Virtual power plant path optimization system and method based on electricity-carbon combination model

Abstract

The invention discloses a virtual power plant path optimization system and method based on an electricity-carbon combination model, belongs to the technical field of virtual power plants, and aims to solve the problem of how to realize carbon emission minimization while ensuring stable operation of a power grid. The method comprises the following steps: collecting target data in real time through interfaces of power generation equipment, energy storage equipment, a load end and carbon emission monitoring equipment; performing data preprocessing on the collected target data, analyzing an energy consumption mode and a carbon emission trend based on the preprocessed target data, predicting a future power demand and a carbon emission level, and judging whether an abnormal trend exists or not; constructing a power-carbon combination model, and optimizing a power production path by using an objective function and constraint conditions; when an abnormal trend is detected, a scheduling scheme is formulated by optimizing a power production path; and executing the scheduling scheme, scheduling the power resources and the power generation equipment, and controlling coordinated operation among the power generation unit, the energy storage equipment and the power grid load in the virtual power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plants, and more specifically, to a virtual power plant path optimization system and method based on an electricity-carbon integration model. Background Art

[0002] Virtual power plants need to participate in competition in multiple markets, including: the electric energy market, the electricity spot market, and the ancillary service market. In addition, virtual power plants also need to coordinate and dispatch among different types of entities to cope with complex market rules and changes. How to optimize resource allocation in these diversified markets to ensure the balance between economy and low-carbon goals has become a key issue in the development of virtual power plants. In order to effectively achieve market participation and operation efficiency under the dual-carbon goal, virtual power plants need to formulate appropriate optimization paths based on the electricity-carbon integration model. The core of path optimization lies in how to comprehensively consider various factors such as power supply, demand response, energy storage dispatch, and carbon emission constraints, and use advanced algorithms and big data analysis technologies to achieve the optimal allocation of resources. In this process, the optimization method of virtual power plants not only needs to consider market participation strategies, but also needs to be combined with the actual needs of energy transformation to promote the application and development of low-carbon technologies. By establishing a scientific optimization path and implementation plan, virtual power plants can play a greater role in the electricity market and promote energy transformation and the realization of the dual-carbon goal.

[0003] The Chinese patent application with the publication number CN115422728A discloses a virtual power plant optimization control system based on robust optimization of stochastic programming, including a virtual power plant optimization control module for economic and grid operation safety, a virtual power plant stochastic programming optimization control module for stochastic renewable energy, and a virtual power plant adaptive robust optimization control module for stochastic renewable energy. The virtual power plant optimization control module for economic and grid operation safety includes a virtual power plant economic dispatch model and a virtual power plant safety dispatch model.

[0004] Although the prior art considers the coordinated operation control method among distributed power sources, energy storage, and demand-side users in the region under the condition of stochastic renewable energy, and the large power grid presents stable power output characteristics under intelligent collaborative regulation and decision support, realizing the safe and efficient utilization of new energy power. It still fails to solve the problem of how to minimize carbon emissions while ensuring the stable operation of the power grid. Therefore, in order to overcome these limitations, the present invention proposes a virtual power plant path optimization system and method based on an electricity-carbon integration model. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technologies, the purpose of the present invention is to provide a virtual power plant path optimization system and method based on an electricity-carbon combination model, which solves the problem of how to minimize carbon emissions while ensuring the stable operation of the power grid. Based on the collaborative work of four core modules, it realizes the high efficiency and low carbon of power production, improves the energy utilization efficiency, reduces environmental pollution, and promotes the sustainable development of the power industry through refined management and optimized decision-making.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A virtual power plant path optimization system based on an electricity-carbon combination model, comprising: a data acquisition module, a data processing module, a path optimization module, and a scheduling control module;

[0008] The data acquisition module is used to collect target data in real time through interfaces with power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment. The target data includes: power data, carbon emission data, environmental data, and market data;

[0009] The data processing module is used to perform data preprocessing on the collected target data, analyze the energy consumption pattern and carbon emission trend based on the preprocessed target data, predict future power demand and carbon emission levels, and determine whether there is an abnormal trend;

[0010] The path optimization module is used to construct an electricity-carbon combination model with the goal of balancing power production and carbon emissions, optimize the power production path using the objective function and constraint conditions, and formulate a scheduling plan by optimizing the power production path when an abnormal trend is detected;

[0011] The scheduling control module is used to execute the scheduling plan, schedule power resources and power generation equipment, and control the coordinated operation among power generation units, energy storage equipment, and grid loads within the virtual power plant.

[0012] Specifically, the construction of the electricity-carbon combination model includes:

[0013] Construct the objective function of the electricity-carbon combination model to achieve a balance between power production and carbon emissions, introduce the factor of power production cost, divide the objective function into multiple levels, and the expression of the objective function is as follows:

[0014]

[0015] Among them, C carbon,t is the carbon emission cost at time t, which is determined by the type and usage of fuel, P power,t is the power production at time t, expressed as the required power generation power, C cost,t is the power production cost at time t, and α, β, and γ are weighting coefficients;

[0016] The constraint conditions for constructing the electricity-carbon combination model include: power plant load constraint, equipment performance constraint, carbon emission constraint, energy storage constraint, and power plant stability constraint.

[0017] Specifically, the specific steps for constructing the electricity-carbon combination model also include:

[0018] The expression of the power plant load constraint is as follows:

[0019]

[0020] where P total,t is the total electricity production at time t, is the predicted value of the electricity demand at time t, N is the number of power generation equipment, and P i,t is the electricity production of the i-th power generation equipment at time t;

[0021] The expression of the equipment performance constraint is as follows:

[0022]

[0023] where P min i,t and P max i,t are the minimum and maximum output powers of the i-th power generation equipment at time t;

[0024] The expression of the carbon emission constraint is as follows:

[0025]

[0026] where f i is the carbon emission factor of the i-th power generation equipment, which is set according to the fuel type and equipment efficiency, and E limit is the total carbon emission limit;

[0027] The expression of the energy storage constraint is as follows:

[0028]

[0029] where E charge,t and E discharge,t are the charging and discharging amounts of the energy storage equipment at time t, E max is the maximum capacity of the energy storage equipment, and δ discharge is the discharging efficiency, with a value between [0, 1];

[0030] The expression of the power plant stability constraint is as follows:

[0031]

[0032] where ζ t is the power grid frequency at time t, and vt is the grid voltage at time t, ∈ freq and ∈ voltage are the maximum fluctuation values of the grid frequency and the grid voltage.

[0033] Specifically, the data processing module includes a preprocessing unit and a pattern recognition unit;

[0034] The preprocessing unit is configured with a data cleaning strategy, which is used to clean the collected target data, remove outliers, fill in missing data, and perform data conversion and data integration operations;

[0035] The pattern recognition unit is configured with a trend analysis strategy, which is used to identify potential power consumption trends and carbon emission trends by analyzing historical data and real-time collected target data, so as to predict future power demand and carbon emission levels and judge whether there are abnormal trends.

