Load management method and device, computer device, storage medium and program product

Abstract

The application relates to a load management method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: obtaining historical load information of an energy system; the energy system comprises a building cluster and an electric vehicle; according to the historical load information of the energy system, the space heating load of the building cluster, the building electricity load and the charging and discharging load of the electric vehicle are predicted; according to the space heating load, the building electricity load and the charging and discharging load, the load of the energy system is managed to obtain the load management result of the energy system. The method can be used for the collaborative optimization and management of the load of the building cluster and the load of the electric vehicle in the urban energy system, and therefore, the electricity stability in the urban energy system can be improved.

Description

Technical Field

[0001] This application relates to the field of energy system technology, and in particular to a load management method, apparatus, computer equipment, storage medium, and program product. Background Technology

[0002] With the construction of new power systems and the continuous increase in the use of renewable energy, the balance between power grid supply and demand faces enormous challenges. Building clusters and large-scale electric vehicles, as two extremely important types of loads in urban energy systems, have great potential in participating in grid control and management.

[0003] Among the related technologies, it is possible to manage the load of building clusters or electric vehicles in urban energy systems.

[0004] However, load management methods in related technologies suffer from low power stability in urban energy systems. Summary of the Invention

[0005] Therefore, it is necessary to provide a load management method, device, computer equipment, storage medium, and program product to address the aforementioned technical problems, thereby improving the power supply stability of urban energy systems.

[0006] In a first aspect, this application provides a load management method, the method comprising:

[0007] Acquire historical load information of the energy system; the energy system includes building clusters and electric vehicles;

[0008] Based on the historical load information of the energy system, predict the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster;

[0009] Based on the space heating load, the building electricity load, and the charging and discharging load, load management is performed on the energy system to obtain the load management results of the energy system.

[0010] In one embodiment, the step of performing load management on the energy system based on the space heating load, the building electricity load, and the charging / discharging load to obtain the load management result of the energy system includes:

[0011] The spatial heating deviation of the building cluster is determined based on the building's electrical load.

[0012] The charging schedule of the electric vehicle is determined based on the charging and discharging load.

[0013] Based on the space heating load, the building electricity load, and the charging and discharging load, determine the user load data of each user in the building cluster;

[0014] Based on the user load data of each user, determine the user load scheduling amount;

[0015] The space heating deviation, the charging scheduling amount, and the user load scheduling amount are optimized based on a predetermined objective function to obtain the load management result of the energy system.

[0016] In one embodiment, determining the user load scheduling amount based on the user load data of each user includes:

[0017] The user load data of each user within the building cluster are summed to obtain the aggregated load data of the building cluster.

[0018] Based on the user load data of each user and the aggregate load data, the individual stress level of each user is determined;

[0019] The user load scheduling amount is determined based on the user load data and individual stress level of each user.

[0020] In one embodiment, optimizing the spatial heating deviation, the charging scheduling amount, and the user load scheduling amount based on a pre-determined objective function to obtain the load management result of the energy system includes:

[0021] The target value is obtained by substituting the space heating deviation, the charging scheduling amount, and the user load scheduling amount into the objective function;

[0022] Based on the target value, the spatial heating deviation, the charging scheduling amount, and the user load scheduling amount are adjusted, and the target value is recalculated based on the adjusted spatial heating deviation, the adjusted charging scheduling amount, and the adjusted user load scheduling amount until the target value reaches the optimal value, thus obtaining the load management result of the energy system.

[0023] In one embodiment, the historical load information includes temperature information of the building cluster, historical electricity consumption information of the building cluster, and historical electricity consumption information of the electric vehicles; the step of predicting the spatial heating load, building electricity load, and charging / discharging load of the electric vehicles based on the historical load information of the energy system includes:

[0024] The temperature information of the building cluster is input into the thermal model for prediction to obtain the spatial heating load of the building cluster.

[0025] The historical electricity consumption information of the building cluster is input into the power load model for prediction to obtain the building's electricity load;

[0026] The historical electricity consumption information of the electric vehicle is input into the electric vehicle prediction model for prediction, and the charging and discharging load of the electric vehicle is obtained.

[0027] In one embodiment, the method further includes:

[0028] The initial prediction model is evaluated according to a preset evaluation function to obtain the evaluation result of the initial prediction model; the preset evaluation function includes at least one of root mean square error, goodness of fit, root mean square error coefficient of variation and probability distribution; the initial prediction model includes an initial thermal model, an initial power load model and an initial electric vehicle prediction model.

[0029] If the evaluation result indicates that the evaluation is passed, the initial thermal model is used as the thermal model, the initial power load model is used as the power load model, and the initial electric vehicle prediction model is used as the electric vehicle prediction model.

[0030] Secondly, this application also provides a load management device, comprising:

[0031] The acquisition module is used to acquire historical load information of the energy system, which includes building clusters and electric vehicles.

[0032] The prediction module is used to predict the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster based on the historical load information of the energy system.

