Water, electricity and heating supply management method and system based on PVT cogeneration

Abstract

The present invention discloses a water, electricity and heating supply management method and system based on PVT cogeneration, which relates to the technical field of PVT cogeneration, and specifically discloses recording a combination of an operating parameter performance characteristic segment and a demand parameter performance characteristic segment as a characteristic segment reference group, optimizing and adjusting the power storage and heat storage strategies corresponding to the characteristic segment reference group, obtaining a plurality of first reference strategies, screening out a plurality of second reference strategies based on evaluation results, determining the most suitable characteristic segment reference group based on comparison results, and identifying the second reference strategy corresponding to the most suitable characteristic segment reference group as the current control strategy for the energy storage system and the heat storage system. The above technical scheme of the present invention realizes the optimization of the power storage and heat storage strategies, and determines the most suitable reference strategy by data comparison, thereby realizing the control optimization of the energy storage system and the heat storage system.

Description

Technical Field

[0001] The present invention relates to the technical field of PVT cogeneration, and in particular to a water, electricity and heating supply management method and system based on PVT cogeneration. Background Art

[0002] The PVT (Photovoltaic-Thermal) cogeneration system is a technology that integrates photovoltaic power generation and thermal energy collection. It can provide electricity and thermal energy at the same time, thereby improving the overall efficiency of energy utilization. In the PVT system, photovoltaic modules convert solar energy into electricity while also absorbing and utilizing the sun's thermal energy. This part of the thermal energy can be used for heating or hot water supply, further increasing the energy output of the system.

[0003] However, the performance of PVT systems is affected by many factors, including weather conditions, time of day changes, fluctuations in user demand, and interactive needs of the power grid. These factors lead to a mismatch between the production and consumption of electricity and thermal energy in PVT systems, which may cause energy waste or insufficient supply. To address this problem, power and heat storage systems are often integrated into PVT systems to balance the uncertainty of energy supply and demand.

[0004] Traditional electricity and heat storage strategies are often based on simple rules or preset patterns. These strategies do not fully consider real-time operating data and dynamically changing needs, and therefore may not achieve optimal energy management. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for associating water, electricity and heating supply of PVT cogeneration, which can optimize energy storage and heat storage strategies.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The water, electricity and heating supply management method based on PVT cogeneration includes:

[0008] Analyze the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and express the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model;

[0009] Performing characteristic performance analysis on the operation parameter performance model and the demand parameter performance model, and based on the analysis results, respectively performing characteristic segment interception on the operation parameter performance model and the demand parameter performance model to obtain the operation parameter performance characteristic segment and the demand parameter performance characteristic segment, and recording the combination of the operation parameter performance characteristic segment and the demand parameter performance characteristic segment as a characteristic segment reference group;

[0010] Optimize and adjust the electricity storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a number of first reference strategies, and evaluate each first reference strategy based on preset energy supply and heat supply evaluation rules, and select a number of second reference strategies based on the evaluation results;

[0011] The current operating parameter data and the current demand parameter data are compared with different feature segment reference groups in turn for similarity, and based on the comparison results, the most suitable feature segment reference group is determined, and the second reference strategy corresponding to the most suitable feature segment reference group is identified as the current control strategy for the energy storage system and the heat storage system.

[0012] In some embodiments disclosed in the present invention, the method of presenting the operating parameter data and the demand parameter data in the time dimension includes:

[0013] The operating parameter data include PVT power generation parameters and PVT heat generation parameters at different time nodes, and the demand parameter data include user electricity demand parameters, user heat demand parameters and power grid electricity demand parameters at different time nodes. Curve expression models with time as the horizontal axis coordinate and parameters as the vertical axis coordinate are constructed respectively to obtain the PVT power generation parameter curve expression model, the PVT heat generation parameter curve expression model, the user electricity demand parameter curve expression model, the user heat demand parameter curve expression model and the power grid electricity demand parameter curve expression model.

[0014] In some embodiments disclosed in the present invention, a method for performing characteristic performance analysis on an operation parameter performance model and a demand parameter performance model includes:

[0015] Dynamic analysis nodes are set for the PVT power generation parameter curve expression model, the PVT heat generation parameter curve expression model, the user power demand parameter curve expression model, the user heat demand parameter curve expression model and the power grid power demand parameter curve expression model respectively, and the time nodes corresponding to the dynamic analysis nodes on each curve expression model are the same;

[0016] Taking the dynamic analysis node as the center, a first interception section is constructed for the PVT power generation parameter curve expression model, a second interception section is constructed for the PVT heat generation parameter curve expression model, a third interception section is constructed for the user power demand parameter curve expression model, a fourth interception section is constructed for the user heat demand parameter curve expression model, and a fifth interception section is constructed for the power grid demand parameter curve expression model;

[0017] A pre-analysis section is set for each curve performance model, and the factors requiring attention of the curve performance model are analyzed in the pre-analysis section with the dynamic analysis node as the center. Based on the performance of the factors requiring attention, the interception length of the interception section corresponding to the curve performance model is determined.