[0036] Specifically, the specific steps of the trend analysis strategy include:

[0037] According to the power path of the virtual power plant, access the operating power generation equipment through the virtual power plant platform to obtain the historical power production data of each power generation equipment;

[0038] Perform statistical analysis on the historical power production data, identify the key factors affecting the power production of each power generation equipment, and predict the power production of each power generation equipment. The power production prediction model is as follows:

[0039]

[0040] W t = λ1T t + λ2F t + λ2Y t

[0041] Where, is the predicted value of the power production of the i-th power generation equipment at time t, M1 is the amount of historical data used for power production prediction, ψ i is the failure rate of the i-th power generation equipment, P i,(t-j) is the power production of the i-th power generation equipment at time t-j, W t is the weather factor at time t, including temperature T t 、wind speed F t and solar radiation intensity Y t , η1 and η2 are the non-negative weights of the failure rate of the power generation equipment and the weather factor respectively, and λ1, λ2 and λ3 are the non-negative weighting coefficients of temperature, wind speed and solar radiation intensity in the weather factor;

[0042] Obtain historical electricity demand data and conduct medium- and short-term forecasts for electricity demand. The electricity demand forecasting model is as follows:

[0043]

[0044] Among them, is the predicted value of electricity demand at time t, μ0 is the constant term, M3 is the order of the non-seasonal autoregressive term, is the parameter of the non-seasonal autoregressive term at time q1, is the electricity demand at time t-q1, M4 is the order of the non-seasonal moving average term, is the parameter of the non-seasonal moving average term, k(t-q2) is the residual at time t-q2, M5 is the order of the seasonal autoregressive term, is the seasonal parameter of the seasonal autoregressive term, Γ is the seasonal period, is the electricity demand at time t-q3Γ, τ t is the residual term at time t.

[0045] Specifically, the specific steps of the trend analysis strategy also include:

[0046] Compare the predicted value of electricity demand with the available electricity production capacity, where the available electricity production capacity includes the predicted value of the electricity production of power generation equipment and the electricity value of energy storage equipment, and evaluate the potential supply-demand gap. The calculation formula of the supply-demand gap is as follows:

[0047]

[0048] Among them, is the supply-demand gap at time t, is the predicted value of electricity demand at time t, is the sum of the predicted values of the electricity production of power generation equipment at time t;

[0049] Configure the electricity threshold. If the supply-demand gap at time t is less than the electricity threshold, it indicates that there is insufficient electricity production. If the supply-demand gap at time t is greater than the sum of the electricity threshold and the electricity quantity of the energy storage equipment at time t, it indicates that there is excessive electricity production. Otherwise, the electricity supply and demand are normal, that is:

[0050]

[0051] Among them, T PD is the electricity threshold, is the electricity quantity of the energy storage equipment at time t-1. When S t takes 1, it indicates that there is insufficient electricity production. When S t takes 2, it indicates that the electricity supply and demand are normal. When S t takes 3, it indicates that there is excessive electricity production.

[0052] Specifically, the specific steps of the trend analysis strategy further include:

[0053] When the available power production capacity meets the future power demand forecast, that is, when the power supply and demand are normal or there is an oversupply of power production, obtain the carbon emission factor according to the type of power generation equipment, evaluate the carbon emissions of different types of power generation equipment, and combine the power production data of the power generation equipment to obtain the carbon emission trend in the power production process of the current virtual power plant's power path, and predict the carbon emissions, that is:

[0054]

[0055] Wherein, is the predicted value of the carbon emissions at time t, N is the number of power generation equipment, is the predicted value of the power production of the i-th power generation equipment at time p, f i is the carbon emission factor of the i-th power generation equipment, M2 is the amount of historical data used for carbon emission prediction, ω p is the non-negative weight coefficient of the carbon emissions at time p, ∈ t is the white noise error at time t;

[0056] Configure a carbon emission threshold, and judge whether the carbon emissions meet the compliance target. If the predicted value of the carbon emissions at time t is greater than the carbon emission threshold, the carbon emission compliance target is not met, otherwise the carbon emission compliance target is met;

[0057] If there is insufficient power production, oversupply of power production, or non-compliance of carbon emissions in the power production path, mark the abnormal trend of the power production path and notify relevant personnel through an abnormal warning.

[0058] Specifically, the path optimization module includes a model construction unit and a scheduling optimization unit;

[0059] The model construction unit is configured with an electricity-carbon combination strategy, which is used to transform the trade-off relationship between power production and carbon emissions into a mathematical programming problem by constructing an electricity-carbon combination model, so as to find the best balance point between power production and carbon emissions, and comply with carbon emission restrictions while meeting the grid load demand;

[0060] The scheduling optimization unit is configured with a dynamic scheduling scheme, which is used to obtain an optimized power production path through the electricity-carbon combination model when an abnormal trend is detected in the power production path, so as to arrange the start and stop times of the power generation equipment on the premise of ensuring the stable operation of the virtual power grid.

[0061] Specifically, the specific steps of the dynamic scheduling scheme include:

[0062] When there is an abnormal trend in the power production path, according to the predicted value of power demand, recalculate and optimize the power production path through the power-carbon combination model to obtain the power production plan;

[0063] Obtain the power production volume of each power generation device at time t and the carbon emission at time t from the power production plan;

[0064] Configure deviation thresholds, including upper deviation threshold and lower deviation threshold. According to the actual value of power demand, optimize the power production plan, calculate the cumulative deviation between the predicted value and the actual value of power demand. When the cumulative deviation is greater than the upper deviation threshold, it indicates that the predicted value of power demand exceeds the actual value of power demand, and there is potential power surplus in the optimized power production path; when the cumulative deviation is less than the lower deviation threshold, it indicates that the predicted value of power demand is less than the actual value of power demand, and there is potential power shortage in the optimized power production path;

[0065] When it is detected that there is potential power surplus in the optimized power production path, obtain the power generation device with the largest carbon emission factor in the optimized power production path and reduce its power production volume;

[0066] When it is detected that there is potential power shortage in the optimized power production path, obtain the power generation device with the smallest carbon emission factor in the optimized power production path and increase its power production volume.

[0067] A virtual power plant path optimization method based on the power-carbon combination model includes the following steps:

[0068] Step S1: Real-time collect target data through the interfaces with power generation devices, energy storage devices, load terminals, and carbon emission monitoring devices;

[0069] Step S2: Perform data preprocessing on the collected target data, analyze the energy consumption pattern and carbon emission trend based on the preprocessed target data, predict the future power demand and carbon emission level, and determine whether there is an abnormal trend;

[0070] Step S3: Take balancing power production and carbon emission as the goal, construct a power-carbon combination model, and optimize the power production path using the objective function and constraint conditions;

[0071] Step S4: When an abnormal trend is detected, formulate a scheduling plan by optimizing the power production path to maximize energy efficiency and reduce carbon emissions;

[0072] Step S5: Execute the scheduling plan, dispatch power resources and power generation devices, and control the coordinated operation among the power generation units, energy storage devices, and grid loads in the virtual power plant.

