embodiments for carrying out the invention; however, these descriptions are for the purpose of understanding the general principles of the specification and are not intended to limit the scope of the invention. The scope of protection of this invention is determined by the appended claims.

[0019] To facilitate understanding of the embodiments of the present invention, the following will provide further explanation and description with reference to the figures and specific embodiments, and the figures do not constitute a limitation on the embodiments of the present invention.

[0020] In one embodiment, the present invention discloses a virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation, comprising:

[0021] S100: Collect data on the photovoltaic output characteristics of distributed photovoltaic systems in the subway under different sunshine conditions, and collect data on the power supply load of subway air conditioning under different ambient temperatures, on weekdays and non-working days, and on special holidays, and establish a database.

[0022] S200, based on a database of measured loads of subway photovoltaic and air conditioning, utilizes modeling simulation and big data technologies, combined with historical meteorological data to build a digital twin model of rail transit photovoltaic and air conditioning;

[0023] S300 utilizes machine learning technology to improve the accuracy and precision of digital twin models of photovoltaic and air conditioning systems in rail transit.

[0024] S400, based on the digital twin model and combined with the dispatch load curve issued by the urban power grid virtual power plant platform, constructs an aggregation method that couples subway photovoltaic power supply with air conditioning regulation.

[0025] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes,

[0026] S500, optimize control strategy design, study adaptive control technology with real-time optimization and autonomous judgment function of overall operation efficiency, design integrated energy management platform for metro photovoltaic power supply and air conditioning interaction, realize intelligent operation of metro photovoltaic and air conditioning with self-optimization and self-diagnosis throughout the process, and realize efficient management of all links of the energy chain.

[0027] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes considering the changes in the characteristics of subway photovoltaic power supply connected to the power grid, studying the load characteristics of rail transit photovoltaic power supply, and exploring the demand of the virtual power plant for subway photovoltaic power supply regulation.

[0028] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes studying multi-source and multi-load operation multi-stage collaborative control technology, studying grid-source-load collaborative rail transit self-consistent optimization power supply technology, and carrying out source-load complementary modeling and simulation algorithms.

[0029] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes a source-load complementary modeling and simulation algorithm. This algorithm couples the subway photovoltaic power supply with the subway air conditioning power load and, combined with the power consumption characteristics of the air conditioning, studies the problem of subway air conditioning participating in the emergency compensation of the subway virtual power plant when the photovoltaic output is insufficient.

[0030] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes collecting data on subway photovoltaic and air conditioning loads and influencing factors using a temperature and humidity collector and a subway load remote recording device to form a database based on actual measurements of subway photovoltaic and air conditioning loads, and using machine learning technology to improve the accuracy and precision of the model.

[0031] In another embodiment, the virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation further includes, when considering emergency compensation for air conditioning, ensuring the comfort of the station environment while ensuring the safe operation of the subway, and therefore, establishing a feedback function for intelligent scheduling.

[0032] In another embodiment, step S100 includes:

[0033] S101: Photovoltaic System Data Acquisition

[0034] Static data:

[0035] Total photovoltaic panel area Apv (unit: m²) 2 Installation tilt angle β (unit: degrees), azimuth angle γ (unit: degrees, due south is 0 degrees).

[0036] Photovoltaic inverter rated power Pinvrated (unit: kW), efficiency curve ηinv(Pdc) (output power as a function of DC input power).

[0037] Dynamic data (collected in real time and stored in a time-series database):

[0038] Irradiance G(t) (unit: W / m²) 2 ): Measured by irradiators deployed in photovoltaic fields.

[0039] Ambient temperature Ta(t) (unit: °C).

[0040] The DC output power of the photovoltaic array is Pdc(t) (unit: kW).

[0041] Inverter AC grid connection point power Ppvac(t) (unit: kW).

[0042] S102: Air Conditioning System Data Acquisition

[0043] The station volume V, the rated power of the air conditioning system Pacrated, the station thermal time constant τ, etc., as well as the real-time electrical power of the air conditioning system Pac(t) (unit: kW), the station indoor temperature Tin(t) (unit: ℃), the air conditioning set temperature Tset(t) (unit: ℃) and its adjustable range [Tsetmin, Tsetmax], the air conditioning control status (such as: normal mode / energy saving mode / emergency control mode), etc.

[0044] Among them, the station volume V (unit: m) 3 ): The internal space volume of the station is calculated from the architectural design drawings and is used to calculate the heat capacity; Rated power of the air conditioning system (unit: kW): The maximum input electrical power of the air conditioning unit under standard operating conditions.

