V2G adaptive discharge method and system based on multi-source data fusion

Abstract

The invention belongs to the technical field of information, and particularly provides a V2G adaptive discharge method and system based on multi-source data fusion, and the method comprises the steps: obtaining the real-time load data and peak prediction information of a power grid, and constructing a load demand model based on a time sequence in combination with the historical power utilization data of the power grid; based on the load demand model, in combination with historical behavior data of a power grid user, obtaining a time integrating degree of the power grid user and a power grid demand; based on the time integrating degree, obtaining operation state data of the vehicle equipment, and adopting a preset health degree evaluation algorithm to obtain a dischargeable state of the vehicle equipment; based on the dischargeable state, a decision algorithm based on dynamic multi-objective optimization is adopted, and a discharge starting time point of the vehicle equipment is obtained; and dynamically adjusting the discharge power of the vehicle equipment by adopting a preset power distribution rule on the basis of the discharge starting time point to realize V2G self-adaptive discharge.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and in particular relates to a V2G adaptive discharge method and system based on multi-source data fusion. Background Art

[0002] In the interaction between new energy vehicles and the power grid, vehicle-to-grid discharge technology is considered a key pillar for achieving efficient energy utilization and stable grid operation. This technology not only alleviates peak grid pressure but also generates economic benefits for users, possessing significant strategic value. However, current methods still have significant shortcomings in practical application, primarily in the selection of discharge timing and method. These methods often lack comprehensive consideration of multiple factors, leading to inefficiency or damage to equipment.

[0003] A deeper analysis of this area reveals that the limitations of existing technologies stem primarily from their inability to adapt to complex environments and dynamic changes. The discharge process needs to consider both the real-time demands of the power grid and the personalized electricity usage patterns of users. However, current methods are mostly based on a single data source or fixed rules, making it difficult to cope with changing scenarios. This further leads to a core issue: how to accurately determine the timing of discharge under the influence of multiple factors. Due to the lack of a comprehensive integrated analysis of grid demand, user habits, and device status, discharge decisions are often not intelligent enough, which in turn leads to another related problem: how to reasonably control the discharge power and depth while meeting external demands to avoid excessive wear and tear on the equipment. These two issues are intertwined: the former determines the accuracy of decision-making, while the latter directly affects the sustainability of the technology.

[0004] Therefore, how to build an intelligent decision-making mechanism based on comprehensive analysis of multi-source data to determine the optimal discharge time and method in real time while taking into account equipment protection and external needs has become a key issue that needs to be urgently addressed. Summary of the Invention

[0005] To solve the problems existing in the prior art, the present invention provides a V2G adaptive discharge method and system based on multi-source data fusion, aiming to determine the optimal discharge timing and method in real time based on the comprehensive analysis of multi-source data, thereby realizing V2G adaptive discharge.

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

[0007] A V2G adaptive discharge method based on multi-source data fusion, the method comprising:

[0008] S1. Acquire real-time load data and peak forecast information of the power grid, and build a load demand model based on time series based on the historical power consumption data of the power grid;

[0009] S2. Based on the load demand model and in combination with historical behavior data of grid users, obtaining a temporal fit between the grid users and grid demand;

[0010] S3. Based on the time coincidence, obtain the operating status data of the vehicle equipment, and use a preset health assessment algorithm to obtain the dischargeable state of the vehicle equipment;

[0011] S4. Based on the dischargeable state, a decision algorithm based on dynamic multi-objective optimization is used to obtain a discharge start time point of the vehicle device;

[0012] S5. Based on the discharge start time point, a preset power allocation rule is used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G.

[0013] Preferably, the S1 acquires real-time load data and peak forecast information of the power grid, and constructs a load demand model based on time series in combination with historical power consumption data of the power grid, including:

[0014] S11. Acquire real-time load data and peak forecast information of the power grid from a power grid management system, combine the data with the historical power consumption data of the power grid to form a comprehensive data set, and preliminarily organize the comprehensive data set based on time periods to obtain an initial load feature set;

[0015] S12. Analyzing demand variation patterns in the historical power consumption data based on the initial load feature set to determine a demand variation trend of the power grid;

[0016] S13. Based on the demand change trend, combined with the real-time load data and the peak prediction information, a time series-based load demand model is constructed.

