Cooperative regulation and control method of building energy system

Abstract

The invention belongs to the technical field of building energy management, and provides a cooperative regulation and control method for a building energy system, and the method comprises the steps: obtaining the dynamic response features of a heterogeneous energy subsystem, constructing a feature matrix, and determining a response system group with the highest coupling contribution degree through cross-correlation analysis; secondly, a load mutation model is constructed based on historical data and a genetic algorithm, a periodic step load scene is simulated, and the cooperative response mismatch degree between subsystems is evaluated; performing correlation analysis on communication protocol isomerism, and identifying dominant mismatch factors by using a random forest algorithm and classifying the dominant mismatch factors; and finally, aiming at physical characteristic dominant mismatch, dynamically constructing a compensation strategy, and sensing and inhibiting a ripple diffusion effect of load mutation through a state equation and recursive filtering. According to the invention, cooperative regulation and control among the subsystems of the building energy system are realized, and the robustness of the system for dealing with sudden load change and the energy utilization efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of building energy management, and specifically relates to a coordinated control method for a building energy system. Background Art

[0002] In the field of building energy systems, as the integration of heterogeneous subsystems such as electricity, HVAC, and lighting continues to increase, coordinated regulation under load mutation scenarios (such as switching between events in large venues and peak and valley load fluctuations in commercial buildings) faces many challenges.

[0003] Existing technologies rely heavily on experience to set parameters in mutation simulations, without combining historical data and genetic algorithms to construct constraints. They are unable to truly restore periodic step load scenarios (such as sudden load changes during halftime in sports stadiums). At the same time, mismatch assessments lack quantitative indicators (such as mismatch coverage ratio and coupling deviation ratio), making it difficult to locate the specific time periods and extent of subsystem response asynchrony.

[0004] Faced with the chain reaction of subsystems caused by sudden load changes, existing technologies lack a dynamic timing compensation mechanism, are unable to cut off the mutation propagation chain in real time, and are difficult to improve the stability of the energy system.

[0005] To this end, the present invention provides a coordinated control method for a building energy system. Summary of the Invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve the technical problem is: a coordinated control method for a building energy system, comprising: Obtain the dynamic response characteristics of heterogeneous energy subsystems in the building, construct a dynamic response characteristic matrix, conduct coupling analysis on the dynamic response characteristics of any two subsystems based on the dynamic response characteristic matrix, and determine the response system group; Obtain the load data of the subsystems and combine it with the dynamic response characteristic matrix to simulate the load mutation of the response system group's periodic step load scenario and evaluate the degree of coordinated response mismatch between subsystems; Based on the degree of response mismatch between subsystems, the heterogeneity of subsystem communication protocols and physical dynamic characteristics are correlated and analyzed to identify the dominant mismatch factor and determine whether the mismatch type corresponding to the mismatch factor is the dominant type. If the mismatch is dominated by physical characteristics, a timing compensation strategy is dynamically constructed to generate targeted instruction precompilation and dynamic timing alignment solutions, obtain a dynamic timing alignment instruction sequence, and track the coordinated state of the subsystems after compensation to perceive and suppress the ripple diffusion effect of load mutations.

[0008] As a further technical solution of the present invention: the method for determining the response system group is: Extract the response characteristics of any two subsystems from the dynamic response characteristic matrix and construct the corresponding response characteristic sequences respectively; Perform cross-correlation analysis on the response characteristic sequences of any two subsystems and obtain the correlation coefficient corresponding to the maximum delay lag value as the coupling contribution; Obtain the two groups of subsystems with the highest coupling contribution and construct the response system group.

[0009] As a further technical solution of the present invention: the method for evaluating the degree of mismatch between the coordinated responses of the subsystems is: Construct a load mutation model, obtain historical load constraints, and input the historical load constraints into the load mutation model. Set a simulation cycle to perform load mutation simulation on the response system group, and extract the response characteristics of the response system group after the load mutation simulation. Obtaining the response characteristics of two subsystems in the response system group of multiple simulation cycles, respectively constructing a response characteristic sequence of the simulation output of each subsystem to obtain a characteristic simulation sequence; Perform response mismatch analysis on the characteristic simulation sequence and extract the simulation mismatch segments within all simulation cycles: Extract the mismatch coverage ratio and coupling deviation ratio of the simulated mismatch segment, and calculate the cooperative mismatch coefficient of the response system group based on the mismatch coverage ratio and coupling deviation ratio; The degree of synergistic response mismatch between subsystems within a response system group is evaluated based on the synergistic mismatch coefficient.

