Electric vehicle and building energy management optimization method based on digital twin technology

Abstract

The invention discloses an electric vehicle and building energy management optimization method based on a digital twin technology, and belongs to the field of building energy management and electric vehicle integration. The electric vehicle and building energy management optimization method based on the digital twin technology comprises the following steps: acquiring real-time data related to a building energy system, and performing short-term prediction; an energy management optimization model is constructed by considering the vehicle state, the electric power price and the photovoltaic power generation factor; performing dynamic optimization solution on the energy management optimization model based on real-time data and a prediction result, sending an optimization result to charging equipment and a battery management system through a communication interface, and adjusting an operation strategy in real time through a feedback mechanism to obtain a final scheduling result; the energy management method is based on the digital twin technology and is combined with the dynamic optimization model, and the energy management problem of the electric vehicle and building integrated system can be better solved.

Description

Technical Field

[0001] The present invention belongs to the field of building energy management and electric vehicle integration, and specifically relates to an electric vehicle and building energy management optimization method based on digital twin technology. Background Art

[0002] With the increasing penetration of electric vehicles (EVs) and the development of distributed renewable energy, building energy systems are facing the need to optimize power utilization and improve energy efficiency. Among existing technologies, vehicle-to-grid (V2G) technology has demonstrated its potential for bidirectional energy flow and peak load shifting. However, optimal management of EVs integrated into building energy systems remains challenging, including complex dynamic loads, the volatility of photovoltaic power generation, and real-time energy price fluctuations.

[0003] To this end, an electric vehicle and building energy management optimization method based on digital twin technology is proposed. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an electric vehicle and building energy management optimization method based on digital twin technology to solve the problems in the existing technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The electric vehicle and building energy management optimization method based on digital twin technology includes the following steps:

[0007] Collect real-time data related to building energy systems and make short-term forecasts;

[0008] Considering vehicle status, electricity prices, and photovoltaic power generation factors, an energy management optimization model is constructed;

[0009] Based on real-time data and prediction results, the energy management optimization model is dynamically optimized and solved, and the optimization results are sent to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result.

[0010] Furthermore, the real-time data related to the building energy system includes: building load data, photovoltaic power generation data, electric vehicle data, power grid and energy price data, energy storage system data and equipment operation constraints.

[0011] Furthermore, in the real-time data collection process, the communication protocols and interfaces used to implement real-time data exchange include: standardized protocols, Internet of Things platforms, edge computing devices, and API interfaces.

[0012] Furthermore, when forecasting data, ARIMA or seasonal decomposition methods are used to predict building load, photovoltaic power generation and electricity price fluctuations; and based on the collected real-time data, the actual value is compared with the predicted value, and the forecast deviation is corrected through Kalman filtering or error regression method.

[0013] Furthermore, when predicting data, for building loads, load curve forecasts are generated; for photovoltaic power generation, photovoltaic power generation output is predicted based on weather changes, capturing dynamic changes in shadows or clouds; for electricity price fluctuation data, electricity market data modeling is used to predict peak and trough periods of electricity prices.

[0014] Furthermore, the objective function of the energy management optimization model is:

[0015]

[0016] Among them, p grid-in,h represents the power purchased from the grid during period h; c grid-in,h represents the unit price of electricity purchased from the power grid in period h; p grid-out,h represents the power sold to the grid in period h; c grid-out,h The unit price of electricity sold in period h.