[0018] In some embodiments disclosed in the present invention, a method for determining a cut length of a cut section corresponding to a curve representation model includes:

[0019] The number of curve inflection points in the pre-analysis section on the curve performance model and the rate of change of the amplitude between the curve inflection points;

[0020] An effective information parameter operator is constructed based on the number of curve inflection points and the amplitude change rate between the curve inflection points, and an initial interception length of the interception section is determined based on the effective information parameter operator;

[0021] Perform a rationality test on the initial intercept length. The rationality test includes taking the initial intercept length, the number of curve inflection points and the curve change rate as screening conditions, randomly screening out a number of equivalent curve performance models, and comparing the difference variances between the curve performance models. If the difference variance is less than or equal to the preset value, the initial intercept length is identified as the applied intercept length, otherwise the initial intercept length is amplified by a preset ratio;

[0022] Among them, the method for comparing the difference variances between curve expression models includes: randomly combining the curve expression models in pairs to obtain several curve expression model comparison groups, and calculating the average difference in the vertical coordinates in each curve expression model comparison group, and based on the average difference in the vertical coordinates, calculating the difference variance about the average difference in the vertical coordinates.

[0023] In some embodiments disclosed in the present invention, the expression for calculating the initial intercept length is:

[0024] ;

[0025] in, is the initial intercept length, is the intercept length conversion factor, is the preset standard valid information parameter, is the amplitude change rate judgment function. If the amplitude change rate of the i-th curve inflection point is greater than or equal to the preset value, the ratio of the amplitude change rate to the preset value is output. is the parameter adjustment constant.

[0026] In some embodiments disclosed in the present invention, the method for optimizing and adjusting the power storage and heat storage strategies corresponding to the characteristic segment reference group includes:

[0027] According to the time relationship, the feature segment reference groups in the same preset monitoring period are sorted to form a feature segment reference group sequence;

[0028] Based on the time difference between the electricity demand and the heat demand in the preset monitoring period, the preset monitoring period is time segmented, and based on the time segmentation of the preset monitoring period, the characteristic segment reference groups in the characteristic segment reference group sequence are classified;

[0029] Calculate the total electricity demand and heat demand of users corresponding to the characteristic reference group in each time segment. If the total electricity demand of users corresponding to the characteristic reference group at a later time is greater than that of the characteristic reference group at an earlier time, and the difference is greater than or equal to the preset value, the electricity storage parameters in the electricity storage and heat storage strategies are increased, otherwise the electricity storage parameters in the electricity storage and heat storage strategies are reduced. If the total heat demand of users corresponding to the characteristic parameter group at a later time is greater than that of the characteristic parameter group at an earlier time, and the difference is greater than or equal to the preset value, the heat storage parameters in the electricity storage and heat storage strategies are increased, otherwise the heat storage parameters in the electricity storage and heat storage strategies are reduced.

[0030] In some embodiments disclosed in the present invention, based on preset energy supply and heat supply evaluation rules, a method for evaluating each first reference strategy includes:

[0031] Based on the relationship between the total electricity demand of users and the total heat demand of users, the characteristic segment reference groups are sorted, and several characteristic reference groups with the highest order are selected as the characteristic reference groups for evaluation;

[0032] Establishing a time node sequence, and based on the time node sequence, mapping a user electricity demand parameter sequence, a user heat demand parameter sequence, an electricity storage parameter sequence, and a heat storage parameter sequence to the evaluation feature reference group;

[0033] Determine a first sub-evaluation of the first reference strategy based on the continuous performance characteristics of the user's electricity demand parameter sequence and the electricity storage parameter sequence, and determine a second sub-evaluation of the first reference strategy based on the continuous performance characteristics of the user's heat demand parameter sequence and the heat storage parameter sequence;

[0034] The weight coefficients are respectively configured for the first sub-evaluation and the second sub-evaluation corresponding to each evaluation feature reference group, and the weight coefficients are summed to determine the comprehensive evaluation of the corresponding first reference strategy;

[0035] Among them, the sub-evaluation expression for determining the first sub-evaluation or the second sub-evaluation is:

[0036] ;

[0037] in, is the corresponding value of the first sub-evaluation or the corresponding value of the second sub-evaluation, is the sub-evaluation conversion coefficient, which is adjusted according to the time segment to which the feature reference group belongs. The later the time segment, the The bigger, is the power storage supply effectiveness judgment function, if is greater than or equal to the preset value, then Output 1, otherwise output 0. is the x-order electrical storage parameter or heat storage parameter, is the x-1th order electrical storage parameter or thermal storage parameter, are the electricity demand parameters and heat demand parameters of the xth order, is the number of parameters in the sequence, Adjustment constant for sub-evaluation.