[0010] As a further technical solution of the present invention: the method for obtaining the historical load constraint condition is: Obtain historical load data of the building energy system and identify the step load mutation characteristics of periodic step load scenarios; Based on the periodic step load mutation characteristics, the historical load constraint conditions with historical step load mutation characteristics are constructed through genetic algorithm.

[0011] As a further technical solution of the present invention: the method of extracting the mismatch coverage ratio and coupling deviation ratio of the simulated mismatch segment is: Obtain the single duration period of the simulation mismatch segment and the single duration period of the periodic step load scenario; The coverage ratio of a single duration period of the simulated mismatch segment and a single duration period of the periodic step load scenario is calculated to obtain the mismatch coverage ratio. The coupling contribution peak value of a single duration period of the characteristic simulation sequence in the simulation mismatch segment is obtained, and the deviation ratio between the coupling contribution peak value and the target boundary of the coupling contribution is calculated to obtain the coupling deviation ratio.

[0012] As a further technical solution of the present invention: the method of identifying the dominant mismatch factor is: If there is a mismatch risk in the coordinated response between subsystems within the response system group, the historical communication characteristics of each subsystem in the response system group are obtained from the log of the building energy system and input into the load mutation model; Among them, historical communication characteristics include communication delay peak and protocol compatibility index; Obtain the communication characteristic sequences of all simulated mismatch segments and the characteristic simulation sequences of the subsystems, construct a mismatch factor matrix, and classify the mismatch factors into mismatch types; A synergistic factor model was constructed based on the random forest algorithm, and the mismatch factor matrix was input into the synergistic factor model to extract the mismatch dominant factor. A matching correspondence analysis is performed based on the mismatch dominant factor to determine whether the mismatch type corresponding to the mismatch factor is the dominant type.

[0013] As a further technical solution of the present invention: the matching correspondence analysis is performed as follows: Perform simulation verification based on the mismatch dominant factor and the corresponding mismatch type, optimize the mismatch dominant factor, and output the optimized synergistic mismatch coefficient; Calculate the deviation of the synergistic mismatch coefficient before and after optimization, perform type matching evaluation on the optimization results, and determine whether the mismatch type corresponding to the mismatch factor is the dominant type.

[0014] As a further technical solution of the present invention: the method of dynamically constructing the timing compensation strategy is: Precompile control instructions based on the load mutation model of the building energy subsystem; Dynamic timing alignment is performed based on the timing deviation characteristics of the simulated mismatch segment; Perform load smoothing on the sudden amplitude overload and build dynamic timing alignment instructions.

[0015] As a further technical solution of the present invention, the method of sensing and suppressing the ripple diffusion effect of the load mutation is: Obtain the load change and coupling contribution of the subsystems in the response system group after tracking compensation, and construct the load mutation vector and coupling strength matrix; Construct a ripple effect propagation equation and perform recursive filtering based on historical parameters to implement the ripple effect triggering criteria; After determining that a ripple effect occurs, the instruction timing is adjusted to the subsystem to suppress the ripple effect.

[0016] As a further technical solution of the present invention: the method for realizing the triggering criterion of the ripple effect is: Establish the system state vector and mutation impact coefficient vector of the response system group, and construct the ripple effect propagation equation by combining the load mutation vector and coupling strength matrix; Recursively filter the ripple effect propagation equation and calculate the Euclidean distance deviation value of the system state vector; When the Euclidean distance deviation value is higher than the preset Euclidean distance deviation threshold, it is determined that there is a ripple effect between the subsystems. The beneficial effects of the present invention are as follows: 1. By acquiring dynamic characteristics such as the transient response ratio of the power subsystem, the energy efficiency fluctuation rate of the HVAC subsystem, and the response delay ratio of the lighting subsystem, a multidimensional feature matrix is constructed. The coupling contribution between subsystems is quantified based on cross-correlation analysis, facilitating the precise identification of groups of closely synergistic response systems. This improves the targeted nature of system analysis, reduces ineffective regulation of weakly correlated subsystems, and mitigates deviations in regulation strategies caused by fuzzy factor system coupling relationships, providing a basis for object screening for subsequent load mutation simulations.