[0017] Preferably, the step S2 obtains the temporal compatibility between the grid user and grid demand based on the load demand model and in combination with the historical behavior data of the grid user, including:

[0018] S21. Obtaining a load demand result based on the load demand model;

[0019] S22. Based on the historical behavior data of the grid users, extract the daily electricity usage time characteristics and electricity usage preference characteristics of the grid users, and group the grid users by combining the K-clustering method;

[0020] S23. Extracting electricity consumption time distribution characteristics of the grid users based on the grouped grid users;

[0021] S24. Based on the load demand result and the power consumption time distribution characteristics, obtain the time compatibility between the power grid user and the power grid demand.

[0022] Preferably, the step S3 obtains the operating status data of the vehicle equipment based on the time coincidence, and uses a preset health evaluation algorithm to obtain the dischargeable state of the vehicle equipment, including:

[0023] S31. Based on the time coincidence, obtain the operating status data of the vehicle equipment through the vehicle equipment management system;

[0024] S32. Based on the operating status data, a preset health evaluation algorithm is used to obtain a quantified health value of the vehicle equipment;

[0025] S33: Obtain a dischargeable state of the vehicle equipment based on the health quantification value.

[0026] Preferably, the step S32 adopts a preset health evaluation algorithm to obtain a quantified health value of the vehicle equipment, including: adopting an adaptive voltage curve fitting algorithm to obtain a quantified health value of the vehicle equipment:

[0027] U=θ1+θ2f(C)+θ3I×r(C)

[0028] Where U is the voltage value of the vehicle equipment during charging, r(C) is the internal resistance of the vehicle equipment battery when the charging capacity is C, C is the capacity of the vehicle equipment battery during charging, f(C) is the reference curve, I is the current during charging of the vehicle equipment battery, and θ1, θ2, and θ3 are all parameters;

[0029]

[0030] Among them, SOH is the health quantification value, C0 is the rated capacity of the vehicle equipment battery, and a and b are both linear relationship coefficients.

[0031] Preferably, the step S4 adopts a decision algorithm based on dynamic multi-objective optimization based on the dischargeable state to obtain the discharge start time point of the vehicle equipment, including:

[0032] S41, obtaining demand data of the power grid;

[0033] S42 : Based on the dischargeable state and the demand data, a decision algorithm based on dynamic multi-objective optimization is adopted to obtain a discharge start time point of the vehicle equipment.

[0034] Preferably, the decision algorithm for dynamic multi-objective optimization in S4 includes:

[0035]

[0036] Among them, F iis the function value of the i-th target, m is the number of targets, f i (t) is the fitness value of the i-th target at time t, f i (t-1) is the fitness value of the i-th objective at time t-1, α is a constant, β is the amplification factor, and F is the final value of dynamic multi-objective optimization.

[0037] Preferably, the S5 dynamically adjusts the discharge power of the vehicle equipment based on the discharge start time point using a preset power allocation rule to achieve adaptive discharge of V2G, including:

[0038] S51. Obtaining the discharge power of the vehicle equipment and the demand data of the power grid at the discharge start time point;

[0039] S52: Based on the discharge power and the demand data, a preset power allocation rule is used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G.