[0017] Furthermore, the constraints of the energy management optimization model include:

[0018] p load,h =p grid-in,h -p grid-out,h +p PV,h +p EV,h +p battery,h

[0019]

[0020] SOC EV,min ≤SOC EV,i,h ≤SOC EV,max

[0021]

[0022] p PV,h ≤p PV,max,h

[0023] p grid-in,h ≤p grid-in,max ,p grid-out,h ≤p grid-out,max

[0024] SOC EV,i,18 ≥1.1 SOC EV,i,9

[0025] Among them, p load,hrepresents the total load demand of the building in period h, p PV,h represents the output power of the photovoltaic power generation system in the hth period, p EV,h represents the net power contribution of the electric vehicle battery in the hth period, p battery,h Indicates the charging and discharging power of the energy storage equipment inside the building; SOC EV,i,h is the state of charge of the i-th vehicle at the h-th period, E EV,i is the battery capacity of the i-th vehicle; p charge,i,h and p discharge,i,h are the charging and discharging powers respectively; η charge and η discharge They are charge and discharge efficiency; SOC EV,min SOC is the lower limit of the state of charge of electric vehicles. EV,max is the upper limit of the state of charge of the electric vehicle; t arrival and t departure They represent the estimated arrival and departure times of electric vehicles respectively; p PV,max,h represents the maximum power of photovoltaic power generation in the h period; p grid-in,max and p grid-out,max are the maximum input and output power allowed by the power grid; SOC EV,i,18 is the state of charge of the i-th vehicle in the 18th period, SOC EV,i,9 is the state of charge of the i-th vehicle in the 9th period.

[0026] Furthermore, the steps of obtaining the final scheduling result are:

[0027] Divide the day into multiple time periods for segment-by-segment optimization; dynamically adjust EV availability constraints, SOC upper and lower limits, and PV power output limits; and update power balance and grid interaction limits based on the latest data. Utilize mixed integer linear programming to solve the optimal strategy, including EV charging and discharging power, energy storage device operation strategy, and grid power purchase and sales plans.

[0028] The optimization results are sent via a communication interface to dynamically control the charging and discharging of electric vehicles, the operation of energy storage devices, and the interaction with the grid. The optimal strategy is implemented, giving priority to using photovoltaic power generation to meet building load demands. When there is excess photovoltaic power generation, the remaining energy is used for charging or sold to the grid. When there is insufficient photovoltaic power generation, the energy storage device is activated or electricity is purchased from the grid.

[0029] Compare actual operating data with predicted values, detect errors, and monitor equipment operating status; adjust data prediction models through deviation analysis, and use Kalman filtering to correct photovoltaic power generation and load forecasts; and update input parameters of energy management optimization models.

[0030] The electric vehicle and building energy management optimization system based on digital twin technology includes:

[0031] Data collection and prediction module: collects real-time data related to the building energy system and makes short-term predictions;

[0032] Optimization model building module: Considering vehicle status, electricity price, and photovoltaic power generation factors, an energy management optimization model is constructed;

[0033] And, the optimization model solving module: based on real-time data and prediction results, the energy management optimization model is dynamically optimized and solved, and the optimization results are sent to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result.

[0034] A computer storage medium stores a readable program, which can execute the above-mentioned load forecasting method when the program is run.

[0035] An electronic device comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0036] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the load forecasting method described above.

[0037] A computer program product includes computer instructions, wherein the computer instructions instruct a computing device to execute operations corresponding to the above-mentioned load forecasting method.

[0038] Beneficial effects of the present invention:

[0039] By introducing digital twin technology and real-time data collection and analysis, we can achieve accurate modeling and dynamic simulation of building energy systems, improve the adaptability to complex dynamic loads, and thus optimize the collaborative energy management of electric vehicles and buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0041] Figure 1 This is a diagram of the integrated structure of the electric vehicle and building energy management system of the present invention;

[0042] Figure 2 It is a schematic diagram of the optimization process of the energy management system of the present invention;

[0043] Figure 3This is a flow chart of the electric vehicle and building energy management optimization method of the present invention. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] Example 1

[0046] Figure 1 This paper describes the architecture of an electric vehicle and building energy management optimization system based on digital twin technology. The system consists of a digital twin model and a remote server, which exchange data through communication. The digital twin model simulates the operating status of the building energy system in real time and generates simulation results that are transmitted to the remote server. The remote server performs optimization calculations based on the received data, generates an optimized power strategy, and feeds this back to the digital twin model to adjust system operating parameters.