[0038] In some embodiments disclosed in the present invention, the method of comparing the current operating parameter data and the current demand parameter data with different feature segment reference groups in sequence for similarity includes:

[0039] Analyze the current operating parameter data and the current demand parameter data to obtain the current operating parameter performance model and the current demand parameter performance model;

[0040] Performing feature dimensionality reduction on the feature segment reference group, wherein the feature dimensionality reduction method includes determining the change trend of each performance feature segment in the feature segment reference group at different time nodes to obtain a change trend sequence;

[0041] Based on the matching performance of the change trend sequence and the current operation parameter performance model and the current demand parameter performance model, the characteristic segment reference group is screened for the first time;

[0042] Overlapping and comparing the operating parameter performance characteristic segments in the screened characteristic segment reference group with the current operating parameter performance model, and calculating a first difference reference area between the two;

[0043] Overlap and compare the demand parameter performance characteristic segments in the filtered characteristic segment reference group with the current demand parameter performance model, and calculate the second difference reference area between the two;

[0044] Based on the type of the operating parameter, a first attention weight coefficient is configured for the first difference reference area to construct a first difference operator, and based on the type of the demand parameter, a second attention coefficient is configured for the second difference reference area to construct a second difference operator;

[0045] Based on the first difference operator and the second difference operator, the difference degree corresponding to the feature segment reference group is calculated, and several feature segment reference groups whose difference degree is less than or equal to the preset value are screened out, and the second reference strategy corresponding to the screened feature segment reference group is identified as the current control strategy for the energy storage system and the heat storage system.

[0046] In some embodiments disclosed in the present invention, a water, electricity and heating supply management system based on PVT cogeneration is also disclosed, including:

[0047] The first module is used to analyze the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and to express the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model;

[0048] The second module is used to perform characteristic performance analysis on the operation parameter performance model and the demand parameter performance model, and based on the analysis results, respectively perform characteristic segment interception on the operation parameter performance model and the demand parameter performance model to obtain the operation parameter performance characteristic segment and the demand parameter performance characteristic segment, and record the combination of the operation parameter performance characteristic segment and the demand parameter performance characteristic segment as a characteristic segment reference group;

[0049] The third module is used to optimize and adjust the power storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a plurality of first reference strategies, and evaluate each first reference strategy based on the preset energy supply and heat supply evaluation rules, and select a plurality of second reference strategies based on the evaluation results;

[0050] The fourth module is used to compare the current operating parameter data and the current demand parameter data with different feature segment reference groups in turn for similarity, and based on the comparison results, determine the most suitable feature segment reference group, and identify the second reference strategy corresponding to the most suitable feature segment reference group as the current control strategy for the energy storage system and the heat storage system.

[0051] The present invention discloses a water, electricity and heating supply management method and system based on PVT cogeneration, which relates to the technical field of PVT cogeneration, and specifically discloses recording a combination of an operating parameter performance characteristic segment and a demand parameter performance characteristic segment as a characteristic segment reference group, optimizing and adjusting the power storage and heat storage strategies corresponding to the characteristic segment reference group, obtaining a plurality of first reference strategies, screening out a plurality of second reference strategies based on evaluation results, determining the most suitable characteristic segment reference group based on comparison results, and identifying the second reference strategy corresponding to the most suitable characteristic segment reference group as the current control strategy for the energy storage system and the heat storage system. The above technical scheme of the present invention realizes the optimization of the power storage and heat storage strategies, and determines the most suitable reference strategy by data comparison, thereby realizing the control optimization of the energy storage system and the heat storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a method step diagram of a water, electricity and heating supply management method based on PVT cogeneration disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0054] The purpose of the present invention is to provide a method and system for associating water, electricity and heating supply of PVT cogeneration, which can optimize energy storage and heat storage strategies.

[0055] In order to achieve the above object, the present invention adopts the following technical solutions:

[0056] Water, electricity and heating supply management method based on PVT cogeneration, see Figure 1 ,include:

[0057] Step S100, analyzing the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and expressing the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model.

[0058] In a PVT cogeneration system, the operation log contains key performance indicators of the system, such as power generation, heat output, ambient temperature, solar radiation intensity, etc.; these data are usually recorded in the form of time series. In step S100, these log data are analyzed to extract operation parameters (such as PVT power and heat generation efficiency) and demand parameters (such as user power and heat demand); through analysis, these parameter data can be visualized as curves on the time axis to form an operation parameter performance model and a demand parameter performance model.

[0059] In some embodiments disclosed in the present invention, the method of presenting the operating parameter data and the demand parameter data in the time dimension includes:

[0060] Step S101, the operating parameter data includes PVT power generation parameters and PVT heat generation parameters at different time nodes, and the demand parameter data includes user power demand parameters, user heat demand parameters and power grid power demand parameters at different time nodes, and respectively constructs a curve expression model with time as the horizontal axis coordinate and the parameter as the vertical axis coordinate to obtain a PVT power generation parameter curve expression model, a PVT heat generation parameter curve expression model, a user power demand parameter curve expression model, a user heat demand parameter curve expression model and a power grid power demand parameter curve expression model.

[0061] For example:

[0062] PVT power generation parameter curve performance model: This model shows the power output of the PVT system at different time points. Time (such as hours) is used as the horizontal axis, and the power output of the PVT system (usually expressed in kilowatt-hours or megawatt-hours) is used as the vertical axis.