[0073] The beneficial effects of the present invention:

[0074] 1. By constructing an electric-carbon coupling model, finding the optimal balance point between power generation and carbon emissions, not only considering the power generation cost but also introducing the carbon emission cost, enables compliance with carbon emission limits while meeting the grid load demand. By optimizing the power generation path, carbon emissions can be effectively reduced while maintaining or improving energy utilization efficiency, which is of great significance for achieving green and low-carbon power generation.

[0075] 2. By real-time collecting and processing target data, including power data, carbon emission data, environmental data, and market data, provides strong support for the stable operation of the power grid. The data processing module can identify potential power consumption trends and carbon emission trends, predict future power demand and carbon emission levels, thus helping grid operators formulate countermeasures in advance.

[0076] 3. By optimizing the scheduling scheme of the power generation path, improving the utilization rate of renewable energy, which can not only reduce the dependence on traditional fossil fuels and lower carbon emissions but also promote the development of the renewable energy industry. In addition, the scheduling control module can execute the scheduling scheme, coordinate the operation between power generation units, energy storage devices, and grid loads, ensuring the stability and reliability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 is a schematic structural diagram of a virtual power plant path optimization system based on an electric-carbon coupling model;

[0078] Figure 2 is a flowchart of the specific steps of a trend analysis strategy;

[0079] Figure 3 is a flowchart of the specific steps of carbon emission assessment;

[0080] Figure 4 is a schematic diagram of the constraint conditions of an electric-carbon coupling model;

[0081] Figure 5 is a flowchart of the specific steps of a dynamic scheduling scheme;

[0082] Figure 6 is a flowchart of a virtual power plant path optimization method based on an electric-carbon coupling model. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0083] Example 1

[0084] Please refer to Figure 1 , this example introduces a virtual power plant path optimization system based on an electric-carbon coupling model, including: a data collection module, a data processing module, a path optimization module, and a scheduling control module;

[0085] The data acquisition module is used to collect target data in real time through interfaces with power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment. The target data includes: power data, carbon emission data, environmental data, and market data;

[0086] Among them, the power data includes power generation, consumption, and storage; the carbon emission data is the calculated real-time carbon emissions based on the carbon emission coefficients of each power generation method; the environmental data includes temperature, humidity, wind speed, and light, which affect the power generation efficiency of renewable energy; the market data includes power market electricity prices and carbon market price fluctuations;

[0087] The data processing module is used to perform data preprocessing on the collected target data, analyze the energy consumption pattern and carbon emission trend based on the preprocessed target data, predict future power demand and carbon emission levels, and determine whether there is an abnormal trend;

[0088] Among them, data preprocessing includes data cleaning, data denoising, filling missing values, data standardization, and data integration;

[0089] The path optimization module is used to build an electricity-carbon combination model with the goal of balancing power production and carbon emissions, optimize the power production path using the objective function and constraint conditions, and formulate a scheduling plan by optimizing the power production path when an abnormal trend is detected, so as to maximize energy efficiency and reduce carbon emissions;

[0090] The scheduling control module is used to execute the scheduling plan, dispatch power resources and power generation equipment, and control the coordinated operation among the power generation units, energy storage equipment, and grid load in the virtual power plant.

[0091] In this embodiment, the data acquisition module realizes the real-time acquisition of various target data through the interfaces with power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment. The connected devices can obtain data through wireless networks, industrial protocols, etc. The acquisition of power data includes collecting power generation data from power generation equipment, collecting power consumption from load terminal equipment to monitor the change of power demand, and collecting storage data from energy storage equipment, including the current energy storage state and battery charge and discharge conditions. The acquisition of carbon emission data: Calculate the real-time carbon emission according to the carbon emission coefficients of different power generation methods. Exemplary, the carbon emission coefficient of a coal-fired power plant is 0.9 kilograms of carbon dioxide per kilowatt-hour. Then, by monitoring the real-time power generation of the power plant, its carbon emission can be calculated. The acquisition of environmental data: Meteorological data such as temperature, humidity, wind speed, and light are obtained through installed sensors. The acquisition of market data: Obtain real-time electricity price and carbon market price fluctuation information from the power market and carbon market through API interfaces to help evaluate the market supply and demand situation and the fluctuation of carbon emission costs, so as to formulate corresponding dispatching decisions. Preprocess the acquired target data and perform subsequent analysis and prediction. First is data preprocessing: including data cleaning: eliminating invalid data and correcting incorrect data. Exemplary, eliminating outliers caused by sensor failures or data transmission problems; data denoising: filtering environmental data to remove the noise impact brought by short-term fluctuations; filling missing values: using interpolation methods or machine learning algorithms to fill missing data; data standardization: standardizing data from different sources to ensure that the data is analyzed under the same dimension and avoid the influence of different units or magnitudes; data integration: integrating data from different sources to ensure data integrity. Exemplary, integrating the power production data and carbon emission data of different power plants into a unified data set to handle the inconsistency problems in multi-source data. Analyze the energy consumption pattern of the target data after data preprocessing, predict the future carbon emission trend based on historical carbon emission data and current power production methods, and identify situations that may be close to the threshold. Judge whether the deviation between power demand and carbon emission is too large. If the actual power generation is significantly lower than the demand, or the carbon emission level is close to the set threshold, a warning is issued to indicate an abnormal trend. By establishing an optimization model based on the balance of power production and carbon emission, formulate an optimization plan to maximize energy production efficiency and reduce carbon emission. The model includes: objective function: minimizing carbon emissions while meeting power demand; constraint conditions: including the operating capacity of power generation equipment, charging / discharging limits of energy storage equipment, market electricity price, and carbon emission cost, etc. Use linear programming or non-linear programming algorithms to solve the optimal power production path. Dynamically adjust the power production strategy according to the changes in environmental data and market data. Exemplary, if the wind speed is high and the electricity price is low, give priority to using wind power generation; if the electricity price is high and the carbon market price rises, it may tend to use low-carbon renewable energy.According to the calculated power production path, a dispatching plan is formulated, including the coordination relationship between each power generation unit, energy storage equipment and grid load, to ensure that power production matches demand and carbon emissions are minimized. Based on real-time data and forecast results, the operation of power generation equipment and energy storage equipment is controlled to ensure efficient and smooth operation of the power system. When it is detected that the deviation between power demand and production is too large, or carbon emissions are close to the set threshold, the system will automatically detect and issue an alarm to remind operators to take measures. If abnormal trends occur, the power production plan is adjusted according to the optimization model, including: if power demand exceeds expectations, start backup power generation equipment or release power from the energy storage system to avoid power shortages. If the carbon emission level is too high, low-carbon power generation methods such as wind, solar or hydropower are prioritized, reduce the proportion of coal and natural gas power generation, and coordinate the operating status between each power generation unit, energy storage equipment and grid load in the virtual power plant. Through real-time monitoring and dynamic adjustment, the stability of power supply and the maximization of energy efficiency are ensured.