[0017] 2. By identifying the characteristics of periodic step loads and combining genetic algorithms to construct historical load constraints, the load mutation model is simulated and the mismatch coverage ratio, coupling deviation ratio, and coordinated mismatch coefficient are calculated. This helps to reproduce realistic load mutation scenarios (such as the step load during halftime in a stadium) and improves the accuracy of mismatch risk assessment. By quantifying the mismatch coverage ratio and coupling deviation ratio, it is easier to locate the period and degree of subsystem response asynchrony, reducing the assessment errors caused by traditional empirical judgment and providing data support for mismatch type analysis.

[0018] 3. Correlating historical communication features with simulated mismatch segments to construct a communication feature sequence, this is then combined with a random forest algorithm to classify mismatch types and extract dominant factors. This facilitates analysis of the root causes of mismatches. For example, by cross-analyzing communication delays and physical response parameters, the specific issue of delayed HVAC response caused by protocol conversion delays can be pinpointed. This classification process improves the targeted nature of control strategies, while optimizing mismatch factors through simulation verification enhances the reliability of identifying dominant factors.

[0019] 4. Precompile control instructions based on the load mutation model, dynamically adjust timing alignment, smooth overload mutations, and suppress ripple propagation through state equations and recursive filtering. This helps reduce the impact of load mutations on the system and improves the synchronization of subsystem responses. By tracking the coordinated state in real time and implementing command control, it helps to cut off the mutation propagation chain, reduce the global chain reaction caused by load mutations, and improve the operational stability and energy utilization efficiency of the building energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention will be further described below with reference to the accompanying drawings.

[0021] Figure 1This is a flowchart of the steps of a coordinated control method for a building energy system according to an embodiment of the present invention; Figure 2 is a flowchart of the steps of collaborative mismatch analysis according to an embodiment of the present invention; Figure 3 This is a module architecture diagram of a collaborative control system for a building energy system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0023] Example 1 See also Figure 1 As shown, a coordinated control method of a building energy system according to an embodiment of the present invention includes the following steps: Step 1: Obtain the dynamic response characteristics of the heterogeneous energy subsystems in the building, construct a dynamic response characteristic matrix, perform coupling analysis on the dynamic response characteristics of any two subsystems based on the dynamic response characteristic matrix, and determine the response system group; Preferably, the heterogeneous energy subsystems in the building include power, HVAC, and lighting subsystems; Among them, the method of quantifying the dynamic response characteristics of each subsystem is: Preferably, the heterogeneous energy subsystems in the building include power, HVAC, and lighting subsystems; Obtain the transient response ratio of the power subsystem, the energy efficiency fluctuation rate of the HVAC subsystem, and the response delay ratio of the lighting subsystem during the historical monitoring period as the response characteristics of each subsystem; It is understood that during the historical monitoring period, the voltage and current transient response data of the power subsystem during sudden load changes are collected in real time through sensors, and compared with the reference values under rated operating conditions to calculate the transient response ratio. The input power and output energy efficiency data of the HVAC subsystem are simultaneously obtained, and the energy efficiency fluctuation rate is calculated based on the fluctuation amplitude of the energy efficiency index per unit time using the standard deviation or coefficient of variation. For the lighting subsystem, the time difference between the time the control command is sent and the time the lamp actually reaches the target state is recorded, and the ratio of this delay time to the standard response time is used as the response delay ratio. Construct a dynamic response characteristic matrix that includes the transient response ratio of the power subsystem, the energy efficiency fluctuation rate of the HVAC subsystem, and the response delay ratio of the lighting subsystem within multiple monitoring periods; Conduct coupling analysis on heterogeneous energy subsystems within the building based on the dynamic response characteristic matrix to determine the coupling contribution between different subsystems; Among them, the coupling analysis method for heterogeneous energy subsystems in buildings is as follows: Extract the response characteristics of any two subsystems from the dynamic response characteristic matrix and construct the corresponding response characteristic sequences respectively; Perform cross-correlation analysis on the response characteristic sequences of any two subsystems and obtain the correlation coefficient corresponding to the maximum delay lag value as the coupling contribution; Those skilled in the art will understand that the cross-correlation analysis calculates the correlation between the response characteristic sequences of the two subsystems at different time delays to obtain a correlation coefficient sequence. The correlation coefficient corresponding to the maximum delay lag value indicates that the response characteristic sequences of the two subsystems have the highest matching degree at this time delay lag. It is important to explain that the coupling contribution quantifies the strength of the temporal correlation between the dynamic responses of subsystems, reflecting the degree to which a sudden load change or response deviation in one subsystem affects the other. A higher coupling contribution value indicates a stronger degree of synergistic coupling between the two subsystems in load-sudden scenarios (e.g., a more significant mutual influence between power fluctuations and the start-up and shutdown of HVAC equipment). This is a core quantitative indicator for identifying key synergistic pathways in building energy systems, providing a physical basis for selecting responsive system groups (e.g., the power-HVAC subsystem with the highest coupling contribution). Obtain the two groups of subsystems with the highest coupling contribution and construct the response system group.