[0063] PVT thermal parameter curve performance model: Similar to the electrical parameter model, this model records the thermal energy output of the PVT system at different points in time. The thermal energy output may be expressed in thermal units (such as kilojoules or megajoules).

[0064] User electricity demand parameter curve expression model: This model reflects the user's electricity demand at different time points. By analyzing this model, the peak and valley periods of electricity demand can be identified, which is crucial for power dispatching and energy storage strategy formulation.

[0065] Model of heat demand curve for users: This model shows the heat demand of users at different time points, such as heating or hot water supply. The heat demand may be related to the season, weather conditions or time of day.

[0066] Grid electricity demand parameter curve representation model: This model represents the power demand of the grid at different time points.

[0067] Step S200, perform characteristic performance analysis on the operating parameter performance model and the demand parameter performance model, and based on the analysis results, perform characteristic segment interception on the operating parameter performance model and the demand parameter performance model respectively to obtain operating parameter performance characteristic segments and demand parameter performance characteristic segments, and record the combination of the operating parameter performance characteristic segments and the demand parameter performance characteristic segments as a characteristic segment reference group.

[0068] In step S200, the operational parameter performance model and the demand parameter performance model are subjected to in-depth feature analysis; this includes identifying key features in the data, such as peak hours, demand change trends, etc. Then, based on these features, the model is subjected to feature segment interception, that is, data within a specific time period is selected for analysis; these feature segments represent efficient or critical periods of system operation and demand. These feature segments are combined into a feature segment reference group to provide a basis for subsequent strategy optimization.

[0069] In some embodiments disclosed in the present invention, a method for performing characteristic performance analysis on an operation parameter performance model and a demand parameter performance model includes:

[0070] Step S201, respectively setting dynamic analysis nodes on the PVT power generation parameter curve expression model, the PVT heat generation parameter curve expression model, the user power demand parameter curve expression model, the user heat demand parameter curve expression model and the power grid power demand parameter curve expression model, and the time nodes corresponding to the dynamic analysis nodes on each curve expression model are the same.

[0071] In step S201, dynamic analysis nodes are set for each curve performance model (PVT power generation, heat generation, user power demand, user heat demand, and grid power demand). These nodes are pre-selected key time points corresponding to specific time periods of the day. Ensuring that the dynamic analysis nodes on each model correspond to the same time points helps to compare the relationships between different parameters.

[0072] Step S202, with the dynamic analysis node as the center, construct the first intercepted segment for the PVT power generation parameter curve expression model, construct the second intercepted segment for the PVT heat generation parameter curve expression model, construct the third intercepted segment for the user power demand parameter curve expression model, construct the fourth intercepted segment for the user heat demand parameter curve expression model, and construct the fifth intercepted segment for the power grid demand parameter curve expression model.

[0073] In step S202, a cut-off segment is constructed with each dynamic analysis node as the center. For example, for the PVT power generation parameter curve expression model, the first cut-off segment is constructed, which may include the time period before and after the analysis node, which contains important information about the power generation parameters. Similarly, respective cut-off segments are constructed for the PVT heat generation parameter, user power demand, user heat demand, and grid power demand curve expression models.

[0074] In step S203, a pre-analysis section is set for each curve representation model, and the factors requiring attention of the curve representation model are analyzed in the pre-analysis section with the dynamic analysis node as the center, and based on the performance of the factors requiring attention, the interception length of the interception section corresponding to the curve representation model is determined.

[0075] In step S203, a pre-analysis section is set for each curve performance model, and the factors of interest of the curve are analyzed within the section. These factors may include the slope, inflection point, peak value, etc. of the curve, which are crucial for understanding the changing trend of the parameters. Based on the performance of these factors, the length of each intercepted section is determined. This process involves complex calculations, such as statistical analysis or machine learning algorithms, to accurately capture the important features of the curve.

[0076] In some embodiments disclosed in the present invention, a method for determining a cut length of a cut section corresponding to a curve representation model includes:

[0077] Step S2031, calculating the number of curve inflection points in the pre-analysis section on the curve representation model and the rate of change of the amplitude between the curve inflection points.

[0078] Step S2032, constructing an effective information parameter operator based on the number of curve inflection points and the amplitude change rate between the curve inflection points, and determining an initial interception length of the intercepted segment based on the effective information parameter operator.

[0079] Step S2033, performing a rationality test on the initial interception length. The rationality test includes taking the initial interception length, the number of curve inflection points and the curve change rate as screening conditions, randomly screening out several equivalent curve representation models, and comparing the difference variances between the curve representation models. If the difference variance is less than or equal to a preset value, the initial interception length is recognized as the applied interception length, otherwise the initial interception length is amplified by a preset ratio.

[0080] Among them, the method for comparing the difference variances between curve expression models includes: randomly combining the curve expression models in pairs to obtain several curve expression model comparison groups, and calculating the average difference in the vertical coordinates in each curve expression model comparison group, and based on the average difference in the vertical coordinates, calculating the difference variance about the average difference in the vertical coordinates.