[0033] The load management module is used to perform load management on the energy system based on the space heating load, the building electricity load, and the charging and discharging load, and obtain the load management result of the energy system.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the above embodiments.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0036] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0037] The aforementioned load management method, apparatus, computer equipment, storage medium, and program product acquire historical load information of an energy system, which includes building clusters and electric vehicles. Based on the historical load information, the system predicts the spatial heating load, building electricity load, and electric vehicle charging / discharging load. Based on these loads, the system performs load management to obtain the load management results. This application's embodiment can perform load management on the energy system based on the spatial heating load, building electricity load, and electric vehicle charging / discharging load of the building clusters. Therefore, it can collaboratively optimize and manage the loads of building clusters and electric vehicles in an urban energy system, thereby improving the power stability of the urban energy system. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a diagram illustrating the application environment of a load management method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating a load management method in one embodiment;

[0041] Figure 3 This is a flowchart illustrating the load prediction step in one embodiment;

[0042] Figure 4 This is a flowchart illustrating the load optimization steps in one embodiment;

[0043] Figure 5 This is a flowchart illustrating the load management method in another embodiment;

[0044] Figure 6 This is a structural block diagram of a load management device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0047] With the construction of new power systems and the continuous increase in the use of renewable energy, the balance between power grid supply and demand faces enormous challenges. Building clusters and large-scale electric vehicles (EVs), as two extremely important types of loads in urban energy systems, have great potential in participating in power grid control and management.

[0048] However, achieving efficient collaborative management of building clusters and electric vehicles faces numerous technical bottlenecks. On the one hand, building loads need to be adjusted while ensuring user thermal comfort; on the other hand, EV users' travel demands and charging / discharging behaviors are highly random and uncertain. Without unified coordination, the disorderly access of large-scale EVs can easily generate new load peaks, exacerbating the pressure on the power distribution network.

[0049] In related technologies, only the load of building clusters or electric vehicles in urban energy systems can be managed. Therefore, the load management methods in these technologies suffer from low power stability in urban energy systems.

[0050] Therefore, there is currently a lack of a mechanism that can dynamically quantify the overall pressure of external grid signals on urban energy systems and intelligently trigger efficient collaborative optimization strategies based on this pressure. This lack of a triggering mechanism often results in urban energy systems responding slowly to urgent grid demands, or performing unnecessary complex collaborative calculations under low-pressure conditions, making it difficult to achieve the optimal balance between ensuring grid stability and reducing user energy costs.

[0051] Having described the background technology of the load management method provided in the embodiments of this application, the following will briefly describe the implementation environment involved in the load management method provided in the embodiments of this application. The load management method provided in the embodiments of this application can be applied to, for example, Figure 1The computer device shown can be a terminal or a server. It includes a processor, memory, input / output interfaces, a communication interface, a display unit, and input devices. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input devices are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a load management method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0052] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0053] In one embodiment, such as Figure 2 As shown, a load management method is provided, and the method is illustrated using a computer device as an example. The method includes the following steps:

[0054] S201, Obtain historical load information of the energy system; the energy system includes building clusters and electric vehicles.

[0055] The energy system includes building clusters and electric vehicles. Historical load information may include, but is not limited to, temperature information of building clusters, historical electricity consumption information of building clusters, and historical electricity consumption information of electric vehicles.

[0056] In this embodiment of the application, optionally, the computer device can collect historical load information of the energy system within a historical time period in real time or at regular intervals; alternatively, the computer device can also obtain historical load information of the energy system from a database or a preset public platform. Of course, this embodiment of the application does not limit the specific implementation method for obtaining historical load information of the energy system.

[0057] S202, based on historical load information of the energy system, predicts the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster.

[0058] Among them, the space heating load can include, but is not limited to, the building space heating load, temperature prediction results, etc.; the building electricity load can include, but is not limited to, the electrical base load for the future prediction period, etc.; and the electric vehicle charging and discharging load can include, but is not limited to, EV charging and discharging power and SOC (State of Charge) trajectory, etc.

[0059] In this embodiment of the application, optionally, the computer device can input historical load information of the energy system into the load curve prediction model for prediction, and output the spatial heating load of the building cluster, the building electricity load, and the charging and discharging load of electric vehicles. The load curve prediction model is a total load prediction model obtained by integrating three sub-models. For example, the three sub-models may include a gray box thermal model for characterizing building thermodynamics, a support vector machine (SVM) model for estimating the electrical base load demand, and a Monte Carlo simulation model for generating electric vehicle charging probability curves.

[0060] Alternatively, computer equipment can input historical load information of the energy system into thermal models, electrical load models, and electric vehicle prediction models for prediction, thereby outputting the spatial heating load, building electricity load, and electric vehicle charging / discharging load of the building cluster, respectively. Of course, the specific implementation methods for predicting spatial heating load, building electricity load, and charging / discharging load are not limited in the embodiments of this application.

[0061] S203, based on the space heating load, building electricity load and charging / discharging load, performs load management on the energy system and obtains the load management results of the energy system.

[0062] The load management results may include, but are not limited to, optimized space heating load, optimized building electricity load, and optimized electric vehicle charging and discharging load for the future forecast period.

[0063] In this embodiment, optionally, the computer device can merge the space heating load, building electricity load, and charging / discharging load to obtain merged load information, and then perform load management on the energy system based on the merged load information to obtain the load management result of the energy system. Alternatively, the computer device can also determine the user load data of each user within the building cluster based on the space heating load, building electricity load, and charging / discharging load, and then perform load management on the energy system based on the space heating load, building electricity load, charging / discharging load, and the user load data of each user within the building cluster to obtain the load management result of the energy system. Of course, this embodiment does not limit the specific implementation method of load management.