[0092] Preferably, the data processing module includes a preprocessing unit and a pattern recognition unit. The preprocessing unit is configured with a data cleaning strategy. The data cleaning strategy is used to clean the collected target data, remove outliers, fill in missing data, and perform data conversion and data integration operations to ensure data quality, so as to effectively improve the accuracy and reliability of subsequent modeling and analysis. The pattern recognition unit is configured with a trend analysis strategy. The trend analysis strategy is used to identify potential power production trends and carbon emission trends by analyzing historical data and target data collected in real time, and predict future power demand and carbon emission levels, and then determine whether there are abnormal trends or potential risks. Through dynamic analysis of data, possible demand deviations or carbon emission anomalies can be identified in real time, thereby providing decision support for the path optimization module and achieving more accurate scheduling and resource optimization.

[0093] See also Figure 2 , preferably, the specific steps of the trend analysis strategy include:

[0094] According to the power path of the virtual power plant, the operating power generation equipment is connected through the virtual power plant platform to obtain the historical power production data of each power generation equipment. The power production data includes the equipment power generation, equipment operating hours, equipment load fluctuations, and equipment failure information; the power generation acquisition includes traditional power generation equipment, renewable energy power generation equipment, and energy storage equipment; by connecting to the virtual power plant platform and obtaining the historical power production data of various types of power generation equipment, a comprehensive understanding of the operation status of each power generation equipment can be achieved.

[0095] Statistically analyze historical power production data to identify the key factors affecting the power production of each power generation device. The key factors include weather factors, equipment failure rates, and historical power production volumes. Then, predict the power production volume for each power generation device. The power production volume prediction model is as follows:

[0096]

[0097] W t = λ1T t + λ2F t + λ2Y t

[0098] Where, is the predicted value of the power production volume of the i-th power generation device at time t, M1 is the amount of historical data used for power production volume prediction, ψ i is the failure rate of the i-th power generation device, P i,(t-j) is the power production volume of the i-th power generation device at time t - j, W t is the weather factor at time t, including temperature T t 、wind speed F t and solar radiation intensity Y t , η1 and η2 are the non - negative weights of the failure rate of the power generation device and the weather factor respectively, and λ1, λ2 and λ3 are the non - negative weighting coefficients of temperature, wind speed and solar radiation intensity in the weather factor; By constructing the power production volume prediction model, predict the future power production of each power generation device, and provide more accurate power production prediction values according to factors such as historical data, weather conditions, and equipment status, so as to optimize power dispatching and planning.

[0099] Obtain historical power demand data and conduct medium - and short - term predictions on power demand. The power demand prediction model is as follows:

[0100]

[0101] Where, is the predicted value of the power demand at time t, μ0 is the constant term, M3 is the order of the non - seasonal autoregressive term, indicating the influence related to the lag values of the previous M3 time points, is the parameter of the non - seasonal autoregressive term at time q1, is the power demand at time t - q1, M4 is the order of the non - seasonal moving average term, indicating the influence related to the prediction residuals of the previous M4 time points, is the parameter of the non - seasonal moving average term, κ(t - q2) is the residual at time t - q2, M5 is the order of the seasonal autoregressive term, indicating the influence related to the previous M5 seasonal cycles, is the seasonal parameter of the seasonal autoregressive term, and Γ is the seasonal period, representing the period length of a complete season. is the electricity demand at time t - q3Γ, and τ t is the residual term at time t, that is, the prediction error of the model; collect historical data of electricity demand and predict medium - and short - term electricity demand through an electricity demand prediction model to predict the electricity demand at a certain future time or period, so as to provide a basis for electricity production and scheduling.

[0102] Compare the predicted value of electricity demand with the available electricity production capacity, where the available electricity production capacity includes the predicted value of the electricity production of power generation equipment and the electricity value of energy storage equipment, and evaluate the potential supply - demand gap. The calculation formula of the supply - demand gap is as follows:

[0103]

[0104] where, is the supply - demand gap at time t, is the predicted value of electricity demand at time t, is the sum of the predicted values of the electricity production of power generation equipment at time t; calculate the supply - demand gap at the current time by comparing the predicted value of electricity demand with the available electricity production capacity. If the supply - demand gap is too large, additional power scheduling or energy storage strategies need to be adopted to balance the supply and demand.

[0105] Configure an electricity threshold. If the supply - demand gap at time t is less than the electricity threshold, it indicates that there is insufficient electricity production. If the supply - demand gap at time t is greater than the sum of the electricity threshold and the electricity quantity of the energy storage equipment at time t, it indicates that there is excessive electricity production. Otherwise, the electricity supply and demand are normal, that is:

[0106]

[0107] where, T PD is the electricity threshold, is the electricity quantity of the energy storage equipment at time t - 1. When S t takes 1, it indicates that there is insufficient electricity production. When S t takes 2, it indicates that the electricity supply and demand are normal. When S t takes 3, it indicates that there is excessive electricity production; according to the set electricity threshold, judge whether there is a situation of insufficient electricity production, excessive electricity production or normal electricity supply and demand, so as to help judge whether the power system is in a balanced state and whether it is necessary to adjust power production or energy storage strategies.

[0108] Please refer to Figure 3, when the available power production capacity meets the future power demand forecast, that is, when the power supply and demand are normal or the power production is in surplus, obtain the carbon emission factor according to the type of power generation equipment, evaluate the carbon emissions of different types of power generation equipment, and combine the power production data of the power generation equipment to obtain the carbon emission trend in the power production process of the power path of the current virtual power plant, and predict the carbon emissions, that is:

[0109]

[0110] Among them, is the predicted value of the carbon emissions at time t, N is the number of power generation equipment, is the predicted value of the power production of the i-th power generation equipment at time p, f i is the carbon emission factor of the i-th power generation equipment, M2 is the amount of historical data used for carbon emission prediction, ω p is the non-negative weight coefficient of the carbon emissions at time p, ∈ t is the white noise error at time t; on the premise of power supply and demand balance, based on the carbon emission factors and power production data of different power generation equipment, evaluate the carbon emissions of the current virtual power plant and predict the future carbon emission trend to help the virtual power plant understand the carbon emission status in real time and ensure that its operation meets environmental protection requirements.

[0111] Configure a carbon emission threshold to judge whether the carbon emissions meet the compliance target. If the predicted value of the carbon emissions at time t is greater than the carbon emission threshold, the carbon emission compliance target is not met, otherwise the carbon emission compliance target is met. By configuring the carbon emission threshold to judge whether the carbon emissions at the current moment meet the environmental protection compliance target, it helps to ensure the green operation of the virtual power plant.