[0081] In some embodiments disclosed in the present invention, the expression for calculating the initial intercept length is:

[0082] .

[0083] in, is the initial intercept length, is the intercept length conversion factor, is the preset standard valid information parameter, is the amplitude change rate judgment function. If the amplitude change rate of the i-th curve inflection point is greater than or equal to the preset value, the ratio of the amplitude change rate to the preset value is output. is the parameter adjustment constant.

[0084] Step S300, optimize and adjust the electricity storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a plurality of first reference strategies, and evaluate each first reference strategy based on preset energy supply and heat supply evaluation rules, and select a plurality of second reference strategies based on the evaluation results.

[0085] In step S300, the characteristic segment reference group is used to optimize the electricity storage and heat storage strategies, including adjusting the charging and discharging time of the energy storage system, optimizing the thermal energy storage and release strategies, etc. The optimized strategies are called the first reference strategies. Then, according to the preset energy supply and heat supply evaluation rules, these strategies are evaluated to determine their effectiveness in meeting user needs and grid requirements. The evaluation results are used to screen out a more effective second reference strategy.

[0086] In some embodiments disclosed in the present invention, the method for optimizing and adjusting the power storage and heat storage strategies corresponding to the characteristic segment reference group includes:

[0087] Step S301, according to the time relationship, the feature segment reference groups in the same preset monitoring period (for example, one day, a day is divided into morning, afternoon and evening, and the electricity and heat score requirements are different at different times) are sorted to form a feature segment reference group sequence.

[0088] In step S301, the characteristic segment reference groups within the same preset monitoring period (such as different time periods in a day) are sorted according to the time sequence. The purpose of this is to understand the energy demand pattern in different time periods and form an ordered sequence of characteristic segment reference groups. This sequence will serve as the basis for subsequent strategy adjustments.

[0089] Step S302, based on the time difference between the electricity demand and the heat demand in the preset monitoring period, the preset monitoring period is time segmented, and based on the time segmentation of the preset monitoring period, the feature segment reference groups in the feature segment reference group sequence are classified.

[0090] In step S302, the monitoring period is time segmented according to the time difference between the electricity demand and the heat demand in the preset monitoring period. For example, a day can be divided into morning, afternoon and evening, because the electricity demand and heat demand in different time periods may be significantly different. Based on these time segments, the feature segment reference groups in the feature segment reference group sequence are classified to facilitate strategy adjustment according to the demand characteristics of different time periods.

[0091] Step S303, calculate the total user electricity demand and the total user heat demand corresponding to the characteristic reference group in each time segment. If the total user electricity demand corresponding to the characteristic reference group at a later time is greater than that of the characteristic reference group at an earlier time, and the difference is greater than or equal to the preset value, the electricity storage parameters in the electricity storage and heat storage strategies are increased, otherwise the electricity storage parameters in the electricity storage and heat storage strategies are reduced. If the total user heat demand corresponding to the characteristic parameter group at a later time is greater than that of the characteristic parameter group at an earlier time, and the difference is greater than or equal to the preset value, the heat storage parameters in the electricity storage and heat storage strategies are increased, otherwise the heat storage parameters in the electricity storage and heat storage strategies are reduced.

[0092] In step S303, the total amount of user electricity demand and the total amount of user heat demand corresponding to the characteristic reference group in each time segment are calculated. By comparing the total amount of demand in different time segments, the changing trend of demand can be identified. If it is found that the total amount of user electricity demand of a characteristic reference group at a later time is greater than that of the previous time period, and this difference exceeds the preset threshold, then the power storage parameter in the power storage strategy is increased to store more electricity to meet the increased demand. Conversely, if the demand decreases, the power storage parameter is reduced. The same principle applies to the heat storage parameter in the heat storage strategy.

[0093] In some embodiments disclosed in the present invention, based on preset energy supply and heat supply evaluation rules, a method for evaluating each first reference strategy includes:

[0094] Step S304, based on the relationship between the total electricity demand of users and the total heat demand of users, the feature segment reference groups are sorted, and several feature reference groups with higher rankings are selected as feature reference groups for evaluation.

[0095] Step S305, establishing a time node sequence, and based on the time node sequence, mapping the user electricity demand parameter sequence, user heat demand parameter sequence, electricity storage parameter sequence and heat storage parameter sequence of the evaluation feature reference group.

[0096] Step S306, based on the continuous performance characteristics of the user electricity demand parameter sequence and the electricity storage parameter sequence, determine the first sub-evaluation of the first reference strategy, based on the continuous performance characteristics of the user heat demand parameter sequence and the heat storage parameter sequence, determine the second sub-evaluation of the first reference strategy.

[0097] Step S307 , respectively configuring weight coefficients for the first sub-evaluation and the second sub-evaluation corresponding to each evaluation feature reference group, and summing them up to determine a comprehensive evaluation of the corresponding first reference strategy.

[0098] Among them, the sub-evaluation expression for determining the first sub-evaluation or the second sub-evaluation is:

[0099] .