[0045] For example, following the principle of avoiding both duplication and omission, the following data collection methods could also be considered:

[0046] Static data collection (one-time acquisition, valid for a long time):

[0047] Internal surface area A (unit: m) 2 ): The total area of ​​the station's internal enclosure structure, including walls, ceilings, and floors, used to calculate the heat transfer area;

[0048] Overall thermal conductivity of the wall (k) (unit: W / (m) 2 ·K): Reflects the overall thermal conductivity of wall materials, obtained through material thermal engineering handbooks or actual measurements.

[0049] Average burial depth of the station ℎh (unit: m): The average vertical distance from the top of the station to the ground, which affects the soil temperature lag.

[0050] Air conditioner rated energy efficiency ratio (COPrated) (dimensionless): The ratio of cooling capacity to input electrical power under rated operating conditions.

[0051] Dynamic data acquisition (continuous real-time acquisition):

[0052] Outdoor dry-bulb temperature Tout(t) (unit: °C): The temperature of the air outside the station, collected every 5 minutes by a meteorological sensor.

[0053] Real-time passenger flow within the station, Npassenger(t) (unit: people / minute): Statistically recorded in real time through the gate counting and video recognition system.

[0054] Station interior temperature Tin(t) (unit: °C): average value of multiple sensors in the station hall and platform.

[0055] Real-time electrical power of the air conditioning system, Pelec(t) (unit: kW): recorded every 15 minutes by a smart meter.

[0056] S103: Access to External and Forecast Data

[0057] Access meteorological forecast data: irradiance Gfc(t), temperature Ta,fc(t), and cloud cover forecast for the next 24-72 hours.

[0058] Access to virtual power plant dispatch instructions: The dispatch load curve Pvppschedule(t) from the city power grid VPP platform is usually the power value of a point every 15 minutes for the next 24 hours, representing the total power that the VPP aggregate needs to provide to the grid (positive for power generation, negative for power consumption).

[0059] Access to operational data: train timetables, predicted passenger flow .

[0060] S104: Construct a database based on the above S101 to S103.

[0061] It should be noted that the specific implementation of step S100 systematically defines the full-dimensional data required by the coupled system, especially clarifying the key parameters required for photovoltaic power output characteristics and air conditioning load characteristics, laying the data foundation for building a high-fidelity digital twin model. Its technical contribution lies in proposing a standardized data acquisition framework for the special coupled system of "metro photovoltaic-air conditioning".

[0062] In another embodiment, step S200 includes:

[0063] S201: The physical model for photovoltaic power output is constructed using a practical engineering model, representing the DC output power of the photovoltaic panel at time t. for:

[0064]

[0065] in,

[0066] G(t): Irradiance on the inclined plane (unit: W / m²) 2The total solar irradiance is calculated from the horizontal irradiance, tilt angle, and azimuth angle, and represents the total solar irradiance illuminating the inclined surface of the photovoltaic panel at time t.

[0067] ηpv: The conversion efficiency of a photovoltaic panel under standard test conditions (STC).

[0068] κ: Power temperature coefficient (unit: % / ℃).

[0069] Tcell(t): Estimated operating temperature inside the photovoltaic panel at time t (unit: °C), obtained by fitting historical data using the following empirical formula:

[0070]

[0071] TNOCT is the rated operating temperature of the solar panel, which is a technical parameter provided by the photovoltaic module manufacturer.

[0072] This represents the air temperature of the environment surrounding the photovoltaic panel at time t, i.e., the ambient air temperature; it serves as the benchmark term for the panel's operating temperature in the above model, reflecting the influence of environmental climate conditions on the photovoltaic module's temperature, while the formula... The additional heating effect of solar irradiance on solar panels was quantified using an empirical formula.

[0073] The AC output power is:

[0074] .

[0075] S202: Construction of a Model for Adjustable Air Conditioning Load

[0076] Establish an adjustable potential model for air conditioning load, where the adjustable power ΔPacup(t) (potentially reduced electricity consumption) and adjustable power ΔPacdown(t) (potentially increased electricity consumption) of the air conditioner at time t are defined as follows:

[0077]

[0078]

[0079] in,

[0080] These represent the minimum and maximum allowable operating power of the air conditioning system, respectively.

[0081] C: Equivalent heat capacity of the station (unit: kWh / ℃); Δt: Control time interval (e.g., 15 minutes);

[0082] The above model quantifies the real-time adjustment capability of the air conditioning load while ensuring that the indoor temperature is within the comfortable range [Tsetmin, Tsetmax].

[0083] S203: Coupled Model Integration to Construct the Model of Total External Power Ptotal(t) of the Coupled System at Time t:

[0084]

[0085] in,

[0086] Pacbase(t) represents the air conditioning base load (i.e., the predicted value when not involved in regulation).

[0087] u(t) represents the control power of the air conditioner, and must have A positive value indicates a reduction in electricity consumption (equivalent to providing positive power to the grid), while a negative value indicates an increase in electricity consumption.