[0024] Step 2: Obtain the load data of the subsystems and combine it with the dynamic response characteristic matrix to simulate the load mutation of the periodic step load scenario of the response system group and evaluate the degree of cooperative response mismatch between the subsystems; The method for simulating load mutation is as follows: Obtain historical load data of the building energy system and identify the step load mutation characteristics of periodic step load scenarios; Exemplary, periodic step load scenarios include halftime scenarios of events at large sports stadiums; It can be understood that historical load data of the power, HVAC, and lighting subsystems are extracted from the building energy system. The historical load data are used to identify similar mutation patterns of the power, HVAC, and lighting subsystems through the DBSCAN clustering algorithm to identify the step load mutation characteristics of periodic step load scenarios; Among them, historical load data includes: power and HVAC load time series, step load mutation characteristics include: load mutation amplitude P(t) and mutation time t; The step load mutation characteristics are correlated with the coupling contribution sequence of the response system group to extract the periodic step load scenarios associated with the existence; Based on the periodic step load mutation characteristics, the historical load constraint conditions of the historical step load mutation characteristics are constructed through genetic algorithm; Preferably, the method of constructing the historical load constraint condition of the historical step load mutation characteristic by the genetic algorithm is as follows: S201, chromosome encoding and parameter definition; Preferably, the load mutation amplitude, mutation rate, and duration of each subsystem are mapped to the chromosome structure of the genetic algorithm, and the physical meaning of each gene bit is defined by real number coding (for example, the first bit represents the power subsystem mutation amplitude, and the range is set to 0-120% of the rated value); At the same time, the mutation rate does not exceed the maximum slope allowed by the device as a limiting parameter boundary, so that the chromosome directly corresponds to the quantifiable characteristics of the load mutation, providing an optimization object for subsequent genetic iterations; S202, constructing a comprehensive fitness function based on the historical load data fitting function and the coupling contribution matching function; Through formula 1: Construct the historical load data fitting function F1; Through formula 2: Construct coupling contribution matching function F2; Through formula three: Construct comprehensive fitness function F; in, are the simulated load mutation amplitude and historical load mutation amplitude at time t, is the preset fitness control factor, T is the total length of the time series for monitoring load mutation characteristics, m is the total number of pairwise combinations of subsystems in the building energy system, and the index identifiers of subsystems i and j are; The coupling contribution between the i-th subsystem and the j-th subsystem in the load mutation scenario and the coupling contribution between the i-th subsystem and the j-th subsystem in the historical load mutation scenario are simulated respectively; S203, genetic algorithm training and iteration; Preferably, a population containing several chromosomes (e.g., 50 to 100, with randomly generated parameter combinations) is initialized, and the quality of each chromosome is calculated using the comprehensive fitness function of S202; high-quality individuals are selected using roulette wheel selection and elite retention strategies, and a new population is generated by linearly combining parent parameters to generate offspring and Gaussian mutation; Repeat the fitness calculation, selection, crossover, and mutation process until the maximum number of iterations reaches 200 generations, and finally output the chromosome with the highest fitness, corresponding to the optimal load mutation parameter combination; S204, generating historical load constraint conditions; Preferably, the load mutation constraint condition is extracted from the optimal chromosome output by the genetic algorithm; Among them, the constraints include: target boundaries of load mutation amplitude, rate, duration, and coupling contribution; Construct a load mutation model, input historical load constraints into the load mutation model, set a simulation cycle to simulate the load mutation of the response system group, and extract the response characteristics of the response system group after the load mutation simulation; Those skilled in the art will appreciate that the transient circuit equations of the power subsystem, the thermal balance equations of the HVAC