[0100] in, is the corresponding value of the first sub-evaluation or the corresponding value of the second sub-evaluation, is the sub-evaluation conversion coefficient, which is adjusted according to the time segment to which the feature reference group belongs. The later the time segment, the The bigger, is the power storage supply effectiveness judgment function, if is greater than or equal to the preset value, then Output 1, otherwise output 0. is the x-order electrical storage parameter or heat storage parameter, is the x-1th order electrical storage parameter or thermal storage parameter, are the electricity demand parameters and heat demand parameters of the xth order, is the number of parameters in the sequence, Adjustment constant for sub-evaluation.

[0101] Step S400, the current operating parameter data and the current demand parameter data are compared with different feature segment reference groups in turn for similarity, and based on the comparison results, the most suitable feature segment reference group is determined, and the second reference strategy corresponding to the most suitable feature segment reference group is identified as the current control strategy for the energy storage system and the heat storage system.

[0102] In step S400, the current operating parameter data and demand parameter data are compared with the previously determined feature segment reference group for similarity; this involves comparing the current system state with the patterns in the historical data to find the most matching feature segment reference group; once the most suitable feature segment reference group is found, its corresponding second reference strategy is identified as the current control strategy, which is used to guide the real-time operation of the energy storage system and the heat storage system.

[0103] In some embodiments disclosed in the present invention, the method of comparing the current operating parameter data and the current demand parameter data with different feature segment reference groups in sequence for similarity includes:

[0104] Step S401, analyzing the current operating parameter data and the current demand parameter data to obtain the current operating parameter expression model and the current demand parameter expression model.

[0105] Step S402 : performing feature dimensionality reduction on the feature segment reference group. The feature dimensionality reduction method includes determining the change trend of each performance feature segment in the feature segment reference group at different time nodes to obtain a change trend sequence.

[0106] Step S403 , based on the matching performance of the change trend sequence and the current operation parameter performance model and the current demand parameter performance model, the feature segment reference group is screened for the first time.

[0107] Step S404: Overlap and compare the operating parameter performance feature segments in the filtered feature segment reference group with the current operating parameter performance model, and calculate a first difference reference area between the two.

[0108] Step S405: Overlap and compare the demand parameter performance feature segments in the filtered feature segment reference group with the current demand parameter performance model, and calculate a second difference reference area between the two.

[0109] Step S406, based on the type of the operating parameter, configure a first attention weight coefficient for the first difference reference area to construct a first difference operator, and based on the type of the demand parameter, configure a second attention coefficient for the second difference reference area to construct a second difference operator.

[0110] Step S407, based on the first difference operator and the second difference operator, calculate the difference degree corresponding to the feature segment reference group, and filter out several feature segment reference groups whose difference degree is less than or equal to the preset value, and identify the second reference strategy corresponding to the filtered feature segment reference group as the current control strategy for the energy storage system and the heat storage system.

[0111] In some embodiments disclosed in the present invention, a water, electricity and heating supply management system based on PVT cogeneration is also disclosed, including:

[0112] The first module is used to analyze the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and to express the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model.

[0113] The second module is used to perform characteristic performance analysis on the operating parameter performance model and the demand parameter performance model, and based on the analysis results, respectively perform characteristic segment interception on the operating parameter performance model and the demand parameter performance model to obtain operating parameter performance characteristic segments and demand parameter performance characteristic segments, and record the combination of the operating parameter performance characteristic segments and the demand parameter performance characteristic segments as a characteristic segment reference group.

[0114] The third module is used to optimize and adjust the electricity storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a number of first reference strategies, and evaluate each first reference strategy based on preset energy supply and heat supply evaluation rules, and screen out a number of second reference strategies based on the evaluation results.

[0115] The fourth module is used to compare the current operating parameter data and the current demand parameter data with different feature segment reference groups in turn for similarity, and based on the comparison results, determine the most suitable feature segment reference group, and identify the second reference strategy corresponding to the most suitable feature segment reference group as the current control strategy for the energy storage system and the heat storage system.

[0116] The present invention discloses a water, electricity and heating supply management method and system based on PVT cogeneration, which relates to the technical field of PVT cogeneration, and specifically discloses recording a combination of an operating parameter performance characteristic segment and a demand parameter performance characteristic segment as a characteristic segment reference group, optimizing and adjusting the power storage and heat storage strategies corresponding to the characteristic segment reference group, obtaining a plurality of first reference strategies, screening out a plurality of second reference strategies based on evaluation results, determining the most suitable characteristic segment reference group based on comparison results, and identifying the second reference strategy corresponding to the most suitable characteristic segment reference group as the current control strategy for the energy storage system and the heat storage system. The above technical scheme of the present invention realizes the optimization of the power storage and heat storage strategies, and determines the most suitable reference strategy by data comparison, thereby realizing the control optimization of the energy storage system and the heat storage system.