[0040] The present invention also provides a V2G adaptive discharge system based on multi-source data fusion, which is used to implement the aforementioned V2G adaptive discharge method based on multi-source data fusion. The system includes: a load demand model construction module, a time fit module, a state assessment module, a discharge decision module, and an adaptive discharge module;

[0041] The load demand model building module is used to obtain real-time load data and peak forecast information of the power grid, and build a load demand model based on time series in combination with the historical power consumption data of the power grid;

[0042] The time compatibility module is configured to obtain the time compatibility between the grid user and grid demand based on the load demand model and in combination with the historical behavior data of the grid user;

[0043] The state evaluation module is used to obtain the operating state data of the vehicle equipment based on the time fit, and obtain the dischargeable state of the vehicle equipment using a preset health evaluation algorithm;

[0044] The discharge decision module is configured to obtain a discharge start time point of the vehicle device based on the dischargeable state and using a decision algorithm based on dynamic multi-objective optimization;

[0045] The adaptive discharge module is used to dynamically adjust the discharge power of the vehicle equipment based on the discharge start time point and adopt a preset power allocation rule to achieve adaptive discharge of V2G.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention discloses a V2G adaptive discharge method and system based on multi-source data fusion. By analyzing the real-time demand change trend of the power grid and the user's electricity consumption habits, a load demand model is constructed to determine the time fit between the user and the power grid demand. Combined with the operating status of the vehicle equipment, it is judged whether it is suitable to participate in the discharge operation. For equipment suitable for discharge, a dynamic multi-objective optimization algorithm is used to calculate the optimal discharge time, and the specific start time is determined according to the peak distribution of the power grid load. The present invention can also dynamically adjust the discharge power according to the real-time battery capacity and power grid demand fluctuations to meet the peak load shaving needs of the power grid. The present invention realizes the intelligent interaction between electric vehicles and power grids, effectively improves the peak-shaving capacity of the power grid, optimizes the utilization of power resources, and provides technical support for the construction of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 This is a flow chart of a V2G adaptive discharge method based on multi-source data fusion according to an embodiment of the present invention;

[0050] Figure 2 Schematic diagram of a V2G adaptive discharge system based on multi-source data fusion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Example 1

[0054] like Figure 1 As shown, the present invention provides a V2G adaptive discharge method based on multi-source data fusion, the method comprising:

[0055] S1. Obtain real-time load data and peak forecast information of the power grid, combine it with the historical power consumption data of the power grid, and build a load demand model based on time series;

[0056] S2. Based on the load demand model and combined with the historical behavior data of grid users, obtain the time fit between grid users and grid demand;

[0057] S3. Based on the time coincidence, obtain the operating status data of the vehicle equipment and use a preset health assessment algorithm to obtain the discharge status of the vehicle equipment;

[0058] S4. Based on the dischargeable state, a decision algorithm based on dynamic multi-objective optimization is used to obtain a discharge start time point of the vehicle equipment;

[0059] S5. Based on the discharge start time point, the preset power allocation rules are used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G.

[0060] Further:

[0061] S1. Obtain real-time load data and peak forecast information from the power grid, combine it with historical power consumption data, and build a time series-based load demand model, including:

[0062] S11. Acquire real-time load data and peak forecast information of the power grid from the power grid management system, combine the historical power consumption data of the power grid to form a comprehensive data set, and preliminarily organize the comprehensive data set based on time periods to obtain an initial load feature set;

[0063] S12. Analyze demand variation patterns in historical electricity consumption data based on the initial load feature set to determine demand variation trends of the power grid;

[0064] S13. Based on the demand change trend, combined with real-time load data and peak forecast information, a time series-based load demand model is constructed.

[0065] S2. Based on the load demand model and combined with the historical behavior data of grid users, the temporal fit between grid users and grid demand is obtained, including:

[0066] S21. Obtaining a load demand result based on the load demand model;

[0067] S22. Based on the historical behavior data of power grid users, extract the daily electricity consumption time characteristics and electricity consumption preference characteristics of power grid users, and group the power grid users by combining the K-clustering method;

[0068] S23. Extracting electricity consumption time distribution characteristics of the grid users based on the grouped grid users;

[0069] S24. Based on the load demand results and the electricity consumption time distribution characteristics, obtain the time fit between the grid users and the grid demand.