subsystem, and the control logic of the lighting subsystem are integrated to form a multi-physical domain coupled load mutation model; Input historical load constraints into the load mutation model, use the historical load data optimized by the genetic algorithm as the model's excitation source boundary conditions, and according to the time scale of the historical load mutation (for example, a 30-minute load sudden change scenario during halftime at a stadium, set the simulation cycle to 30 minutes and refine the time step to the second level to capture transient responses); For highly synergistic subsystem groups selected by coupling contribution, load mutation excitation is injected into the model to simulate the dynamic interactive response of the subsystems under sudden shock. Through the model's built-in data acquisition module, the characteristic sequences of power transient response ratio, HVAC energy efficiency fluctuation rate, and lighting response delay ratio in the simulation time series are tracked in real time, providing dynamic data support for subsequent mismatch assessment. Obtaining the response characteristics of two subsystems in the response system group of multiple simulation cycles, respectively constructing a response characteristic sequence of the simulation output of each subsystem to obtain a characteristic simulation sequence; Among them, the method for evaluating the mismatch degree of coordinated response between response system groups is: Perform response mismatch analysis on the characteristic simulation sequence and extract the simulation mismatch segments within all simulation cycles; Obtain the single duration period of the simulation mismatch segment and the single duration period of the periodic step load scenario; The coverage ratio of a single duration period of the simulated mismatch segment and a single duration period of the periodic step load scenario is calculated to obtain the mismatch coverage ratio. Obtain the coupling contribution peak value of a single duration period of the characteristic simulation sequence in the simulation mismatch segment, calculate the deviation ratio between the coupling contribution peak value and the target boundary of the coupling contribution, and obtain the coupling deviation ratio; Calculate the cooperative mismatch coefficient of the response system group based on the mismatch coverage ratio and the coupling deviation ratio; Preferably, by the formula: Obtaining the synergy mismatch coefficient M; in, is the number of the simulated mismatch segment, N is the total number of simulated mismatch segments, Respectively The mismatch coverage ratio of the simulated mismatch segment, Coupling deviation ratio of the simulated mismatch segment; It can be understood that the synergy mismatch coefficient quantifies the degree of overall synergy deviation of the response system group under load mutation scenario; The purpose of calculating the synergy mismatch coefficient is: Objective 1: To verify the effectiveness of the simulation scenario, the coordination mismatch coefficient is compared with the deviation between the calculated value of the simulation scenario and the measured value of the historical scenario to determine the load mutation model's ability to reproduce the real multi-subsystem coordination mismatch law; Objective 2: As a basis for formulating the timing of control strategies, the timing characteristics of the coordination mismatch coefficient (such as peak occurrence time and fluctuation period) can guide the timing arrangement of control commands. If the coefficient reaches its peak 10 seconds after the load mutation, it indicates that the coordination mismatch of the subsystems is the most serious during this period. The control strategy can be pre-set with timing logic to pre-issue control commands 1 second in advance. Objective 3: Locate the root cause of mismatch. The synergy mismatch coefficient supports the quantitative decomposition of subsystem contributions to coupling. By calculating the coupling mismatch weights of different subsystem pairs (such as power-HVAC, power-lighting), it is possible to directly locate the synergy deviation between subsystems as the dominant factor in the overall mismatch, improving the efficiency of problem location. like Figure 2 As shown, the degree of mismatch in the coordinated response between subsystems within the response system group is evaluated based on the coordinated mismatch coefficient. If the coordinated mismatch coefficient is not within the preset coordinated mismatch coefficient range, it is considered that there is a mismatch risk in the coordinated response between subsystems within the response system group. If the synergy mismatch coefficient is within a preset synergy mismatch coefficient range, the change of the synergy mismatch coefficient is continuously monitored.