[0064] The aforementioned load management method acquires historical load information of the energy system, which includes building clusters and electric vehicles. Based on this historical load information, it predicts the spatial heating load, building electricity load, and electric vehicle charging / discharging load. Based on these loads, the method performs load management on the energy system, yielding the load management results. This embodiment of the application can perform load management on the energy system based on the spatial heating load, building electricity load, and electric vehicle charging / discharging load of the building clusters. Therefore, it can collaboratively optimize and manage the loads of building clusters and electric vehicles within the urban energy system, thereby improving the power stability of the urban energy system.

[0065] In one embodiment, such as Figure 3 As shown, the aforementioned historical load information includes temperature information of the building cluster, historical electricity consumption information of the building cluster, and historical electricity consumption information of electric vehicles. Based on this, a method for predicting load is provided, namely, "predicting the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster based on the historical load information of the energy system" in S202 above, including:

[0066] S301 inputs the temperature information of the building cluster into the thermal model for prediction, and obtains the spatial heating load of the building cluster.

[0067] The temperature information of the building cluster may include, but is not limited to, indoor temperature, heating power, outdoor air temperature (OAT), and global horizontal irradiance (GHI).

[0068] In this embodiment of the application, optionally, the computer device can directly input the temperature information of the building cluster into the thermal model for prediction to obtain the spatial heating load of the building cluster; or, the computer device can first process the temperature information of the building cluster, and then input the processed temperature information of the building cluster into the thermal model for prediction to obtain the spatial heating load of the building cluster.

[0069] For example, the thermal model can be a gray box thermal model, that is, a 3R2C2α resistive-capacitive thermal network model that combines physical mechanisms and data calibration for heat transfer analysis. Here, the gray box indicates that the thermal model includes both the building's heat transfer physical structure and is calibrated using historical measurement data for thermal resistance, heat capacity, and solar gain parameters. The formulas for the thermal model are shown in equations (1)-(2) below:

[0070] (1)

[0071] (2)

[0072] Among them, T AIR [°C] represents indoor air temperature, T ENV [°C] represents the envelope node temperature, Q HEAT [W] represents heating power. The building's thermodynamic properties are captured by calibrating the above seven parameters: R EXT [K / W] represents the overall thermal resistance of the building, R IN [K / W] represents the overall thermal resistance between the indoor air and the envelope node temperature, R INF [K / W] represents the thermal resistance of permeability, C ENV [J / K] represents the envelope node heat capacity, C AIR [J / K] represents the heat capacity of the air node attached to the interior of the room, representing the contents and air. α ENV [m²] is the solar coefficient, α AIR [m²] represents the low-capacity node coefficient.

[0073] Parameter estimation was performed using a data calibration algorithm developed within the MATLAB environment. The general formula for MRI (Magnetic Resonance Imaging) is as follows:

[0074] (3)

[0075] Where Nd represents the total number of data points in the training set, CH is selected as either the calibration prediction step size or the calibration time domain, the prediction range extends forward by 96 steps, and the time step is 15 minutes. Indicates the start time of the training samples. This indicates the number of predictions made backward from the starting time. Step length This indicates the actual observed temperature. Indicates at time The first one obtained based on model prediction Temperature at time. J is the objective function value in the thermal model parameter calibration process. By minimizing J, the error between the model-predicted temperature and the actual measured temperature is minimized, thereby identifying model parameters such as thermal resistance, heat capacity, and solar gain. Formula (3) completes the model parameter calibration by accumulating the prediction errors of multiple steps.

[0076] S302, input the historical electricity consumption information of the building cluster into the power load model for prediction, and obtain the building electricity load.

[0077] Historical electricity consumption information may include, but is not limited to, historical electrical base load, OAT, GHI, weekdays, and hours. Historical electrical base load may include loads generated by non-adjustable energy sources within the building, such as lighting and office equipment, to represent electricity demand other than space heating. For example, the electricity load model may be an SVM model.

[0078] In this embodiment of the application, optionally, the computer device can directly input the historical electricity consumption information of the building cluster into the power load model for prediction to obtain the building electricity load; or, the computer device can first process the historical electricity consumption information of the building cluster, and then input the processed historical electricity consumption information of the building cluster into the power load model for prediction to obtain the building electricity load.

[0079] S303: Input the historical electricity consumption information of electric vehicles into the electric vehicle prediction model for prediction to obtain the charging and discharging load of electric vehicles.

[0080] Historical electricity consumption information may include, but is not limited to, the arrival time distribution of electric vehicles, initial state of charge (SOC), charging power, battery capacity, and charging and discharging efficiency.

[0081] In this embodiment of the application, optionally, the computer device can directly input the historical electricity consumption information of the electric vehicle into the electric vehicle prediction model for prediction to obtain the charging and discharging load of the electric vehicle; or, the computer device can first process the historical electricity consumption information of the electric vehicle, and then input the processed historical electricity consumption information of the electric vehicle into the electric vehicle prediction model for prediction to obtain the charging and discharging load of the electric vehicle.

[0082] For example, the electric vehicle prediction model (i.e., the EV model) can be an MPC (Model Predictive Control) framework, using SOC as the main decision trigger in predictive optimization load management, and using formula (4) to calculate SOC:

[0083] (4)

[0084] Where, ω e η represents the energy loss rate during a single-step voltage change. Ch For charging efficiency, η Disch P represents the discharge efficiency. in [W] represents the charging power, P out [W] represents the discharge power. The h / Dt ratio was used for hourly standardized measurements, and the final CAP value was... EV [Wh] represents the energy capacity of the battery under study. This formula system can describe any charging level and configuration scheme. Generally, the initial SOC is taken as the initial remaining state of charge when the electric vehicle is connected to the charging facility. This initial SOC can be obtained from the actual measurement data of the vehicle; or, in the absence of real-time data, it can be estimated based on historical travel data and the remaining SOC distribution obtained by Monte Carlo sampling.