[0047] Figure 2 This system optimizes the energy management process for electric vehicles and buildings based on digital twin technology. The system first obtains target electricity prices and grid-connected vehicle information, predicts load and photovoltaic power generation, and performs dynamic simulation. It then determines the power setpoint through optimization decisions and determines whether the optimization target has been achieved. If not, the system continues to iterate; otherwise, the process ends.

[0048] like Figure 3 As shown in FIG, the electric vehicle and building energy management optimization method based on digital twin technology includes the following steps:

[0049] S1, collects real-time data related to building energy systems and makes short-term forecasts;

[0050] Data collection and prediction are the foundation of the optimization method. Its purpose is to obtain system operation data in real time to provide accurate input for the optimization model, and at the same time improve the adaptability to future energy demand and supply through prediction algorithms. Data collection mainly focuses on the key elements of the building energy system;

[0051] 1) Real-time data related to building energy systems

[0052] Specifically including: building load data, photovoltaic power generation data, electric vehicle data, grid and energy price data, energy storage system data and equipment operation constraints;

[0053] 1.1) Building load data, including:

[0054] Real-time load: The building's energy management system (EMS) collects the real-time power demand of various electrical equipment, including lighting, air conditioning, office equipment, etc.

[0055] Historical load curve: Obtain historical building load data and analyze daily patterns and peak time periods.

[0056] Partition load: For complex building structures, load data is collected by floor or functional partition to facilitate refinement and optimization of the model.

[0057] 1.2) Photovoltaic power generation data, including:

[0058] Real-time power generation: The current photovoltaic power generation is collected through the photovoltaic inverter.

[0059] Meteorological data: Obtain meteorological information related to photovoltaic power generation from meteorological sensors or external API interfaces (such as weather service platforms), including solar radiation intensity, cloud coverage, temperature, etc.

[0060] Historical power generation records: Combine historical data to establish a photovoltaic power generation model and analyze power generation patterns under different seasons and weather conditions.

[0061] 1.3) Electric vehicle data, including:

[0062] State of Charge (SOC): The battery charging status is obtained in real time through the communication interface with the electric vehicle charging equipment (such as ISO15118-9).

[0063] Vehicle arrival and departure times: Records the time when electric vehicles enter the parking lot and the estimated time of departure to determine vehicle availability.

[0064] Target charge capacity: Collects the target charge capacity or minimum battery capacity requirement set by the vehicle owner to ensure that the vehicle meets the requirements when leaving.

[0065] Charging power and efficiency: Real-time monitoring of electric vehicle charging power and collection of charging and discharging efficiency parameters of the equipment.

[0066] 1.4) Grid and energy price data, including:

[0067] Real-time electricity price: Obtain real-time electricity price fluctuation data from the electricity market or energy service providers.

[0068] Historical electricity price curve: Analyze historical electricity price trends and predict future electricity price fluctuations.

[0069] Regional power grid data: Collects the interaction power between buildings and the grid, access point constraints, and grid power supply stability.

[0070] 1.5) Energy storage system data, including:

[0071] Energy storage device status: Real-time acquisition of the battery energy storage system's SOC, charge and discharge power, and device capacity.

[0072] Energy storage efficiency: includes charging efficiency, discharging efficiency, and efficiency changes due to equipment aging.

[0073] 1.6) Equipment operation constraints, including:

[0074] Device status: Obtain the operating status of electric vehicle charging piles, photovoltaic inverters, and energy storage devices, including whether they are online and device fault information.

[0075] Safety constraints: Monitor the maximum allowable power, current, voltage, etc. of the equipment to prevent overload or overheating.

[0076] 2. Data transmission and communication

[0077] Real-time data acquisition relies on efficient data transmission and communication technology. The following communication protocols and interfaces are used to achieve real-time data exchange:

[0078] 2.1) Standardized protocols: Supports communication protocols such as ISO 15118, Modbus, and OPC UA to achieve interoperability between different devices.