[0088] The specific implementation of step S200 above constructs a coupled digital twin model that includes the physical characteristics of photovoltaics and the adjustment potential of air conditioning. Its most critical technical contribution is the proposal of a quantitative model of "adjustable air conditioning potential", which transforms the originally rigid air conditioning load into a continuously adjustable resource with clear upper and lower limits. This is the basis for the dynamic coupling optimization of photovoltaics and air conditioning in this invention.

[0089] In another embodiment, step S300 includes:

[0090] S301: Historical data collection for photovoltaic model error correction {G,Ta, Considering that the physical model of photovoltaics ignores many details (such as stains, aging, and shading), this invention specifically introduces a gradient boosting regressor (GBR) to establish an error correction model:

[0091] The feature vectors include: G(t), Ta(t), season, time. ;

[0092] The label is: Error .

[0093] Training GBR Model The final predicted output is: .

[0094] S302: Dynamic Parameter Identification of Air Conditioner Adjustable Potential Model Considering that parameters such as the heat capacity C and actual COP of the air conditioning system will change, this invention adopts the recursive least squares method with a forgetting factor (FFRLS) for online identification.

[0095] Discretize the heat balance equation:

[0096] .

[0097] Let a, b, d be the parameters to be identified, θ.

[0098] By using the real-time measured {Tin, Pac, Tout} sequence, θ is updated online through the FFRLS algorithm, thereby dynamically updating parameters such as C and actual COP in the adjustable potential model.

[0099] The specific implementation of step S300 above lies in using machine learning and adaptive algorithms to solve the two major problems of inherent bias in physical models and time-varying system parameters. Its technical contribution lies in designing a two-layer model optimization framework of "physical model + data-driven correction" and "online parameter identification", which ensures the prediction accuracy and reliability of the coupled digital twin model throughout its entire life cycle for the scenario faced by this invention and the technical problems to be solved.

[0100] In another embodiment, step S400 includes:

[0101] S401: Define the optimization problem with tracking virtual power plant dispatch instructions as the core objective and minimizing air conditioning regulation costs as the economic objective, and establish a rolling optimization model. In each optimization cycle (e.g., the current time t0), solve for the optimal control sequence {u∗(t0),...,u∗(t0+H−1)} for the next H time periods (e.g., 96H=96, i.e., 24 hours, with each hour divided into 15-minute intervals, 24×4=96).

[0102] Objective function:

[0103]

[0104] in,

[0105] λ,ρ: Weighting coefficients, balancing tracking accuracy and adjustment costs.

[0106] .

[0107] S402: Define constraints

[0108] The air conditioning regulation capacity is constrained as follows: ;

[0109] Indoor temperature comfort constraints are as follows: Tin(t+1) is calculated by the thermal dynamic model that incorporates updated parameters in step S203;

[0110] The hard constraints on air conditioner power are as follows: ;

[0111] Regulation continuity constraint: To avoid frequent start-stop of the air conditioner.

[0112] Thus, it can be seen that, mathematically speaking, the above optimization problem is a quadratic programming (QP) problem with linear constraints, which can be efficiently solved using mature algorithms such as the interior-point method to obtain the optimal control sequence {u∗(t)}, and then transformed into specific control commands:

[0113] like Send an instruction to the corresponding station to increase the air conditioning set temperature by ΔT at time t, or to reduce the operating frequency.

[0114] like Lower the set temperature or pre-cool it.

[0115] The specific implementation of S400 described above constructs a complete coupled aggregation optimization model, unifying business objectives (tracking VPP commands), physical constraints (air conditioning regulation capacity, temperature comfort), and economic costs (regulation costs) within a single mathematical framework. Its core contribution lies in proposing a systematic control method that uses air conditioning as a flexible resource to dynamically compensate for photovoltaic randomness, achieving precise tracking of aggregated power, and providing a solvable mathematical form.

[0116] In another embodiment, step S500 includes:

[0117] S501: Platform Architecture Design. The design is based on a microservice-based three-layer architecture of "cloud-edge-device".

[0118] Cloud platform (VPP aggregation layer): Deploys the aggregation optimization algorithm of the above S400, receives power grid dispatch instructions, and issues control targets to each line.

[0119] Edge Controller (Line Control Layer): Deployed in the control centers of each subway line, it runs the S300 model and the S400 optimization solver, generates specific station air conditioning control commands, and uploads the execution results.

[0120] Station equipment layer: Photovoltaic inverters and station BAS (Building Automation System) receive and execute commands.

[0121] S502: Implementation of self-optimization and self-diagnosis functions

[0122] Parameter self-learning: As described in S303, the FFRLS module runs continuously to update the model parameters.