[0112] If there is insufficient power production, surplus power production, or the carbon emissions do not meet the compliance target in the power production path, then mark the abnormal trend of the power production path and notify relevant personnel through an abnormal warning.

[0113] Preferably, the path optimization module includes a model construction unit and a scheduling optimization unit. The model construction unit is configured with an electricity-carbon combination strategy. The electricity-carbon combination strategy is used to transform the trade-off relationship between power production and carbon emissions into a mathematical programming problem by constructing an electricity-carbon combination model to find the best balance point between power production and carbon emissions, while meeting the grid load demand and complying with carbon emission restrictions; the scheduling optimization unit is configured with a dynamic scheduling plan. The dynamic scheduling plan is used to obtain an optimized power production path through the electricity-carbon combination model when an abnormal trend is detected in the power production path, so as to reasonably arrange the start and stop times of power generation equipment on the premise of ensuring the stable operation of the virtual power grid, so as to improve the overall efficiency and economy of the system.

[0114] Preferably, the construction of the electricity-carbon combination model includes:

[0115] Construct the objective function of the electric-carbon coupling model to balance power production and carbon emissions, introduce the factor of power production cost, divide the objective function into multiple levels, and the expression of the objective function is as follows:

[0116]

[0117] Among them, C carbon,t is the carbon emission cost at time t, which is determined by the type and usage of fuel, that is:

[0118]

[0119] P power,t is the power production at time t, expressed as the required power generation, that is:

[0120]

[0121] C cost,t is the power production cost at time t, including fuel cost and operation and maintenance cost, that is:

[0122]

[0123] Among them, P i,t is the power production of the i-th power generation device at time t, f i is the carbon emission factor of the i-th power generation device, N is the number of power generation devices, Cost i is the unit power production cost of the i-th power generation device; α, β, and γ are weighting coefficients used to adjust the importance of carbon emission cost, power production, and power production cost in the objective function, and the value range is [0, 1]; by adjusting the weighting coefficients, the trade-off between carbon emission and power production can be flexibly adjusted, and the power production plan can be optimized according to actual needs to achieve the emission reduction goal while ensuring the stability and economy of power supply.

[0124] Please refer to Figure 4 , for the constraint conditions for constructing the electric-carbon coupling model, including: power plant load constraint, equipment performance constraint, carbon emission constraint, energy storage constraint, and power plant stability constraint; the power plant load constraint ensures that power production can meet the real-time load demand and avoids power shortage or surplus. The equipment performance constraint ensures that the operation of various power generation devices is within a safe range and prevents equipment overload or inefficient operation. The carbon emission constraint ensures that the total carbon emission does not exceed the specified limit and helps to achieve environmental protection goals. The energy storage constraint ensures the efficient utilization of energy storage devices and improves the flexibility and reliability of the system. The power plant stability constraint ensures the safety and stability of the power grid operation and reduces the risk of power outages and voltage fluctuations.

[0125] Power plant load constraint, which is used to ensure that power production meets the load demand in each time period. The expression of the power plant load constraint is as follows:

[0126]

[0127] Where, P total,t is the total power production at time t, is the predicted value of the power demand at time t, N is the number of power generation devices, and P i,t is the power production of the i-th power generation device at time t;

[0128] Device performance constraint, which is used to ensure that the power production of each power generation device must be between its minimum and maximum output powers. The expression of the device performance constraint is as follows:

[0129]

[0130] Where, P min i,t and P max i,t are the minimum and maximum output powers of the i-th power generation device at time t;

[0131] Carbon emission constraint, which is used to restrict carbon emissions to meet the total limit in order to comply with the requirements of regulations or market mechanisms. The expression of the carbon emission constraint is as follows:

[0132]

[0133] Where, f i is the carbon emission factor of the i-th power generation device, which is set according to the fuel type and device efficiency, and E limit is the total carbon emission limit;

[0134] Energy storage constraint, which is used to restrict the charging and discharging states of energy storage devices to meet the capacity and efficiency requirements of energy storage devices. The expression of the energy storage constraint is as follows:

[0135]

[0136] Where, E charge,t and E discharge,t are the charging amount and discharging amount of the energy storage device at time t, E max is the maximum capacity of the energy storage device, and δ discharge is the discharging efficiency, with a value between [0, 1];

[0137] Power plant stability constraint, which is used to ensure the safe and stable operation of the power grid and ensure that the power grid frequency and voltage are within the allowable fluctuation range. The expression of the power plant stability constraint is as follows:

[0138]

[0139] where ζ t is the grid frequency at time t, v t is the grid voltage at time t, ∈ freq and ∈ voltage are the maximum fluctuation values of the grid frequency and the grid voltage.

[0140] Combining the objective function and constraints of the electricity-carbon coupling model, the entire electricity-carbon coupling optimization problem is expressed as a mathematical programming problem. Solving this mathematical programming problem uses mathematical optimization methods, including linear programming, mixed-integer linear programming, non-linear programming, etc., to effectively find the best balance between power production and carbon emissions, meet the grid load demand, while complying with carbon emission regulations to ensure economy and sustainability.

[0141] Solve the objective function and satisfy all constraints, and output the power production plan, including:

[0142] Optimal power production: The optimal values for each time t and each power generation device, which not only meet the grid load demand but also consider the minimization of carbon emissions;

[0143] Optimal carbon emissions: On the premise of meeting the grid demand, the carbon emissions are minimized and do not exceed the specified maximum limit.

[0144] Please refer to Figure 5 , preferably, the specific steps of the dynamic scheduling plan include:

[0145] When there is an abnormal trend in the power production path, according to the predicted value of power demand, recalculate the optimized power production path through the electricity-carbon coupling model to obtain the power production plan; The optimization process uses the electricity-carbon coupling model to generate a new power production plan by balancing the power production volume and carbon emissions.

[0146] Obtain the power production volume of each power generation device at time t and the carbon emissions at time t from the power production plan; The optimized power production plan includes the power production volume of each power generation device at different time points, and also provides the carbon emissions of these devices at each moment, which helps to monitor the power production efficiency and carbon emission level in real time.

[0147] Configure deviation thresholds, including upper and lower deviation thresholds. According to the actual value of power demand, optimize the power production plan, calculate the cumulative deviation between the predicted value of power demand and the actual value of power demand. When the cumulative deviation is greater than the upper deviation threshold, it indicates that the predicted value of power demand exceeds the actual value of power demand, and there is potential power surplus in the optimized power production path; when the cumulative deviation is less than the lower deviation threshold, it indicates that the predicted value of power demand is less than the actual value of power demand, and there is potential power shortage in the optimized power production path. Set the upper and lower deviation thresholds to monitor the deviation between the actual value and the predicted value of power demand. When the cumulative deviation between the actual demand and the predicted demand exceeds the upper deviation threshold, it indicates that the prediction is too high, which may lead to power surplus; on the contrary, if the cumulative deviation is less than the lower deviation threshold, it indicates that the prediction is too low, which may lead to power shortage.