[0079] 2.2) Internet of Things (IoT) Platform: Utilize IoT devices (such as smart meters, sensors, and controllers) to collect data and upload it to the cloud via wireless networks (such as Wi-Fi, LoRa, or 5G).

[0080] 2.3) Edge computing devices: Edge computing nodes are deployed locally to pre-process data to reduce network latency and improve real-time response capabilities.

[0081] 2.4) API interface: Obtain relevant data from external platforms (such as meteorological services and electricity markets) through open API interfaces.

[0082] 3. Data prediction

[0083] Based on real-time data collection, predictive algorithms provide forward-looking input for optimization models

[0084] 3.1) Forecasting Methods: Use ARIMA or seasonal decomposition methods to predict building load, PV power generation, and electricity price fluctuations; utilize regression models (such as XGBoost and random forest) or deep learning algorithms (such as LSTM) to improve forecast accuracy; combine physical modeling with data-driven methods, and comprehensively consider the impact of environmental variables and historical data.

[0085] 3.2) Forecast Content: For building loads, short-term (e.g., 15 minutes to 1 hour) and medium- to long-term (e.g., 1 day) load curve forecasts are generated. For photovoltaic power generation, photovoltaic power generation output is predicted based on weather changes, capturing dynamic changes in shadows or cloud cover. For electricity price fluctuation data, electricity market data modeling is used to predict peak and trough periods of electricity prices, providing a reference for optimized decision-making.

[0086] 3.3) Data update and feedback

[0087] The prediction model is updated in real time based on the latest collected data, improving the algorithm's dynamic adaptability. Actual values ​​are compared with predicted values, and prediction deviations are corrected using Kalman filtering or error regression methods. Through multi-level data collection and prediction, the system provides comprehensive, accurate, and dynamic input data for the optimization algorithm, ensuring the reliability and applicability of the optimization results in complex scenarios.

[0088] S2, considers vehicle status, electricity price, and photovoltaic power generation factors to build an energy management optimization model;

[0089] The optimization model, based on mixed-integer linear programming (MILP), focuses on the interaction between photovoltaic power generation, electric vehicle energy storage, and the grid within the building energy system. It incorporates multiple dynamic constraints to ensure a balance between economic efficiency and energy efficiency under complex and variable operating conditions. The model aims to coordinate the use of internal building resources through dynamic optimization strategies to reduce energy costs while meeting the power requirements of electric vehicles and the building's energy stability requirements.

[0090] 1. Objective Function

[0091] The core goal of the energy management optimization model is to minimize the total operating cost of the building energy system, while at the same time improving economic benefits and system efficiency by dynamically adjusting grid interaction, photovoltaic power generation utilization, and electric vehicle charging and discharging strategies while meeting the building load and vehicle power requirements. The objective function of the energy management optimization model is:

[0092]

[0093] Among them, p grid-in,h represents the power purchased from the grid in period h, taking into account the building load demand or battery charging; c grid-in,h represents the unit price of electricity purchased from the power grid in period h, which changes dynamically according to the real-time price fluctuations in the power market; p grid-out,h represents the power sold to the grid during the h period, usually the surplus power of building photovoltaic power generation or battery discharge power; c grid-out,hThe unit price of electricity sold during period h may be affected by local electricity market rules or building contract terms. The objective function design not only considers the direct economic costs of purchasing and selling electricity but also implicitly promotes peak load reduction (peak shaving) and maximum utilization of photovoltaic power generation, helping to reduce dependence on external energy supplies.