[0117] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A water, electricity and heating supply management method based on PVT cogeneration, characterized in that: include: Analyze the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and express the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model; Performing characteristic performance analysis on the operation parameter performance model and the demand parameter performance model, and based on the analysis results, respectively performing characteristic segment interception on the operation parameter performance model and the demand parameter performance model to obtain the operation parameter performance characteristic segment and the demand parameter performance characteristic segment, and recording the combination of the operation parameter performance characteristic segment and the demand parameter performance characteristic segment as a characteristic segment reference group; Optimize and adjust the electricity storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a number of first reference strategies, and evaluate each first reference strategy based on preset energy supply and heat supply evaluation rules, and select a number of second reference strategies based on the evaluation results; The current operating parameter data and the current demand parameter data are sequentially compared with different characteristic segment reference groups for similarity, and based on the comparison results, the most suitable characteristic segment reference group is determined, and the second reference strategy corresponding to the most suitable characteristic segment reference group is identified as the current control strategy for the energy storage system and the heat storage system; Methods for expressing operation parameter data and demand parameter data in the time dimension include: The operating parameter data include PVT power generation parameters and PVT heat generation parameters at different time nodes, and the demand parameter data include user power demand parameters, user heat demand parameters and power grid power demand parameters at different time nodes. Curve expression models with time as the horizontal axis coordinate and parameter as the vertical axis coordinate are constructed respectively to obtain the PVT power generation parameter curve expression model, the PVT heat generation parameter curve expression model, the user power demand parameter curve expression model, the user heat demand parameter curve expression model and the power grid power demand parameter curve expression model; The method for optimizing and adjusting the electricity storage and heat storage strategies corresponding to the characteristic segment reference group includes: According to the time relationship, the feature segment reference groups in the same preset monitoring period are sorted to form a feature segment reference group sequence; Based on the time difference between the electricity demand and the heat demand in the preset monitoring period, the preset monitoring period is time segmented, and based on the time segmentation of the preset monitoring period, the characteristic segment reference groups in the characteristic segment reference group sequence are classified; Calculate the total electricity demand and heat demand of users corresponding to the characteristic reference group in each time segment. If the total electricity demand of users corresponding to the characteristic reference group at a later time is greater than that of the characteristic reference group at an earlier time, and the difference is greater than or equal to the preset value, the electricity storage parameters in the electricity storage and heat storage strategies are increased, otherwise the electricity storage parameters in the electricity storage and heat storage strategies are reduced. If the total heat demand of users corresponding to the characteristic parameter group at a later time is greater than that of the characteristic parameter group at an earlier time, and the difference is greater than or equal to the preset value, the heat storage parameters in the electricity storage and heat storage strategies are increased, otherwise the heat storage parameters in the electricity storage and heat storage strategies are reduced.

2. The water, electricity and heating supply management method based on PVT cogeneration according to claim 1 is characterized in that: The method for performing characteristic performance analysis on the operation parameter performance model and the demand parameter performance model includes: Dynamic analysis nodes are set for the PVT power generation parameter curve expression model, the PVT heat generation parameter curve expression model, the user power demand parameter curve expression model, the user heat demand parameter curve expression model and the power grid power demand parameter curve expression model respectively, and the time nodes corresponding to the dynamic analysis nodes on each curve expression model are the same; Taking the dynamic analysis node as the center, a first interception section is constructed for the PVT power generation parameter curve expression model, a second interception section is constructed for the PVT heat generation parameter curve expression model, a third interception section is constructed for the user power demand parameter curve expression model, a fourth interception section is constructed for the user heat demand parameter curve expression model, and a fifth interception section is constructed for the user power demand parameter curve expression model; A pre-analysis section is set for each curve performance model, and the factors requiring attention of the curve performance model are analyzed in the pre-analysis section with the dynamic analysis node as the center. Based on the performance of the factors requiring attention, the interception length of the interception section corresponding to the curve performance model is determined.

3. The water, electricity and heating supply management method based on PVT cogeneration according to claim 2 is characterized in that: The method for determining the interception length of the interception section corresponding to the curve representation model includes: The number of curve inflection points in the pre-analysis section on the curve performance model and the rate of change of the amplitude between the curve inflection points; An effective information parameter operator is constructed based on the number of curve inflection points and the amplitude change rate between the curve inflection points, and an initial interception length of the interception section is determined based on the effective information parameter operator; Perform a rationality test on the initial intercept length. The rationality test includes taking the initial intercept length, the number of curve inflection points and the curve change rate as screening conditions, randomly screening out a number of equivalent curve performance models, and comparing the difference variances between the curve performance models. If the difference variance is less than or equal to the preset value, the initial intercept length is identified as the applied intercept length, otherwise the initial intercept length is amplified by a preset ratio; Among them, the method for comparing the difference variances between curve expression models includes: randomly combining the curve expression models in pairs to obtain several curve expression model comparison groups, and calculating the average difference in the vertical coordinates in each curve expression model comparison group, and based on the average difference in the vertical coordinates, calculating the difference variance about the average difference in the vertical coordinates.