[0123] Adaptive strategy: Design a two-layer optimization. The inner layer performs the rolling optimization described above. The outer layer evaluates historical performance at regular intervals (e.g., once a week).

[0124] If the long-term tracking error is large, the weighting coefficients λ and ρ will be automatically adjusted.

[0125] If a station frequently reaches its adjustment limit, its adjustable potential parameters will be automatically reassessed.

[0126] In addition, self-diagnosis includes the following abnormal self-diagnoses:

[0127] Photovoltaic anomalies: Comparison with predicted output With actual output If the error exceeds the limit continuously, an alarm for "photovoltaic panel failure" or "irradiator malfunction" will be triggered.

[0128] Air conditioning malfunction: Compare predicted room temperature Compared to actual room temperature If the error continues to exceed the limit without adjustment, an alarm for "air conditioning system efficiency decline" or "sensor failure" will be triggered.

[0129] It should be noted that the platform can also provide visualization methods such as a web interface to display: real-time photovoltaic output and prediction curves, air conditioning load and adjustable potential of each station, VPP dispatch instructions and actual aggregated power tracking, system energy efficiency indicators, alarm information, etc.

[0130] The specific implementation of the above step S500 designs a smart energy management system with self-learning and self-maintenance capabilities. Its technical contribution in this field lies in realizing the leap from single optimization to continuous optimization and from open-loop control to closed-loop diagnosis, ensuring that the "metro photovoltaic-air conditioning" virtual power plant aggregate participates in grid interaction in a long-term, stable and efficient manner. The inventors did not find similar reports in the existing technology.

[0131] Although the embodiments of the present invention have been described above in conjunction with the figures, the present invention is not limited to the specific embodiments and application fields described above. The specific embodiments described above are merely illustrative and instructive, and not restrictive. Those skilled in the art can make many other forms based on the guidance of this specification and without departing from the scope of protection of the claims of the present invention, and all of these are within the scope of protection of the present invention.

Claims

1. A virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation, characterized in that, Includes the following steps: S100: Collect data on the photovoltaic output characteristics of distributed photovoltaic systems in the subway under different sunshine conditions, and collect data on the power supply load of subway air conditioning under different ambient temperatures, on weekdays and non-working days, and on special holidays, and establish a database. S200, based on a database of measured loads of subway photovoltaic and air conditioning, utilizes modeling simulation and big data technologies, combined with historical meteorological data to build a digital twin model of rail transit photovoltaic and air conditioning; S300 utilizes machine learning technology to improve the accuracy and precision of digital twin models of photovoltaic and air conditioning systems in rail transit. S400, based on the digital twin model and combined with the dispatch load curve issued by the urban power grid virtual power plant platform, constructs an aggregation method that couples subway photovoltaic power supply with air conditioning regulation.

2. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation as described in claim 1, characterized in that, It also includes the following steps: S500, optimize control strategy design, study adaptive control technology with real-time optimization and autonomous judgment function of overall operation efficiency, design integrated energy management platform for metro photovoltaic power supply and air conditioning interaction, realize intelligent operation of metro photovoltaic and air conditioning with self-optimization and self-diagnosis throughout the process, and realize efficient management of all links of the energy chain.

3. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation as described in claim 1, characterized in that, Considering the changes in the power supply characteristics of subway photovoltaic grid connection, this study investigates the load characteristics of rail transit photovoltaic power supply and explores the demand of virtual power plants for subway photovoltaic power supply regulation.

4. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation as described in claim 1, characterized in that, Step S200 also includes the following steps: This research focuses on the coordinated control technology for multi-power source and multi-load operation, the self-consistent optimization power supply technology for rail transit with grid-source-load coordination, and the development of source-load complementary modeling and simulation algorithms.

5. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation as described in claim 4, characterized in that, The source-load complementary modeling and simulation algorithm described above couples the electricity load of subway photovoltaic and subway air conditioning through the model, and combines the electricity consumption characteristics of air conditioning to study the problem of subway air conditioning participating in the emergency compensation of the subway virtual power plant when the output of photovoltaic is insufficient.

6. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation as described in claim 1, characterized in that, Step S100 also includes the following steps: collecting data on subway photovoltaic and air conditioning loads and influencing factors using a temperature and humidity collector and a subway load remote recording device, forming a database based on actual measurements of subway photovoltaic and air conditioning loads, and using machine learning technology to improve the accuracy and precision of the model.

7. The virtual power plant load aggregation method based on the coupling of subway photovoltaic power supply and air conditioning regulation according to claim 1, characterized in that, Step S400 also includes the following steps: When considering emergency compensation for air conditioning, the comfort of the station environment should be fully guaranteed while ensuring the safe operation of the subway. Therefore, a feedback function should be established for intelligent scheduling.

Images