[0094] 2 Constraints

[0095] The optimization model must be solved under the premise of satisfying multiple physical and operational constraints to ensure the practical feasibility and reliability of the results. The following is an expanded description of the main constraints:

[0096] 2.1) Power balance constraints ensure that the sum of all energy flows within the system matches real-time demand, while supporting dynamic adjustment of photovoltaic power generation, battery charging and discharging, and grid interaction. The power balance of the building energy system in any time period h must meet the following requirements:

[0097] p load,h =p grid-in,h -p grid-out,h +p PV,h +p EV,h +p battery,h (2)

[0098] Among them, p load,h represents the total load demand of the building in the hth period, including basic electricity, air conditioning, office equipment, etc.; p PV,h represents the output power of the photovoltaic power generation system in the hth period, which depends on weather and equipment conditions; p EV,h represents the net power contribution of the electric vehicle battery in the hth period, including charging and discharging; p battery,h Indicates the charging and discharging power of the energy storage equipment inside the building.

[0099] 2.2) The charging and discharging of electric vehicle batteries are subject to the following state constraints, including the battery dynamic change equation, SOC safety range, and charging constraints when leaving:

[0100]

[0101] Among them, E EV,i is the battery capacity of the i-th vehicle; p charge,i,h and p discharge,i,h are the charging and discharging powers respectively; η charge and η discharge They are charge and discharge efficiency, usually less than 1, SOC EV,i,h is the state of charge of the i-th vehicle at the h-th time period

[0102] 2.3) To prevent battery overcharge or over-discharge and protect battery life, it is necessary to consider the battery SOC safety range:

[0103] SOC EV,min ≤SOC EV,i,h ≤SOC EV,max (4)

[0104] Among them, SOC EV,min Is the lower limit of the state of charge of electric vehicles, SOC EV,max The upper limit of the state of charge of electric vehicles

[0105] 2.4) Optimization uses a rolling time window approach, performing optimization calculations for each time period (e.g., 15 minutes) and dynamically adjusting the strategy for the next phase. This approach can respond to unexpected events such as load surges or sudden drops in photovoltaic power generation. To ensure that vehicles can only charge or discharge during parking time, the following constraints must be met:

[0106]

[0107] Among them, t arrival and t departure represent the estimated arrival and departure times of electric vehicles, respectively.

[0108] 2.5) For photovoltaic power generation restrictions, the following constraints must be met:

[0109] p PV,h ≤p PV,max,h (6)

[0110] Among them, p PV,max,h It represents the maximum power of photovoltaic power generation in the hth period, taking into account the dynamic changes in weather and equipment conditions.

[0111] 2.6) When interacting with the grid, purchase and sale power must be limited to prevent exceeding the power cap set by the grid or the contract. Specific constraints are as follows:

[0112] p grid-in,h ≤p grid-in,max ,p grid-out,h ≤p grid-out,max (7)

[0113] Among them, p grid-in,max and p grid-out,max are the maximum input and output power allowed by the power grid respectively.

[0114] 2.7) In addition, to ensure that the battery charge of electric vehicles is not less than 110% of the charge when they arrive, high-reliability charging services are provided to car owners.

[0115] SOC EV,i,18 ≥1.1 SOC EV,i,9 (8)

[0116] Among them, SOC EV,i,18 is the state of charge of the i-th vehicle at the 18th period (when leaving), SOC EV,i,9 is the state of charge of the i-th vehicle at the 9th time period (arrival time).

[0117] S3, based on the real-time data and prediction results collected in S1, dynamically optimizes and solves the energy management optimization model built in S2, and sends the optimization results to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result;

[0118] Through real-time data collection, rolling optimization, and feedback mechanisms, the system can quickly respond to changes in external conditions and dynamically adjust energy management strategies to achieve efficient coordination between building energy systems and electric vehicle energy storage.

[0119] The steps to obtain the final scheduling results are:

[0120] S31, rolling time window optimization;

[0121] Time segmentation: Divide a day into multiple time periods (such as 15 minutes) and optimize them segment by segment.

[0122] Constraint update: Dynamically adjust EV availability constraints, SOC upper and lower limits, and PV output limits, and update power balance and grid interaction limits based on the latest data.