[0085] In addition, the Monte Carlo numerical estimation method can be used to identify and predict the arrival time and remaining state of charge (SOC) of electric vehicles.

[0086] In this embodiment, historical load information of the energy system can be input into the thermal model, the power load model, and the electric vehicle prediction model for prediction, so as to accurately output the spatial heating load of the building cluster, the building power load, and the charging and discharging load of electric vehicles respectively.

[0087] In one embodiment, a method for model evaluation is provided, wherein the above method further includes:

[0088] The initial prediction model is evaluated based on the preset evaluation function to obtain the evaluation result of the initial prediction model.

[0089] If the evaluation results indicate that the evaluation is passed, the initial thermal model will be used as the thermal model, the initial power load model will be used as the power load model, and the initial electric vehicle prediction model will be used as the electric vehicle prediction model.

[0090] The preset evaluation function includes at least one of the following: root mean square error, goodness of fit, root mean square error coefficient of variation, and probability distribution. The initial prediction model may include an initial thermal model, an initial power load model, and an initial electric vehicle prediction model.

[0091] In this embodiment of the application, the computer device can evaluate the initial prediction model according to a preset evaluation function to obtain the evaluation result of the initial prediction model. For example, different accuracy thresholds for sub-models can be set. For instance, RMSE and FIT can be used to evaluate the thermal model, and CVRMSE can be used to evaluate the electrical base load model and the total load curve model. The formula for the root mean square error (RMSE) is shown in the following equation (5):

[0092] (5)

[0093] in, For the predicted value, y i For the observed value, n obs The number of observations.

[0094] The formula for goodness of fit (FIT) is shown in equation (6) below:

[0095] (6)

[0096] Where NRMSE is the normalized RMSE, It is the average of the observed values.

[0097] For example, the performance of the SVM model on the power base load and the resulting load curve model are both evaluated using the RMSE coefficient of variation (i.e., CVRMSE, Coefficient of Variation of the Root Mean Square Error) defined in equation (7):

[0098] (7)

[0099] For example, EV models can be evaluated from two levels: probability distribution fitting and load results. At the probability distribution level, the deviations between the arrival time generated by Monte Carlo simulation and the initial SOC distribution are compared with historical data distributions. At the load results level, the simulated daily charging capacity, peak charging power, the proportion of SOC reaching the target value, and whether the upper and lower limits of charging power and the SOC safety boundary are met are evaluated. If the simulation results deviate little from historical statistical characteristics, and the vehicle meets the target SOC threshold before leaving the station, then the EV model is considered to meet the application requirements.

[0100] Therefore, if the initial thermal model is evaluated according to RMSE and FIT and the evaluation result is that the thermal model is evaluated and passed; and the initial power load model and electric vehicle prediction model are evaluated according to CVRMSE and the evaluation result is that the initial power load model and electric vehicle prediction model are evaluated and passed, then the computer equipment can use the initial thermal model as the thermal model, the initial power load model as the power load model, and the initial electric vehicle prediction model as the electric vehicle prediction model.

[0101] If the initial thermal model fails the evaluation based on RMSE and FIT, and / or the initial power load model and electric vehicle prediction model fail the evaluation based on CVRMSE, then the computer equipment can update at least one of the initial prediction models and re-evaluate the updated initial prediction model according to a preset evaluation function until all three initial models—the initial thermal model, the initial power load model, and the initial electric vehicle prediction model—pass the evaluation. This ensures that the accuracy of the subsequently applied thermal model, power load model, and electric vehicle prediction model meets the required standards.

[0102] In one embodiment, such as Figure 4 As shown, a load management implementation method is provided, namely, "based on the space heating load, building electricity load, and charging / discharging load, load management of the energy system is performed to obtain the load management result of the energy system" in S203 above, including:

[0103] S401, determine the spatial heating deviation of the building cluster based on the building's electrical load.

[0104] S402 determines the charging schedule for electric vehicles based on the charging and discharging load.

[0105] Among them, building electrical load can be expressed as The deviation in space heating can be expressed as The space heating deviation is used to balance the discrepancy between heating electricity costs and temperature comfort. The charging / discharging load can be expressed as... The charging scheduling quantity can be expressed as It is used to optimize EV charging and discharging power and penalize deviations from the target SOC or ideal charging behavior.

[0106] In this embodiment of the application, the computer device can calculate the building's electrical load according to the above expression to obtain the spatial heating deviation of the building cluster, and calculate the charging and discharging load according to the above expression to obtain the charging scheduling amount of electric vehicles.

[0107] S403 determines the user load data of each user in the building cluster based on the space heating load, building electricity load, and charging / discharging load.

[0108] In this embodiment of the application, the computer device can control the space heating load. Building electrical load and charge / discharge load By overlaying these data at the same time scale, user load data for each user within the building cluster can be obtained. For example, user load data for each user can be the load curve of a single user.

[0109] S404 determines the user load scheduling amount based on the user load data of each user.

[0110] In one embodiment, S404 includes:

[0111] The aggregated load data of the building cluster is obtained by summing the user load data of each user within the building cluster.

[0112] Based on the user load data and aggregate load data of each user, the individual stress level of each user is determined.