4. The water, electricity and heating supply management method based on PVT cogeneration according to claim 3 is characterized in that: The expression for calculating the initial intercept length is: ； in, is the initial intercept length, is the intercept length conversion factor, is the preset standard valid information parameter, is the amplitude change rate judgment function. If the amplitude change rate of the i-th curve inflection point is greater than or equal to the preset value, the ratio of the amplitude change rate to the preset value is output, and b is the parameter adjustment constant.

5. The water, electricity and heating supply management method based on PVT cogeneration according to claim 4 is characterized in that: Based on the preset energy supply and heat supply evaluation rules, the method for evaluating each first reference strategy includes: Based on the relationship between the total electricity demand of users and the total heat demand of users, the characteristic segment reference groups are sorted, and several characteristic reference groups with the highest order are selected as the characteristic reference groups for evaluation; Establishing a time node sequence, and based on the time node sequence, mapping a user electricity demand parameter sequence, a user heat demand parameter sequence, an electricity storage parameter sequence, and a heat storage parameter sequence to the evaluation feature reference group; Determine a first sub-evaluation of the first reference strategy based on the continuous performance characteristics of the user's electricity demand parameter sequence and the electricity storage parameter sequence, and determine a second sub-evaluation of the first reference strategy based on the continuous performance characteristics of the user's heat demand parameter sequence and the heat storage parameter sequence; The weight coefficients are respectively configured for the first sub-evaluation and the second sub-evaluation corresponding to each evaluation feature reference group, and the weight coefficients are summed to determine the comprehensive evaluation of the corresponding first reference strategy; Among them, the sub-evaluation expression for determining the first sub-evaluation or the second sub-evaluation is: ； in, is the corresponding value of the first sub-evaluation or the corresponding value of the second sub-evaluation, is the sub-evaluation conversion coefficient, which is adjusted according to the time segment to which the feature reference group belongs. The later the time segment, the The bigger, is the power storage supply effectiveness judgment function, if is greater than or equal to the preset value, then Output 1, otherwise output 0. is the x-order electrical storage parameter or heat storage parameter, For the Sequential electrical storage parameters or heat storage parameters, are the electricity demand parameters and heat demand parameters of the xth order, is the number of parameters in the sequence, Adjustment constant for sub-evaluation.

6. The water, electricity and heating supply management method based on PVT cogeneration according to claim 1 is characterized in that: The method of comparing the current operating parameter data and the current demand parameter data with different characteristic segment reference groups in sequence for similarity includes: Analyze the current operating parameter data and the current demand parameter data to obtain the current operating parameter performance model and the current demand parameter performance model; Performing feature dimensionality reduction on the feature segment reference group, wherein the feature dimensionality reduction method includes determining the change trend of each performance feature segment in the feature segment reference group at different time nodes to obtain a change trend sequence; Based on the matching performance of the change trend sequence and the current operation parameter performance model and the current demand parameter performance model, the characteristic segment reference group is screened for the first time; Overlapping and comparing the operating parameter performance characteristic segments in the screened characteristic segment reference group with the current operating parameter performance model, and calculating a first difference reference area between the two; Overlap and compare the demand parameter performance characteristic segments in the filtered characteristic segment reference group with the current demand parameter performance model, and calculate the second difference reference area between the two; Based on the type of the operating parameter, a first attention weight coefficient is configured for the first difference reference area to construct a first difference operator, and based on the type of the demand parameter, a second attention coefficient is configured for the second difference reference area to construct a second difference operator; Based on the first difference operator and the second difference operator, the difference degree corresponding to the feature segment reference group is calculated, and several feature segment reference groups whose difference degree is less than or equal to the preset value are screened out, and the second reference strategy corresponding to the screened feature segment reference group is identified as the current control strategy for the energy storage system and the heat storage system.

7. The water, electricity and heating supply management system based on PVT cogeneration is characterized by: The method for managing water, electricity and heating supply according to any one of claims 1 to 6 comprises: The first module is used to analyze the operation log of the PVT cogeneration system to obtain a number of operation parameter data and demand parameter data, and to express the operation parameter data and demand parameter data in the time dimension to obtain an operation parameter expression model and a demand parameter expression model; The second module is used to perform characteristic performance analysis on the operation parameter performance model and the demand parameter performance model, and based on the analysis results, respectively perform characteristic segment interception on the operation parameter performance model and the demand parameter performance model to obtain the operation parameter performance characteristic segment and the demand parameter performance characteristic segment, and record the combination of the operation parameter performance characteristic segment and the demand parameter performance characteristic segment as a characteristic segment reference group; The third module is used to optimize and adjust the power storage and heat storage strategies corresponding to the characteristic segment reference group to obtain a plurality of first reference strategies, and evaluate each first reference strategy based on the preset energy supply and heat supply evaluation rules, and select a plurality of second reference strategies based on the evaluation results; The fourth module is used to compare the current operating parameter data and the current demand parameter data with different feature segment reference groups in turn for similarity, and based on the comparison results, determine the most suitable feature segment reference group, and identify the second reference strategy corresponding to the most suitable feature segment reference group as the current control strategy for the energy storage system and the heat storage system.

Images