[0123] Objective: Use mixed integer linear programming (MILP) to solve the optimal strategy, including: electric vehicle charging and discharging power, energy storage equipment operation strategy and power grid purchase and sales plan.

[0124] S32, strategy execution;

[0125] Energy distribution: photovoltaic power generation is used first to meet building load needs; when photovoltaic power generation is in excess, the remaining energy is used for charging or sold to the grid; when photovoltaic power generation is insufficient, energy storage equipment is used or electricity is purchased from the grid.

[0126] Equipment control: Optimization results are sent through the communication interface to dynamically control the charging and discharging of electric vehicles, the operation of energy storage devices, and the interaction with the power grid.

[0127] S33, real-time feedback and adjustment;

[0128] Actual operation monitoring: Compare actual operation data with predicted values ​​to detect errors; monitor equipment operating status to ensure the effectiveness of optimization strategy execution.

[0129] Error correction: Adjust the data prediction model through deviation analysis and use Kalman filtering to correct photovoltaic power generation and load forecasts; update the input parameters of the energy management optimization model to improve the decision accuracy of the next time period.

[0130] Based on similar inventive concepts, an embodiment of the present invention also provides a computer storage medium storing a readable program, which, when the program is running, can execute the above-mentioned electric vehicle and building energy management optimization method based on digital twin technology.

[0131] Based on similar inventive concepts, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0132] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned electric vehicle and building energy management optimization method based on digital twin technology.

[0133] Based on similar inventive concepts, an embodiment of the present invention also provides a computer program product, including computer instructions, which instruct a computing device to perform operations corresponding to the above-mentioned electric vehicle and building energy management optimization method based on digital twin technology.

[0134] Example 2

[0135] Based on the electric vehicle and building energy management optimization method based on digital twin technology proposed in Example 1, this embodiment proposes an electric vehicle and building energy management optimization system based on digital twin technology, which specifically includes:

[0136] Data collection and prediction module: collects real-time data related to the building energy system and makes short-term predictions;

[0137] Optimization model building module: Considering vehicle status, electricity price, and photovoltaic power generation factors, an energy management optimization model is constructed;

[0138] And, the optimization model solving module: based on real-time data and prediction results, the energy management optimization model is dynamically optimized and solved, and the optimization results are sent to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result.

[0139] The method of the present invention can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CDROM, RAM, floppy disk, hard disk or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded over a network and will be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It will be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.

[0140] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention as claimed.

Claims

1. Electric vehicle and building energy management optimization method based on digital twin technology, characterized by: The following steps are involved: Collect real-time data related to building energy systems and make short-term forecasts; Considering vehicle status, electricity prices, and photovoltaic power generation factors, an energy management optimization model is constructed; Based on real-time data and prediction results, the energy management optimization model is dynamically optimized and solved, and the optimization results are sent to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result.

2. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 1 is characterized in that: The real-time data related to the building energy system includes: building load data, photovoltaic power generation data, electric vehicle data, power grid and energy price data, energy storage system data and equipment operation constraints.

3. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 2 is characterized in that: During the real-time data collection process, the communication protocols and interfaces used to implement real-time data exchange include: standardized protocols, Internet of Things platforms, edge computing devices, and API interfaces.

4. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 2 is characterized in that: When forecasting data, ARIMA or seasonal decomposition methods are used to predict building load, photovoltaic power generation and electricity price fluctuations; and based on the collected real-time data, the actual value is compared with the predicted value, and the forecast deviation is corrected through Kalman filtering or error regression method.

5. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 2 is characterized in that: When predicting data, for building loads, load curve forecasts are generated; for photovoltaic power generation, photovoltaic power generation output is predicted based on weather changes, capturing dynamic changes in shadows or clouds; for electricity price fluctuation data, electricity market data modeling is used to predict peak and trough periods of electricity prices.

6. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 1 is characterized in that: The objective function of the energy management optimization model is: Among them, p grid-in,h represents the power purchased from the grid during period h; c grid-in,h represents the unit price of electricity purchased from the power grid in period h; p grid-out,h represents the power sold to the grid in period h; c grid-out,h The unit price of electricity sold in period h.

7. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 6 is characterized in that: The constraints of the energy management optimization model include: p load,h =p grid-in,h -p grid-out,h +p PV,h +p EV,h +p battery,h SOC EV,min ≤SOC EV,i,h ≤SOC EV,max p charge,i,h =0or p discharge,i,h =0if p PV,h ≤p PV,max,h p grid-in,h ≤p grid-in,max ,p grid-out,h ≤p grid-out,max SOCIETY EV,i,18 ≥1.1·SOC EV,i,9 Among them, p load,h represents the total load demand of the building in period h, p PV,h represents the output power of the photovoltaic power generation system in the hth period, p EV,h represents the net power contribution of the electric vehicle battery in the hth period, p battery,h Indicates the charging and discharging power of the energy storage equipment inside the building; SOC EV,i,h is the state of charge of the i-th vehicle at the h-th period, E EV,i is the battery capacity of the i-th vehicle; p charge,i,h and p discharge,i,h are the charging and discharging powers respectively; η charge and η discharge They are charge and discharge efficiency; SOC EV,min SOC is the lower limit of the state of charge of electric vehicles. EV,max is the upper limit of the state of charge of the electric vehicle; t arrival and t departure They represent the estimated arrival and departure times of electric vehicles respectively; p PV,max,h represents the maximum power of photovoltaic power generation in the h period; p grid-in,max and p grid-out,max are the maximum input and output power allowed by the power grid; SOC EV,i,18 is the state of charge of the i-th vehicle in the 18th period, SOC EV,i,9 is the state of charge of the i-th vehicle in the 9th period.

8. The electric vehicle and building energy management optimization method based on digital twin technology according to claim 1 is characterized in that: The steps for obtaining the final scheduling result are: Divide the day into multiple time periods for segment-by-segment optimization; dynamically adjust EV availability constraints, SOC upper and lower limits, and PV power output limits; and update power balance and grid interaction limits based on the latest data. Utilize mixed integer linear programming to solve the optimal strategy, including EV charging and discharging power, energy storage device operation strategy, and grid power purchase and sales plans. The optimization results are sent via a communication interface to dynamically control the charging and discharging of electric vehicles, the operation of energy storage devices, and the interaction with the grid. The optimal strategy is implemented, giving priority to using photovoltaic power generation to meet building load demands. When there is excess photovoltaic power generation, the remaining energy is used for charging or sold to the grid. When there is insufficient photovoltaic power generation, the energy storage device is activated or electricity is purchased from the grid. Compare actual operating data with predicted values, detect errors, and monitor equipment operating status; adjust data prediction models through deviation analysis, and use Kalman filtering to correct photovoltaic power generation and load forecasts; and update input parameters of energy management optimization models.

9. The electric vehicle and building energy management optimization system based on digital twin technology is characterized by: include: Data collection and prediction module: collects real-time data related to the building energy system and makes short-term predictions; Optimization model building module: Considering vehicle status, electricity price, and photovoltaic power generation factors, an energy management optimization model is constructed; And, the optimization model solving module: based on real-time data and prediction results, the energy management optimization model is dynamically optimized and solved, and the optimization results are sent to the charging equipment and battery management system through the communication interface. The operation strategy is adjusted in real time through the feedback mechanism to obtain the final scheduling result.

10. A computer storage medium storing a readable program, characterized in that: When the program is running, it can execute the load forecasting method described in any one of claims 1 to 8.

11. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the load forecasting method according to any one of claims 1 to 8.

12. A computer program product comprising computer instructions, characterized in that The computer instructions instruct the computing device to execute operations corresponding to the load forecasting method according to any one of claims 1 to 8.

Images