[0113] The user load scheduling amount is determined based on the user load data and individual stress level of each user.

[0114] In this embodiment of the application, the computer device can process the user load data P of each user within the building cluster. Lp Perform a summation operation to obtain the aggregated load data of the building cluster. Therefore, the computer equipment can determine the individual stress level of each user based on the user load data and aggregate load data. This allows us to quantify each user's contribution to the cluster load pressure by calculating each user's ISL.

[0115] It should be noted that, to assess the impact of load management strategies on the overall stress of the distribution network, this application introduces an innovative indicator, Individual Stress Level (ISL), to quantify the contribution of a single user to the overall stress of the cluster / distribution network. ISL is developed based on distribution network feeder performance evaluation indicators and includes a load factor (LF) to measure the utilization rate of generation assets, and a severity index (α1.5), where the severity index reflects the distribution network node P... LP,i The percentage of time exceeding average demand by 150%.

[0116] ISL aims to quantify the impact of the i-th user on the overall stress of the power grid. The ISL is defined by the following formulas (8)-(9):

[0117] (8)

[0118] (9)

[0119] Among them, LF grid LF represents the entire range of combinations. grid-i This represents the combined LF after excluding the i-th agent load, and its calculation method is from P grid Subtract the power requirement P of the i-th agent LP,i . The severity coefficient reflects the extent to which a user's load exceeds their average demand by a certain percentage.

[0120] ISL measures the relative change in local frequency (LF) resulting from the removal of agent i, amplified by its peak time demand. A higher ISL value indicates that the agent has a significant impact on grid instability or inefficiency, meaning that the user is more likely to increase cluster peaks or reduce load factors, thus incurring a higher penalty for overload during optimization. A lower ISL value (or a negative value) indicates that the agent suppresses overall demand fluctuations, meaning that the user has a smoothing effect on the load curve, and the corresponding penalty can be reduced.

[0121] Furthermore, the computer equipment can determine the user load scheduling amount based on the user load data and the individual stress level of each user. Thus, it is possible to... Adjust the demand cost penalty weights. Specifically, the user load scheduling amount is used to impose differentiated demand cost penalties on user loads exceeding normal capacity based on the ISL (Independent Load Level).

[0122] S405 optimizes the spatial heating deviation, charging scheduling, and user load scheduling based on a predetermined objective function to obtain the load management results of the energy system.

[0123] In one embodiment, S405 includes:

[0124] The target value is obtained by substituting the space heating deviation, charging scheduling, and user load scheduling into the objective function.

[0125] Based on the target values, the spatial heating deviation, charging scheduling, and user load scheduling are adjusted, and the target values ​​are recalculated based on the adjusted spatial heating deviation, charging scheduling, and user load scheduling until the target values ​​reach the optimal level, thus obtaining the load management results of the energy system.

[0126] In this embodiment, the computer device can substitute the space heating deviation, charging scheduling amount, and user load scheduling amount into the objective function for calculation to obtain the target value L. For example, the expression of the objective function is shown in equation (10), the power balance relationship is shown in equation (11), and the constraints and penalty terms are shown in equation (12).

[0127] (10)

[0128] (11)

[0129] (12)

[0130] Among them, c en [¥ / kWh] represents the electricity price provided by the utility company. ΔT [￥ / ◦C] represents the equivalent cost of deviating from the preferred temperature setting by 1℃ / hour, where c dc [¥ / kW] is the demand surcharge designed by the utility company. DT[°C] represents the temperature deviation from the preferred set temperature, and the total demand (i.e., the load curve P) is calculated based on this. LP [kW]) from space heating P H Electric vehicle charging P LEV and power base load P EB The sum constitutes the total demand of the portfolio. The total demand for this portfolio is defined as P. grid [kW], NC[kW] represents the normal capacity of the polymer. Indicates the first A penalty term for the charging behavior of electric vehicle users is used to constrain the charging and discharging behavior of electric vehicles in the economic model's predictive control objective function.

[0131] P H The constraints are limited to positive values ​​within the heating capacity (hC) range. The electric vehicle charging power needs to be controlled between a lower limit (lb) and an upper limit (ub), with specific parameters determined by the type of charging infrastructure used. To ensure charging safety, the system needs to implement additional penalty mechanisms: deep discharge (DD) and deep charge (DC) must operate within the limited range of the electric vehicle's total capacity to reduce the number of charge-discharge cycles, and the control range is limited to an interval where the applied voltage is linearly related to the vehicle's remaining capacity. The nPf parameter is used to limit frequent power fluctuations based on the total harmonic distortion level (ε is a threshold parameter), and finally, the SOC is used to control the power output. EV,SP The parameters ensure the integrity of the overnight charging cycle.

[0132] Therefore, based on the target value, the spatial heating deviation, charging scheduling, and user load scheduling can be adjusted to obtain the adjusted spatial heating deviation, charging scheduling, and user load scheduling. The target value is then recalculated based on these adjusted values. In other words, the adjusted spatial heating deviation, charging scheduling, and user load scheduling are used as the new spatial heating deviation, the new charging scheduling, and the new user load scheduling. The process of substituting these values ​​into the target function is repeated until the target value is optimal, yielding the energy system's load management result.