[0025] Example 2 like Figure 1 As shown, a coordinated control method for a building energy system further includes the following steps: Step 3: Based on the response mismatch degree between subsystems, perform correlation analysis on the heterogeneity of subsystem communication protocols and physical dynamic characteristics, identify the dominant mismatch factor, and determine whether the mismatch type corresponding to the mismatch factor is the dominant type; Among them, the method of correlating the heterogeneity of subsystem communication protocols with physical dynamic characteristics is as follows: Preferably, if there is a mismatch risk in the coordinated response between subsystems in the response system group, the historical communication characteristics of each subsystem in the response system group are obtained from the log of the building energy system and input into the load mutation model; Among them, historical communication characteristics include communication delay peak and protocol compatibility index; The load mutation model associates the communication characteristics with all simulation mismatch segments to construct a communication characteristic sequence; It should be explained that the protocol compatibility index is calculated by parsing or capturing packets to analyze the matching load of data format, instruction set, timing rules, and error handling dimensions, and then summing them up to obtain the protocol compatibility index. The mutation model associates the communication features with all the simulated mismatch segments by extracting the communication features and their corresponding timestamps from the building energy system logs, and performing spatiotemporal alignment with the simulated mismatch segments based on the timestamps. A sliding window is used to extract the communication feature subset corresponding to each simulated mismatch segment, and the delay peak is quantile-normalized to convert the protocol compatibility index into a numerical feature in the range of 0-1. A dynamic time warping algorithm is also used to match the timing correlation between the communication features and the mismatch segment, and invalid features with a temporal overlap rate of less than 30% with the mismatch segment are eliminated. The processed communication feature vectors are arranged in the order of occurrence of the mismatch segment, and a three-dimensional communication feature sequence containing timestamps, delay peaks, and protocol indices is constructed to provide standardized input for the subsequent construction of the mismatch factor matrix. Obtain the communication characteristic sequences of all simulated mismatch segments and the characteristic simulation sequences of the subsystems, construct a mismatch factor matrix, and classify the mismatch factors into mismatch types; For example: if the communication delay peak in the simulated mismatch segment lasts for more than 200ms and the protocol compatibility index is lower than 0.4, and the mismatch coverage ratio reaches 40%, it is classified as communication-dominated mismatch; If the simulated mismatch segment corresponds to a HVAC system energy efficiency fluctuation rate exceeding the rated value by 25% and a power transient response ratio deviation of 30%, but the communication delay is only 80ms, it is classified as a physical characteristics-dominated mismatch; If the communication delay is 180ms and the HVAC equipment response time is 5 seconds, and the contribution of both to the mismatch coverage ratio exceeds 35%, it is determined to be a mixed-action mismatch; During classification, the communication delay is set to ≥150ms and the physical parameter deviation is set to ≥20% as the threshold, and the random forest feature importance is combined to achieve type division; A synergistic factor model was constructed based on the random forest algorithm, and the mismatch factor matrix was input into the synergistic factor model to extract the mismatch dominant factor. Those skilled in the art will understand that by integrating multi-dimensional features such as power transient response ratio, HVAC energy efficiency fluctuation rate, lighting response delay ratio, coupling contribution, communication delay peak, and protocol compatibility index, each sample corresponds to characteristic data under a load mutation scenario; The mismatch factor matrix is divided into a training set and a test set. A synergistic factor model is constructed based on the random forest algorithm. Multiple groups of training samples are generated through Bootstrap sampling. A feature subset is randomly selected from each group of samples to train a decision tree. By calculating the contribution of each mismatch factor to the coordinated mismatch state in the decision tree split, the dominant factors are screened and sorted in descending order of feature importance weight. The factors with the highest weight (such as communication delay peak and power transient response ratio) are selected as the mismatch dominant factors. Perform simulation verification based on the mismatch dominant factor and the corresponding mismatch type, optimize the mismatch dominant factor, and output the optimized synergistic mismatch coefficient; Calculate the deviation of the synergistic mismatch coefficient before and after optimization, conduct type matching evaluation on the optimization results, and determine whether the mismatch type corresponding to the mismatch factor is the dominant type; It should be explained that if the deviation value exceeds the preset threshold, it is determined that the mismatch factor has a significant impact on the collaborative mismatch. Combined with the mismatch type corresponding to the mismatch factor (such as communication-dominated type, physical property-dominated type), if its contribution to reducing the collaborative mismatch coefficient is the highest, then the mismatch type is determined to be the dominant type, thereby completing the type matching evaluation of the optimization result. Identifying the dominant mismatch type provides optimization targets for compensation strategies. If communication is the dominant type, regulation should focus on adapting the communication protocol; if physical characteristics are the dominant type, physical layer parameters should be adjusted. By identifying the root cause, ineffective regulation due to policy mismatches can be reduced, minimizing trial-and-error costs.