[0148] When it is detected that there is potential power surplus in the optimized power production path, obtain the power generation equipment with the largest carbon emission factor in the optimized power production path and reduce its power production volume, that is:

[0149]

[0150] where, P * i,t is the power production volume of the i-th optimized power generation equipment at time t when there is power surplus, and P max,t is the power production volume of the power generation equipment with the largest carbon emission factor in the optimized power production path at time t. is an optimization parameter used to control the amplitude of optimizing power production, and its value range is [0, 1]; when a potential situation of power surplus is detected, the power generation equipment with the largest carbon emission factor in the optimized path will be selected and its power production volume will be reduced to effectively control carbon emissions and prevent waste of resources caused by power surplus.

[0151] When it is detected that there is potential power shortage in the optimized power production path, obtain the power generation equipment with the smallest carbon emission factor in the optimized power production path and increase its power production volume, that is:

[0152]

[0153] where, P · i,t is the power production volume of the i-th optimized power generation equipment at time t when there is power shortage, and P min,t is the power production volume of the power generation equipment with the smallest carbon emission factor in the optimized power production path at time t. is an optimization parameter used to control the amplitude of optimizing power production, with a value range of [0, 1]; when a potential situation of insufficient power is detected, the power generation equipment with the smallest carbon emission factor in the optimized path is selected, and its power production is increased to minimize carbon emissions as much as possible while ensuring power supply.

[0154] Preferably, the specific steps for implementing the scheduling plan include:

[0155] According to the scheduling plan, implement specific power scheduling operations, including: starting or stopping specific power generation equipment; adjusting the charging and discharging modes of energy storage equipment to balance load demands; coordinating various resources through a virtual power plant to ensure the stable operation of the power grid;

[0156] Through the virtual power plant scheduling system, ensure the coordinated operation among power generation equipment, energy storage equipment, and grid load. Monitor each device in real time to ensure it operates according to the scheduling plan and respond in case of unexpected situations;

[0157] During the implementation process, continuously monitor the scheduling effect, adjust the scheduling plan based on real-time data feedback. If it is found that the scheduling plan does not meet the expectations, give an early warning and notify relevant personnel;

[0158] Embodiment 2

[0159] Please refer to Figure 6 , a virtual power plant path optimization method based on an electricity-carbon integration model, includes the following steps:

[0160] Step S1: Real-time collect target data through interfaces with power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment;

[0161] Step S2: Perform data preprocessing on the collected target data. Based on the preprocessed target data, analyze the energy consumption pattern and carbon emission trend, predict future power demands and carbon emission levels, and determine whether there are abnormal trends;

[0162] Step S3: With the goal of balancing power production and carbon emissions, construct an electricity-carbon integration model, and optimize the power production path using the objective function and constraint conditions;

[0163] Step S4: When an abnormal trend is detected, formulate a scheduling plan by optimizing the power production path to maximize energy efficiency and reduce carbon emissions;

[0164] Step S5: Execute the scheduling plan, dispatch power resources and power generation equipment, and control the coordinated operation among power generation units, energy storage equipment, and grid load within the virtual power plant.

[0165] Preferably, the construction of the electricity-carbon integration model includes:

[0166] Construct the objective function of the electricity-carbon combination model to balance power production and carbon emissions, introduce the factor of power production cost, divide the objective function into multiple levels, and the expression of the objective function is as follows:

[0167]

[0168] Among them, C carbon,t is the carbon emission cost at time t, which is determined by the type and usage of fuel, and P power,t is the power production at time t, expressed as the required power generation capacity, and C cost,t is the power production cost at time t, and α, β, and γ are weighting coefficients;

[0169] Construct the constraint conditions of the electricity-carbon combination model, including: power plant load constraint, equipment performance constraint, carbon emission constraint, energy storage constraint, and power plant stability constraint;

[0170] The expression of the power plant load constraint is as follows:

[0171]

[0172] Among them, P total,t is the total power production at time t, is the predicted value of the power demand at time t, N is the number of power generation equipment, and P i,t is the power production of the i-th power generation equipment at time t;

[0173] The expression of the equipment performance constraint is as follows:

[0174]

[0175] Among them, P min i,t and P max i,t are the minimum and maximum output powers of the i-th power generation equipment at time t;

[0176] The expression of the carbon emission constraint is as follows:

[0177]

[0178] Among them, f i is the carbon emission factor of the i-th power generation equipment, set according to the fuel type and equipment efficiency, and E limit is the total carbon emission limit;

[0179] The expression of the energy storage constraint is as follows:

[0180]

[0181] Among them, E charge,t and Edischarge,t is the charging and discharging amounts of the energy storage device at time t, E max is the maximum capacity of the energy storage device, δ discharge is the discharge efficiency, with a value between [0, 1];

[0182] The expression for the power plant stability constraint is as follows:

[0183]

[0184] where ζ t is the grid frequency at time t, v t is the grid voltage at time t, ∈ freq and ∈ voltage are the maximum fluctuation values of the grid frequency and grid voltage.

[0185] Preferably, the specific steps for abnormal trend judgment include:

[0186] According to the power path of the virtual power plant, access the operating power generation equipment through the virtual power plant platform to obtain the historical power production data of each power generation equipment;

[0187] Statistically analyze the historical power production data, identify the key factors affecting the power production of each power generation equipment, and predict the power production of each power generation equipment. The power production prediction model is as follows:

[0188]

[0189] W t =λ1T t +λ2F t +λ2Y t

[0190] where, is the predicted value of the power production of the i-th power generation equipment at time t, M1 is the amount of historical data used for power production prediction, ψ i is the failure rate of the i-th power generation equipment, P i,(t-j) is the power production of the i-th power generation equipment at time t-j, W t is the weather factor at time t, including temperature T t 、wind speed F t and solar radiation intensity Y t , η1 and η2 are the non-negative weights of the failure rate of the power generation equipment and the weather factor respectively, and λ1, λ2 and λ3 are the non-negative weighting coefficients of temperature, wind speed and solar radiation intensity in the weather factor;

[0191] Obtain historical power demand data and conduct medium- and short-term prediction of power demand. The power demand prediction model is as follows:

[0192]

[0193] wherein, is the predicted value of the electricity demand at time t, μ0 is the constant term, M3 is the order of the non-seasonal autoregressive term, is the parameter of the non-seasonal autoregressive term at time q1, is the electricity demand at time t-q1, M4 is the order of the non-seasonal moving average term, is the parameter of the non-seasonal moving average term, k(t-q2) is the residual at time t-q2, M5 is the order of the seasonal autoregressive term, is the seasonal parameter of the seasonal autoregressive term, Γ is the seasonal period, is the electricity demand at time t-q3Γ, τ t is the residual term at time t;

[0194] Compare the predicted value of the electricity demand with the available electricity production capacity, where the available electricity production capacity includes the predicted value of the electricity production of the power generation equipment and the electricity value of the energy storage equipment, and evaluate the potential supply-demand gap. The calculation formula of the supply-demand gap is as follows:

[0195]

[0196] wherein, is the supply-demand gap at time t, is the predicted value of the electricity demand at time t, is the sum of the predicted values of the electricity production of the power generation equipment at time t;

[0197] Configure the power threshold. If the supply-demand gap at time t is less than the power threshold, it indicates that there is insufficient power production. If the supply-demand gap at time t is greater than the sum of the power threshold and the electricity quantity of the energy storage equipment at time t, it indicates that there is excessive power production. Otherwise, the power supply and demand are normal, that is:

[0198]

[0199] wherein, T PD is the power threshold, is the electricity quantity of the energy storage equipment at time t-1. When S t takes 1, it indicates that there is insufficient power production. When S t takes 2, it indicates that the power supply and demand are normal. When S t takes 3, it indicates that there is excessive power production;

[0200] When the available power production capacity meets the future power demand forecast, that is, when the power supply and demand are normal or there is an oversupply of power production, obtain the carbon emission factors of power generation equipment according to the type of power generation equipment, evaluate the carbon emissions of different types of power generation equipment, and combine the power production data of the power generation equipment to obtain the carbon emission trend in the power production process of the power path of the current virtual power plant, and predict the carbon emissions, that is:

[0201]

[0202] Among them, is the predicted value of the carbon emissions at time t, N is the number of power generation equipment, is the predicted value of the power production of the i-th power generation equipment at time p, f i is the carbon emission factor of the i-th power generation equipment, M2 is the amount of historical data used for carbon emission prediction, ω p is the non-negative weight coefficient of the carbon emissions at time p, ∈ t is the white noise error at time t;

[0203] Configure the carbon emission threshold, and judge whether the carbon emissions meet the compliance target. If the predicted value of the carbon emissions at time t is greater than the carbon emission threshold, it does not meet the carbon emission compliance target, otherwise it meets the carbon emission compliance target;

[0204] If there is insufficient power production, oversupply of power production, or non-compliance with the carbon emission compliance target in the power production path, mark the abnormal trend of the power production path and notify relevant personnel through an abnormal warning.

[0205] Working principle and its effects:

[0206] The virtual power plant path optimization system based on the electric-carbon coupling model works in coordination through a series of modules and steps to achieve the best balance between power generation and carbon emissions. First, the data acquisition module collects relevant data from power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment in real time, including power data, carbon emission data, environmental data, and market data. This data is then sent to the data processing module for preprocessing, including data cleaning, outlier removal, missing data filling, and necessary data conversion and integration. In the data processing module, the trend analysis strategy uses historical and real-time data to predict future power demand and carbon emission levels. This involves building a power generation prediction model and a power demand prediction model, and evaluating the potential supply-demand gap by comparing the power demand prediction with the available power generation capacity. At the same time, this module also calculates the carbon emissions of different types of power generation equipment and predicts the carbon emission trend of the entire virtual power plant. When an abnormal trend is detected in the power generation path, the path optimization module will start working. The electric-carbon coupling model in this module comprehensively considers conditions such as power plant load constraints, equipment performance constraints, carbon emission constraints, energy storage constraints, and power plant stability constraints, aiming to find the best balance point between power generation and carbon emissions. By constructing an objective function and introducing the factor of power generation cost, the model can optimize the power generation path to minimize the carbon emission cost and maximize the energy efficiency. Once the optimized power generation path is determined, the scheduling control module will execute the corresponding scheduling plan. This includes arranging the start-stop time of power generation equipment, adjusting the charge-discharge plan of energy storage equipment, and coordinating the grid load to ensure the coordinated operation of each unit within the virtual power plant. In addition, if potential problems are still detected in the optimized power generation path, corresponding measures will be taken for adjustment, such as increasing or decreasing the power generation amount of certain power generation equipment.

[0207] In summary, through a series of steps such as real-time data acquisition, preprocessing, trend analysis, model construction, path optimization, and scheduling control, the goal of maximizing energy efficiency and reducing carbon emissions while ensuring the stable operation of the power grid is achieved.

[0208] The above description is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A virtual power plant path optimization system based on an electricity-carbon combined model, characterized in that: include: Data acquisition module, data processing module, path optimization module and scheduling control module; The data acquisition module is used to collect target data in real time through interfaces with power generation equipment, energy storage equipment, load terminals and carbon emission monitoring equipment. The target data includes: power data, carbon emission data, environmental data and market data; The data processing module is used to perform data preprocessing on the collected target data, analyze energy consumption patterns and carbon emission trends based on the preprocessed target data, predict future electricity demand and carbon emission levels, and determine whether there are abnormal trends; The path optimization module is used to build an electricity-carbon combination model with the goal of balancing electricity production and carbon emissions, optimize the electricity production path using the objective function and constraints, and formulate a scheduling plan by optimizing the electricity production path when an abnormal trend is detected; The dispatch control module is used to execute the dispatch plan, dispatch power resources and power generation equipment, and control the coordinated operation between power generation units, energy storage equipment and power grid loads in the virtual power plant.

2. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 1 is characterized in that: The construction of the electric-carbon combination model includes: The objective function of the electricity-carbon combination model is constructed to achieve a balance between electricity production and carbon emissions. The electricity production cost factor is introduced and the objective function is divided into multiple levels. The expression of the objective function is as follows: Among them, C carbon,t is the carbon emission cost at time t, which is determined by the type and amount of fuel used, P power,t is the electricity production at time t, expressed as the required power generation, C cost,t is the electricity production cost at time t, α, β and γ are weighting coefficients; The constraints for constructing the electricity-carbon combined model include: power plant load constraints, equipment performance constraints, carbon emission constraints, energy storage constraints and power plant stability constraints.

3. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 2 is characterized in that: The specific steps of constructing the electric-carbon combination model also include: The expression of the power plant load constraint is as follows: Among them, P total,t is the total electricity production at time t, is the predicted value of power demand at time t, N is the number of power generation equipment, P i,t is the power production of the ith power generation equipment at time t; The expression of the equipment performance constraint is as follows: Among them, P min i,t and P max i,t is the minimum and maximum output power of the ith power generation equipment at time t; The expression of carbon emission constraint is as follows: Among them, f i is the carbon emission factor of the ith power generation equipment, which is set according to the fuel type and equipment efficiency, E limit is the total carbon emission limit; The expression of energy storage constraint is as follows: Among them, E charge,t and E discharge,t is the charge and discharge capacity of the energy storage device at time t, E max is the maximum capacity of the energy storage device, δ discharge is the discharge efficiency, with a value between [0, 1]; The expression of the power plant stability constraint is as follows: Among them, t is the grid frequency at time t, v t is the grid voltage at time t, ∈ freq and ∈ voltage It is the maximum fluctuation value of grid frequency and grid voltage.

4. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 1 is characterized in that: The data processing module includes a preprocessing unit and a pattern recognition unit; The preprocessing unit is configured with a data cleaning strategy, which is used to clean the collected target data, remove abnormal values, fill in missing data, and perform data conversion and data integration operations; The pattern recognition unit is configured with a trend analysis strategy, which is used to identify potential electricity consumption trends and carbon emission trends by analyzing historical data and target data collected in real time, so as to predict future electricity demand and carbon emission levels and determine whether there are abnormal trends.

5. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 4 is characterized in that: The specific steps of the trend analysis strategy include: According to the power path of the virtual power plant, the operating power generation equipment is connected through the virtual power plant platform to obtain the historical power production data of each power generation equipment; Statistical analysis is performed on historical power production data to identify the key factors affecting the power production of each power generation equipment, and the power production of each power generation equipment is predicted. The power production prediction model is as follows: W t =λ1T t +λ2F t +λ2Y t in, is the predicted value of power production of the ith power generation equipment at time t, M1 is the amount of historical data used for power production prediction, ψ i is the failure rate of the ith power generation equipment, P i,(t-j) is the power production of the ith power generation equipment at time tj, W t is the weather factor at time t, including temperature T t , wind speed F t and solar radiation intensity Y t , η1 and η2 are the non-negative weights of the failure rate of power generation equipment and weather factors, respectively, λ1, λ2 and λ3 are the non-negative weighting coefficients of temperature, wind speed and solar radiation intensity in weather factors, respectively; Obtain historical power demand data and predict power demand. The power demand prediction model is as follows: in, is the predicted value of electricity demand at time t, μ0 is a constant term, M3 is the order of the non-seasonal autoregressive term, is the parameter of the non-seasonal autoregressive term at time q1, is the electricity demand at time t-q1, M4 is the order of the non-seasonal moving average term, is the parameter of the non-seasonal moving average term, k(t-q2) is the residual at time t-q2, M5 is the order of the seasonal autoregressive term, is the seasonal parameter of the seasonal autoregressive term, Γ is the seasonal period, is the power demand at time t-q3Γ, τ t is the residual term at time t.

6. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 5 is characterized in that: The specific steps of the trend analysis strategy also include: Compare the forecast value of power demand with the available power production capacity, where the available power production capacity includes the forecast value of power production of power generation equipment and the power value of energy storage equipment, to evaluate the potential supply and demand gap. The calculation formula for the supply and demand gap is as follows: in, is the gap between supply and demand at time t, is the predicted value of electricity demand at time t, is the sum of the predicted values ​​of power production of the power generation equipment at time t; Configure the power threshold. If the gap between supply and demand at time t is less than the power threshold, it indicates that there is insufficient power production. If the gap between supply and demand at time t is greater than the sum of the power threshold and the power of the energy storage device at time t, it indicates that there is excess power production. Otherwise, the power supply and demand are normal, that is: Among them, T PD is the power threshold, is the energy storage device capacity at time t-1. t When it is 1, it means that there is insufficient power production. t When it is 2, it means that the power supply and demand are normal. t When the value is 3, it indicates overproduction of electricity.

7. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 6 is characterized in that: The specific steps of the trend analysis strategy also include: If the available power production capacity meets the forecast of future power demand, that is, when the power supply and demand is normal or when there is overproduction of power, the carbon emission factor is obtained according to the type of power generation equipment, the carbon emissions of different types of power generation equipment are evaluated, and the carbon emission trend of the power generation process of the power path of the current virtual power plant is obtained in combination with the power production data of the power generation equipment, and the carbon emissions are predicted, that is: in, is the predicted value of carbon emissions at time t, N is the number of power generation equipment, is the predicted value of power production of the ith power generation equipment at time p, f i is the carbon emission factor of the ith power generation equipment, M2 is the amount of historical data used for carbon emission prediction, ω p is the non-negative weight coefficient of carbon emissions at time p, ∈ t is the white noise error at time t; Configure the carbon emission threshold to determine whether the carbon emissions meet the compliance target. If the predicted value of the carbon emissions at time t is greater than the carbon emission threshold, the carbon emission compliance target is not met; otherwise, the carbon emission compliance target is met. If the power production path shows insufficient power production, excessive power production, or carbon emissions that do not meet compliance targets, the power production path will be marked as having an abnormal trend.

8. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 1 is characterized in that: The path optimization module includes a model building unit and a scheduling optimization unit; The model building unit is configured with an electricity-carbon combination strategy, which is used to convert the trade-off relationship between electricity production and carbon emissions into a mathematical programming problem by building an electricity-carbon combination model to find the optimal balance point between electricity production and carbon emissions; The scheduling optimization unit is configured with a dynamic scheduling scheme, which is used to obtain an optimized power production path through an electricity-carbon combined model when an abnormal trend is detected in the power production path.

9. The virtual power plant path optimization system based on the electricity-carbon combined model according to claim 8 is characterized in that: The specific steps of the dynamic scheduling scheme include: When there is an abnormal trend in the power production path, the optimized power production path is recalculated through the electricity-carbon combined model according to the predicted value of power demand to obtain the power production plan; Obtain the power production of each power generation equipment at time t and the carbon emissions at time t from the power production plan; Configure deviation thresholds, including upper deviation thresholds and lower deviation thresholds, optimize the power production plan according to the actual value of power demand, calculate the cumulative deviation between the predicted value of power demand and the actual value of power demand, and when the cumulative deviation is greater than the upper deviation threshold, it indicates that the predicted value of power demand exceeds the actual value of power demand, and the optimized power production path has potential power surplus; when the cumulative deviation is less than the lower deviation threshold, it indicates that the predicted value of power demand is less than the actual value of power demand, and the optimized power production path has potential power shortage; When it is detected that there is a potential power surplus in the optimized power production path, the power generation equipment with the largest carbon emission factor in the optimized power production path is obtained and its power production is reduced; When it is detected that there is a potential power shortage in the optimized power production path, the power generation equipment with the smallest carbon emission factor in the optimized power production path is obtained to increase its power production.

10. A virtual power plant path optimization method based on an electricity-carbon combined model, which is executed based on a virtual power plant path optimization system based on an electricity-carbon combined model according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step S1: Collect target data in real time through interfaces with power generation equipment, energy storage equipment, load terminals, and carbon emission monitoring equipment; Step S2: preprocess the collected target data, analyze the energy consumption pattern and carbon emission trend based on the preprocessed target data, predict future electricity demand and carbon emission level, and determine whether there is an abnormal trend; Step S3: With the goal of balancing electricity production and carbon emissions, a combined electricity-carbon model is constructed, and the electricity production path is optimized using the objective function and constraints; Step S4: When an abnormal trend is detected, a scheduling plan is formulated by optimizing the power production path to maximize energy efficiency and reduce carbon emissions; Step S5: Execute the dispatching plan, dispatch power resources and power generation equipment, and control the coordinated operation between power generation units, energy storage equipment and grid loads in the virtual power plant.

Images