[0133] It should be noted that this application's embodiments optimize energy load management by balancing three core elements: spatial heating deviation, charging scheduling, and user load scheduling. Firstly, the spatial heating deviation ensures thermal comfort by minimizing the deviation from the set temperature; for example, different heating power outputs can be predicted using a thermal model. The indoor temperature in the future time domain is predicted, and the deviation DT between the predicted indoor temperature and the set temperature is calculated. Then, 2) The comfort penalty term is added to formula (10) as the objective function, and a temperature comfort range constraint is set in formula (10), for example... , or equivalently written as Therefore, the solver searches for the optimal control quantity under the constraints of heating power, EV charging and discharging power, and grid capacity. Thus, if the temperature deviation increases, the objective value of the objective function will increase, and the optimizer will tend to choose a heating control strategy that can reduce the temperature deviation. Secondly, the electric vehicle charging scheduling term focuses on optimizing the charging scheduling scheme of electric vehicles and imposes a penalty mechanism for deviations from the ideal charging behavior pattern. Thirdly, the user load scheduling coordination term aims to synchronize the heat load and the electric vehicle load, minimizing conflicts between these demands and ensuring the overall stability of the power grid.

[0134] In this embodiment, through the iterative process of the objective function corresponding to the objective value, the objective function can be solved in the nonlinear optimization part of the solver in the MATLAB environment; and when designing the economic multi-objective programming (eMPC, i.e., the above equations (10)-(12)) in the multi-objective optimization framework, the identification of the optimal strategy can be ensured by carefully selecting the weights, soft constraints and penalty terms. In this way, energy load management can be optimized by balancing the three core elements of space heating deviation, charging scheduling and user load scheduling.

[0135] For example, weights and penalties can be determined as follows: First, the target items such as electricity cost, temperature comfort deviation, EV charging deviation, and demand cost are standardized or normalized in terms of dimensions. Second, hard constraints are set according to user comfort requirements, EV off-site SOC requirements, and grid demand response requirements. Third, conditions that can be slightly violated but incur costs are set as soft constraints, such as temperature deviation, EV not reaching the target SOC, and power fluctuations. Fourth, the weights are adjusted through historical data simulation or sensitivity analysis to achieve a comprehensive optimization of total cost, peak load, and user comfort. For example, during demand response periods, penalties for temperature deviation and demand cost can be increased to prevent the system from exceeding normal capacity; during normal periods, the relevant penalties can be reduced to minimize unnecessary adjustments.

[0136] In one exemplary embodiment, such as Figure 5 As shown, a load management method is provided, applied to computer equipment, including:

[0137] S501, obtain historical load information of the energy system.

[0138] The energy system includes building clusters and electric vehicles, and the historical load information includes temperature information of building clusters, historical electricity consumption information of building clusters, and historical electricity consumption information of electric vehicles.

[0139] S502, evaluate the initial prediction model according to the preset evaluation function, and obtain the evaluation result of the initial prediction model.

[0140] The preset evaluation function includes at least one of root mean square error, goodness of fit, root mean square error coefficient of variation and probability distribution, and the initial prediction model includes an initial thermal model, an initial power load model and an initial electric vehicle prediction model.

[0141] S503, if the evaluation results indicate that the evaluation is passed, the initial thermal model is used as the thermal model, the initial power load model is used as the power load model, and the initial electric vehicle prediction model is used as the electric vehicle prediction model.

[0142] S504 inputs the temperature information of the building cluster into the thermal model for prediction to obtain the spatial heating load of the building cluster.

[0143] S505 inputs the historical electricity consumption information of the building cluster into the power load model for prediction to obtain the building electricity load;

[0144] S506, input the historical electricity consumption information of electric vehicles into the electric vehicle prediction model for prediction, and obtain the charging and discharging load of electric vehicles;

[0145] S507, Determine the spatial heating deviation of a building cluster based on the building's electrical load;

[0146] S508 determines the charging scheduling amount of electric vehicles based on the charging and discharging load;

[0147] S509 determines the user load data of each user in the building cluster based on the space heating load, building electricity load, and charging and discharging load;

[0148] S510 sums up the user load data of each user within the building cluster to obtain the aggregated load data of the building cluster.

[0149] S511, based on the user load data and aggregate load data of each user, determine the individual stress level of each user;

[0150] S512 determines the user load scheduling amount based on the user load data and individual stress level of each user;

[0151] S513, substitute the space heating deviation, charging scheduling amount and user load scheduling amount into the objective function to calculate the target value;

[0152] S514, based on the target value, adjust the space heating deviation, charging scheduling, and user load scheduling, and recalculate the target value based on the adjusted space heating deviation, charging scheduling, and user load scheduling until the target value reaches the optimal value, thus obtaining the load management result of the energy system.

[0153] This application provides a method for coordinated load management of building clusters and electric vehicles. When building clusters and electric vehicles are simultaneously connected to the grid, the method dynamically quantifies the contribution of each user to the aggregated load peak and grid pressure based on the grid demand response signal (i.e., historical load information) and load forecast results (i.e., space heating load, building electricity load, and charging and discharging load). Based on this, the method triggers economic model predictive control coordinated optimization to achieve optimal load scheduling under the grid demand response signal. This avoids the response lag, invalid calculation, and peak superposition problems caused by fixed period optimization or single threshold response in related technologies, thereby reducing peak load and improving grid stability.