[0070] S3. Based on the time fit, obtain the operating status data of the vehicle equipment and use the preset health assessment algorithm to obtain the discharge status of the vehicle equipment, including:

[0071] S31. Based on the time coincidence, obtain the operating status data of the vehicle equipment through the vehicle equipment management system;

[0072] S32. Based on the operating status data, a preset health evaluation algorithm is used to obtain a quantified health value of the vehicle equipment;

[0073] S33. Obtain the dischargeable state of the vehicle equipment based on the health quantification value.

[0074] Among them, in S32, a preset health evaluation algorithm is used to obtain a quantified value of the health of the vehicle equipment, including: using an adaptive voltage curve fitting algorithm to obtain a quantified value of the health of the vehicle equipment.

[0075] The linear parameter model of the vehicle equipment charging voltage curve is as follows:

[0076] U=θ1+θ2f(C)+θ3I×r(C)

[0077] Where U is the voltage value of the vehicle equipment during charging, r(C) is the internal resistance of the vehicle equipment battery when the charging capacity is C, C is the capacity of the vehicle equipment battery during charging, f(C) is the reference curve, I is the current during charging of the vehicle equipment battery, and θ1, θ2, and θ3 are all parameters;

[0078] In order to enable the linear parameter model of the vehicle equipment charging voltage curve to accurately match the charging voltage curve of the vehicle equipment battery at different health quantification values ​​SOH, it is necessary that the parameters of the linear parameter model of the vehicle equipment charging voltage curve can be appropriately adjusted in real time according to the charging voltage value. Therefore, the recursive least squares method is selected to calculate the unknown coefficients θ1, θ2 and θ3.

[0079] After several recursive calculations, there will be multiple results for the unknown parameters in the model, but eventually these parameters will converge to three constants. At this point, the voltage model for this charge is considered to be determined, and the converged constants are substituted into the model.

[0080] When the relationship between the charging capacity ΔC of the vehicle equipment battery and the health quantification value is linear, the linear relationship is expressed as:

[0081] ΔC=aSOH+b

[0082] The definition formula of the health quantification value SOH is:

[0083]

[0084] but

[0085]

[0086] Where C0 is the rated capacity of the vehicle equipment battery, and a and b are both linear relationship coefficients.

[0087] S4. Based on the dischargeable state, a decision algorithm based on dynamic multi-objective optimization is used to obtain the discharge start time point of the vehicle equipment, including:

[0088] S41, obtaining demand data of the power grid;

[0089] S42 : Based on the dischargeable state and the demand data, a decision algorithm based on dynamic multi-objective optimization is adopted to obtain a discharge start time point of the vehicle equipment.

[0090] The dynamic multi-objective optimization decision-making algorithm in S4 includes:

[0091]

[0092] Among them, F i is the function value of the i-th target, m is the number of targets, f i (t) is the fitness value of the i-th target at time t, f i (t-1) is the fitness value of the i-th objective at time t-1, α is a constant, β is the amplification factor, and F is the final value of dynamic multi-objective optimization.

[0093] S5. Based on the discharge start time point, the preset power allocation rules are used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G, including:

[0094] S51. Obtaining discharge power of vehicle equipment and grid demand data at the discharge start time point;

[0095] S52. Based on the discharge power and demand data, the preset power allocation rules are used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G. Specifically:

[0096] A battery capacity threshold for the vehicle equipment is preset. When the battery capacity of the vehicle equipment is lower than the preset threshold during discharge, the discharge power output ratio is reduced. When the battery capacity of the vehicle equipment is higher than the preset threshold during discharge, the discharge power output ratio is maintained or increased to determine the adjusted temporary discharge power.

[0097] Obtain real-time grid demand data and compare it with the preset load peak shaving target value range. If the demand data exceeds the preset range, further fine-tune the temporary discharge power; if the demand data is within the preset range, maintain the temporary discharge power.