[0026] Step 4: If the mismatch is dominated by physical characteristics, a timing compensation strategy is dynamically constructed to generate targeted instruction pre-compilation and dynamic timing alignment solutions, obtain a dynamic timing alignment instruction sequence, and track the coordinated state of the subsystems after compensation to perceive and suppress the ripple diffusion effect of load mutations. The method for constructing a dynamic build timing compensation strategy is as follows: S401. Precompile control instructions based on a load mutation model of a building energy subsystem; Preferably, based on the load mutation amplitude, response delay, and duration in the simulated mismatch segment parameters output by the load mutation model, combined with the response threshold, the optimal control parameters for compensating the mismatch are pre-calculated from the transient equations of the power, HVAC, and lighting subsystems. A standardized instruction template containing the adjustment stage, time interval, and adjustment target parameters (e.g., a staged frequency modulation instruction for an HVAC water pump) is generated according to the equipment type. The effectiveness of the instruction is verified through model closed-loop simulation, and the template is finally stored as a standardized file that can be quickly retrieved and called according to the mismatch characteristics, thereby realizing the pre-compilation of the control instructions. S402, performing dynamic timing alignment based on the timing deviation characteristics of the simulated mismatch segment; Preferably, the subsystem response delay time difference and the mutation triggering time offset are extracted from the simulation mismatch section as timing deviation features, the deviation trend under the current working condition is predicted by the LSTM algorithm, and the control instruction triggering time is dynamically adjusted according to the predicted deviation + safety margin; A rigid time window is set after a sudden load change occurs, and the actual startup time and adjustment amplitude are compared with the simulation expectation through real-time acquisition equipment feedback. If the deviation exceeds the threshold, the subsequent instruction timing is corrected, forming a closed-loop alignment mechanism with mismatch feature extraction, deviation prediction, timing compensation, and real-time calibration. S403, performing load smoothing processing on the sudden amplitude overload and constructing a dynamic timing alignment instruction; Preferably, when the load mutation amplitude exceeds the standard in real-time monitoring, the original step mutation instruction is split into a multi-level step adjustment sequence, for example, a 100% power mutation is split into 3 levels, with an interval of 5 seconds between each level; The optimal regulation slope for each stage is calculated using the physical model of the equipment, and buffer time is inserted between stages to reduce system impact. Simultaneously, the number of steps and time intervals are dynamically adjusted based on the simulated mismatch segment data. Ultimately, a dynamic instruction sequence containing the regulation phase, target parameters, and timestamps is generated and sent to the subsystem controller in real time to achieve progressive load adjustment. The method for tracking the coordinated state of the compensated subsystems and sensing and suppressing the ripple diffusion effect of load mutations is as follows: S411, obtaining the load change and coupling contribution of the subsystems in the response system group after tracking compensation, and constructing the load mutation vector and coupling strength matrix; Preferably, the load mutation vectors of the two subsystems are defined as ; in, , , Represents subsystem i in time interval The load variation within represents subsystem j in the time interval Load variation within It should be explained that subsystems i and j are the numbers of the subsystems of the response system group; The coupling strength matrix is defined as , where c is the coupling contribution of the two subsystems; S412. Construct a ripple effect propagation equation and perform recursive filtering in combination with historical parameters to implement a ripple