[0154] Specifically, firstly, an individual stress level index is proposed to quantify the impact of each user on the grid load factor, which is used to dynamically adjust the load reduction weight in demand response and achieve differentiated demand response responsibility allocation. Secondly, an economic model predictive control objective function is constructed to simultaneously optimize electricity price cost, temperature comfort deviation, and demand cost, unifying the modeling and optimization scheduling of building thermal inertia flexibility and electric vehicle charging / discharging flexibility. Thirdly, the Monte Carlo method is used to probabilistically model the arrival time and remaining power of electric vehicles, improving the robustness of load forecasting. Fourthly, the flexibility potential provided by building thermal inertia is quantified through a thermal model to achieve dynamic scheduling of spatial heating load.

[0155] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0156] Based on the same inventive concept, this application also provides a load management device for implementing the load management method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more load management device embodiments provided below can be found in the limitations of the load management method described above, and will not be repeated here.

[0157] In one exemplary embodiment, such as Figure 6 As shown, a load management device is provided, including: an acquisition module 31, a forecasting module 32, and a load management module 33, wherein:

[0158] The acquisition module 31 is used to acquire historical load information of the energy system, which includes building clusters and electric vehicles.

[0159] The prediction module 32 is used to predict the spatial heating load, building electricity load and electric vehicle charging and discharging load of the building cluster based on the historical load information of the energy system.

[0160] The load management module 33 is used to perform load management on the energy system based on the space heating load, building electricity load and charging / discharging load, and obtain the load management results of the energy system.

[0161] In one embodiment, the load management module 33 includes:

[0162] The first determining unit is used to determine the spatial heating deviation of the building cluster based on the building's electrical load.

[0163] The second determining unit is used to determine the charging scheduling amount of electric vehicles based on the charging and discharging load;

[0164] The third determining unit is used to determine the user load data of each user in the building cluster based on the space heating load, building electricity load and charging and discharging load;

[0165] The fourth determining unit is used to determine the user load scheduling amount based on the user load data of each user;

[0166] The optimization unit is used to optimize the spatial heating deviation, charging scheduling and user load scheduling based on a predetermined objective function, so as to obtain the load management results of the energy system.

[0167] In one embodiment, the fourth determining unit is specifically used for:

[0168] The aggregated load data of the building cluster is obtained by summing the user load data of each user within the building cluster.

[0169] Based on the user load data and aggregate load data of each user, determine the individual stress level of each user;

[0170] The user load scheduling amount is determined based on the user load data and individual stress level of each user.

[0171] In one embodiment, the optimization unit is specifically used for:

[0172] Substitute the spatial heating deviation, charging scheduling, and user load scheduling into the objective function to calculate the target value;

[0173] Based on the target values, the spatial heating deviation, charging scheduling, and user load scheduling are adjusted, and the target values ​​are recalculated based on the adjusted spatial heating deviation, charging scheduling, and user load scheduling until the target values ​​reach the optimal level, thus obtaining the load management results of the energy system.

[0174] In one embodiment, historical load information includes temperature information of the building cluster, historical electricity consumption information of the building cluster, and historical electricity consumption information of electric vehicles; prediction module 32 includes:

[0175] The first prediction unit is used to input the temperature information of the building cluster into the thermal model for prediction, and obtain the spatial heating load of the building cluster.

[0176] The second prediction unit is used to input the historical electricity consumption information of the building cluster into the power load model for prediction, and obtain the building electricity load.

[0177] The third prediction unit is used to input the historical electricity consumption information of electric vehicles into the electric vehicle prediction model for prediction, so as to obtain the charging and discharging load of electric vehicles.

[0178] In one embodiment, the load management device further includes:

[0179] The evaluation module is used to evaluate the initial prediction model according to the preset evaluation function and obtain the evaluation result of the initial prediction model. The preset evaluation function includes at least one of root mean square error, goodness of fit, root mean square error coefficient of variation and probability distribution. The initial prediction model includes the initial thermal model, the initial power load model and the initial electric vehicle prediction model.

[0180] The model determination module is used to use the initial thermal model as the thermal model, the initial power load model as the power load model, and the initial electric vehicle prediction model as the electric vehicle prediction model when the evaluation results indicate that the evaluation is passed.

[0181] Each module in the aforementioned load management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0182] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 1As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a load management method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0183] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0184] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0185] Acquire historical load information for the energy system, which includes building clusters and electric vehicles;

[0186] Based on historical load information of the energy system, predict the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster;

[0187] Based on the space heating load, building electricity load, and charging / discharging load, load management of the energy system is carried out to obtain the load management results of the energy system.

[0188] In one embodiment, load management of the energy system is performed based on the space heating load, building electricity load, and charging / discharging load to obtain the load management result of the energy system. When the processor executes the computer program, it also performs the following steps:

[0189] Determine the spatial heating deviation of the building cluster based on the building's electrical load;

[0190] The charging schedule for electric vehicles is determined based on the charging and discharging load.

[0191] Based on the space heating load, building electricity load, and charging / discharging load, determine the user load data for each user within the building cluster;

[0192] Determine the user load scheduling amount based on the user load data of each user;

[0193] Based on a predetermined objective function, the spatial heating deviation, charging scheduling, and user load scheduling are optimized to obtain the load management results of the energy system.

[0194] In one embodiment, based on the user load data of each user, the user load scheduling amount is determined, and the processor, when executing the computer program, also performs the following steps:

[0195] The aggregated load data of the building cluster is obtained by summing the user load data of each user within the building cluster.

[0196] Based on the user load data and aggregate load data of each user, determine the individual stress level of each user;

[0197] The user load scheduling amount is determined based on the user load data and individual stress level of each user.