[0098] In summary, the present invention provides a V2G adaptive discharge method based on multi-source data fusion. By analyzing the real-time demand change trend of the power grid and the user's electricity consumption habits, a load demand model is constructed to determine the time fit between the user and the power grid demand. Combined with the operating status of the vehicle equipment, it is judged whether it is suitable to participate in the discharge operation. For equipment suitable for discharge, a dynamic multi-objective optimization algorithm is used to calculate the optimal discharge time, and the specific start time is determined according to the peak distribution of the power grid load. The present invention can also dynamically adjust the discharge power according to the real-time battery capacity and power grid demand fluctuations to meet the peak load shaving needs of the power grid. The present invention realizes the intelligent interaction between electric vehicles and power grids, effectively improves the peak-shaving capacity of the power grid, optimizes the utilization of power resources, and provides technical support for the construction of smart grids.

[0099] Example 2

[0100] like Figure 2 As shown, the present invention also provides a V2G adaptive discharge system based on multi-source data fusion, which is used to implement the V2G adaptive discharge method based on multi-source data fusion as described in the above embodiment. The system includes: a load demand model construction module, a time fit module, a state assessment module, a discharge decision module and an adaptive discharge module;

[0101] The load demand model building module is used to obtain real-time load data and peak forecast information of the power grid, and build a load demand model based on time series based on the historical power consumption data of the power grid;

[0102] The time compatibility module is used to obtain the time compatibility between grid users and grid demand based on the load demand model and the historical behavior data of grid users;

[0103] The status assessment module is used to obtain the operating status data of the vehicle equipment based on the time fit and obtain the discharge status of the vehicle equipment using a preset health assessment algorithm;

[0104] A discharge decision module is used to obtain the discharge start time point of the vehicle equipment based on the discharge state and a decision algorithm based on dynamic multi-objective optimization;

[0105] The adaptive discharge module is used to dynamically adjust the discharge power of vehicle equipment based on the discharge start time point and adopt preset power allocation rules to achieve adaptive discharge of V2G.

[0106] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A V2G adaptive discharge method based on multi-source data fusion, characterized in that: The method comprises: S1. Acquire real-time load data and peak forecast information of the power grid, and build a load demand model based on time series based on the historical power consumption data of the power grid; S2. Based on the load demand model and in combination with historical behavior data of grid users, obtaining a temporal fit between the grid users and grid demand; S3. Based on the time coincidence, obtain the operating status data of the vehicle equipment, and use a preset health assessment algorithm to obtain the dischargeable state of the vehicle equipment; S4. Based on the dischargeable state, a decision algorithm based on dynamic multi-objective optimization is used to obtain a discharge start time point of the vehicle device; S5. Based on the discharge start time point, a preset power allocation rule is used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G.

2. The V2G adaptive discharge method based on multi-source data fusion according to claim 1 is characterized in that: The S1 obtains real-time load data and peak forecast information of the power grid, and builds a load demand model based on time series based on the historical power consumption data of the power grid, including: S11. Acquire real-time load data and peak forecast information of the power grid from a power grid management system, combine the data with the historical power consumption data of the power grid to form a comprehensive data set, and preliminarily organize the comprehensive data set based on time periods to obtain an initial load feature set; S12. Analyzing demand variation patterns in the historical power consumption data based on the initial load feature set to determine a demand variation trend of the power grid; S13. Based on the demand change trend, combined with the real-time load data and the peak prediction information, a time series-based load demand model is constructed.

3. The V2G adaptive discharge method based on multi-source data fusion according to claim 1, characterized in that: The S2 obtains the temporal compatibility between the grid user and grid demand based on the load demand model and in combination with the historical behavior data of the grid user, including: S21. Obtaining a load demand result based on the load demand model; S22. Based on the historical behavior data of the grid users, extract the daily electricity usage time characteristics and electricity usage preference characteristics of the grid users, and group the grid users by combining the K-clustering method; S23. Extracting electricity consumption time distribution characteristics of the grid users based on the grouped grid users; S24. Based on the load demand result and the power consumption time distribution characteristics, obtain the time compatibility between the power grid user and the power grid demand.

4. The V2G adaptive discharge method based on multi-source data fusion according to claim 1, characterized in that: The step S3 obtains the operating status data of the vehicle device based on the time coincidence, and uses a preset health evaluation algorithm to obtain the dischargeable state of the vehicle device, including: S31. Based on the time coincidence, obtain the operating status data of the vehicle equipment through the vehicle equipment management system; S32. Based on the operating status data, a preset health evaluation algorithm is used to obtain a quantified health value of the vehicle equipment; S33: Obtain a dischargeable state of the vehicle equipment based on the health quantification value.

5. The V2G adaptive discharge method based on multi-source data fusion according to claim 4 is characterized in that: The step S32 uses a preset health evaluation algorithm to obtain a quantified health value of the vehicle device, including: using an adaptive voltage curve fitting algorithm to obtain a quantified health value of the vehicle device: U=θ1+θ2f(C)+θ3I×r(C) Where U is the voltage value of the vehicle equipment during charging, r(C) is the internal resistance of the vehicle equipment battery when the charging capacity is C, C is the capacity of the vehicle equipment battery during charging, f(C) is the reference curve, I is the current during charging of the vehicle equipment battery, and θ1, θ2, and θ3 are all parameters; Among them, SOH is the health quantification value, C0 is the rated capacity of the vehicle equipment battery, and a and b are both linear relationship coefficients.

6. The V2G adaptive discharge method based on multi-source data fusion according to claim 1, characterized in that: The step S4 obtains the discharge start time point of the vehicle device based on the dischargeable state by adopting a decision algorithm based on dynamic multi-objective optimization, including: S41, obtaining demand data of the power grid; S42 : Based on the dischargeable state and the demand data, a decision algorithm based on dynamic multi-objective optimization is used to obtain a discharge start time point of the vehicle equipment.

7. The V2G adaptive discharge method based on multi-source data fusion according to claim 6, characterized in that: The dynamic multi-objective optimization decision algorithm in S4 includes: Among them, F i is the function value of the i-th target, m is the number of targets, f i (t) is the fitness value of the i-th target at time t, f i (t-1) is the fitness value of the i-th objective at time t-1, α is a constant, β is the amplification factor, and F is the final value of dynamic multi-objective optimization.

8. The V2G adaptive discharge method based on multi-source data fusion according to claim 6, characterized in that: The S5 dynamically adjusts the discharge power of the vehicle equipment based on the discharge start time point using a preset power allocation rule to achieve adaptive discharge of V2G, including: S51, obtaining the discharge power of the vehicle equipment and the demand data of the power grid at the discharge start time point; S52: Based on the discharge power and the demand data, a preset power allocation rule is used to dynamically adjust the discharge power of the vehicle equipment to achieve adaptive discharge of V2G.

9. A V2G adaptive discharge system based on multi-source data fusion, the system being used to implement the V2G adaptive discharge method based on multi-source data fusion according to any one of claims 1 to 8, characterized in that: The system includes: a load demand model building module, a time fit module, a state assessment module, a discharge decision module and an adaptive discharge module; The load demand model building module is used to obtain real-time load data and peak forecast information of the power grid, and build a load demand model based on time series in combination with the historical power consumption data of the power grid; The time compatibility module is configured to obtain the time compatibility between the grid user and grid demand based on the load demand model and in combination with the historical behavior data of the grid user; The state evaluation module is used to obtain the operating state data of the vehicle equipment based on the time fit, and obtain the dischargeable state of the vehicle equipment using a preset health evaluation algorithm; The discharge decision module is configured to obtain a discharge start time point of the vehicle device based on the dischargeable state and using a decision algorithm based on dynamic multi-objective optimization; The adaptive discharge module is used to dynamically adjust the discharge power of the vehicle equipment based on the discharge start time point and adopt a preset power allocation rule to achieve adaptive discharge of V2G.

Images