[0198] In one embodiment, the spatial heating deviation, charging scheduling, and user load scheduling are optimized based on a predetermined objective function to obtain the load management results of the energy system. When the processor executes the computer program, it also performs the following steps:

[0199] Substitute the spatial heating deviation, charging scheduling, and user load scheduling into the objective function to calculate the target value;

[0200] Based on the target values, the spatial heating deviation, charging scheduling, and user load scheduling are adjusted, and the target values ​​are recalculated based on the adjusted spatial heating deviation, charging scheduling, and user load scheduling until the target values ​​reach the optimal level, thus obtaining the load management results of the energy system.

[0201] In one embodiment, historical load information includes temperature information of the building cluster, historical electricity consumption information of the building cluster, and historical electricity consumption information of electric vehicles; based on the historical load information of the energy system, the spatial heating load of the building cluster, the building electricity load, and the charging and discharging load of electric vehicles are predicted. When the processor executes the computer program, it also performs the following steps:

[0202] The temperature information of the building cluster is input into the thermal model for prediction, and the spatial heating load of the building cluster is obtained.

[0203] Historical electricity consumption information of building clusters is input into the power load model for prediction to obtain building electricity load;

[0204] Historical electricity consumption information of electric vehicles is input into the electric vehicle prediction model for prediction, and the charging and discharging load of electric vehicles is obtained.

[0205] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0206] The initial prediction model is evaluated according to the preset evaluation function to obtain the evaluation result of the initial prediction model. The preset evaluation function includes at least one of root mean square error, goodness of fit, root mean square error coefficient of variation and probability distribution. The initial prediction model includes the initial thermal model, the initial power load model and the initial electric vehicle prediction model.

[0207] If the evaluation results indicate that the evaluation is passed, the initial thermal model will be used as the thermal model, the initial power load model will be used as the power load model, and the initial electric vehicle prediction model will be used as the electric vehicle prediction model.

[0208] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0209] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0210] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0211] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0212] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A load management method, characterized in that, The method includes: Acquire historical load information of the energy system; the energy system includes building clusters and electric vehicles; Based on the historical load information of the energy system, predict the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster; Based on the space heating load, the building electricity load, and the charging and discharging load, load management is performed on the energy system to obtain the load management results of the energy system.

2. The method according to claim 1, characterized in that, The process of performing load management on the energy system based on the space heating load, the building electricity load, and the charging and discharging load, to obtain the load management results of the energy system, includes: The spatial heating deviation of the building cluster is determined based on the building's electrical load. The charging schedule of the electric vehicle is determined based on the charging and discharging load. Based on the space heating load, the building electricity load, and the charging and discharging load, determine the user load data of each user in the building cluster; Based on the user load data of each user, determine the user load scheduling amount; The space heating deviation, the charging scheduling amount, and the user load scheduling amount are optimized based on a predetermined objective function to obtain the load management result of the energy system.

3. The method according to claim 2, characterized in that, The step of determining the user load scheduling amount based on the user load data of each user includes: The user load data of each user within the building cluster are summed to obtain the aggregated load data of the building cluster. Based on the user load data of each user and the aggregate load data, the individual stress level of each user is determined; The user load scheduling amount is determined based on the user load data and individual stress level of each user.

4. The method according to claim 2, characterized in that, The optimization of the spatial heating deviation, the charging scheduling quantity, and the user load scheduling quantity based on a pre-determined objective function yields the load management results of the energy system, including: The target value is obtained by substituting the space heating deviation, the charging scheduling amount, and the user load scheduling amount into the objective function; Based on the target value, the spatial heating deviation, the charging scheduling amount, and the user load scheduling amount are adjusted, and the target value is recalculated based on the adjusted spatial heating deviation, the adjusted charging scheduling amount, and the adjusted user load scheduling amount until the target value reaches the optimal value, thus obtaining the load management result of the energy system.

5. The method according to any one of claims 1-4, characterized in that, The historical load information includes the temperature information of the building cluster, the historical electricity consumption information of the building cluster, and the historical electricity consumption information of the electric vehicles; the step of predicting the spatial heating load, building electricity load, and charging / discharging load of the building cluster based on the historical load information of the energy system includes: The temperature information of the building cluster is input into the thermal model for prediction to obtain the spatial heating load of the building cluster. The historical electricity consumption information of the building cluster is input into the power load model for prediction to obtain the building's electricity load; The historical electricity consumption information of the electric vehicle is input into the electric vehicle prediction model for prediction, and the charging and discharging load of the electric vehicle is obtained.

6. The method according to claim 5, characterized in that, The method further includes: The initial prediction model is evaluated according to a preset evaluation function to obtain the evaluation result of the initial prediction model; the preset evaluation function includes at least one of root mean square error, goodness of fit, root mean square error coefficient of variation and probability distribution; the initial prediction model includes an initial thermal model, an initial power load model and an initial electric vehicle prediction model. If the evaluation result indicates that the evaluation is passed, the initial thermal model is used as the thermal model, the initial power load model is used as the power load model, and the initial electric vehicle prediction model is used as the electric vehicle prediction model.

7. A load management device, characterized in that, The device includes: The acquisition module is used to acquire historical load information of the energy system, which includes building clusters and electric vehicles. The prediction module is used to predict the spatial heating load, building electricity load, and electric vehicle charging and discharging load of the building cluster based on the historical load information of the energy system. The load management module is used to perform load management on the energy system based on the space heating load, the building electricity load, and the charging and discharging load, and obtain the load management result of the energy system.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images