effect triggering criterion. By formula: Construct the ripple effect propagation equation; It is understandable that constructing the ripple effect propagation equation quantitatively analyzes the propagation path, intensity attenuation, and timing correlation of the coupled chain reaction caused by load mutations between subsystems in the building energy system through mathematical relationships, transforming the dynamic process of energy signal interaction into a computable state evolution law. It reflects the physical mechanism of how mutations spread across the system (such as coupling strength determines propagation amplitude, and response delay shapes timing difference), providing model support for predicting the impact boundary and peak moment of ripples, and designing early compensation. in, is the system state vector of the response system group, S1 and S2 are the response characteristics of the two subsystems in the response system group respectively; is the mutation influence coefficient matrix, are the mismatch coverage ratios of the two subsystems in the response system group; It should be explained that the mismatch coverage ratios of the two subsystems within the response system group are obtained by splitting the mismatch coverage ratio of the response system group as a whole; Among them, the way of performing recursive filtering is: Through the system of equations: Recursively update the state, where c is the coupling contribution between subsystem 1 and subsystem 2; β is the preset smoothing coefficient. For example, when the physical characteristics dominate the mismatch, β is 0.7. in, are the response characteristics of subsystem 1 and subsystem 2 at time t respectively; The response characteristics of subsystem 1 and subsystem 2 at time t-1 are are the load changes of subsystem 1 and subsystem 2 at time t respectively; The timing compensation parameters for each subsystem are obtained by linearly mapping the coupling deviation ratio and the reference compensation value; It can be understood that; through the coupling deviation ratio Quantify the mismatch coupling degree of subsystem 1. The coupling deviation ratio is the normalized ratio of the mismatch difference between the power and HVAC subsystems to the average mismatch between the two. Then extract the mean compensation parameter of the power subsystem in the historical fully coordinated scenario as the benchmark compensation value. represents the basic compensation amount; Finally, the preset simulation scale coefficient optimized by simulation is introduced ,For example =0.1, used to describe the impact of coupling mismatch on compensation strength and to establish a linear relationship: ,make Dynamically adjust as the coupling mismatch intensifies to match the compensation strength with the mismatch degree; It should be noted that the linear mapping method of subsystem 2 is the same as that of subsystem 1; By formula: Calculate the Euclidean distance deviation value of the system state vector ; When the Euclidean distance deviation value is higher than the preset Euclidean distance deviation threshold, it is determined that there is a ripple effect between the subsystems; Those skilled in the art will understand that, when a ripple effect is determined to have occurred, the instruction timing is adjusted to the subsystem (e.g., a 300ms delay in HVAC control) to cut off the mutation propagation chain; finally, the suppression effect is verified through the collaborative mismatch coefficient, requiring a coefficient reduction of more than 25% after compensation, thereby achieving closed-loop control of the entire process from mutation monitoring and propagation analysis to dynamic suppression.

[0027] Example 3 like Figure 3 As shown, a coordinated control system for a building energy system also includes the following modules: Response screening module: used to obtain the dynamic response characteristics of heterogeneous energy subsystems in the building, construct a dynamic response characteristic matrix, perform coupling analysis on the dynamic response characteristics of any two subsystems based on the dynamic response characteristic matrix, and determine the response system group; Mismatch assessment module: Obtains subsystem load data and combines it with the dynamic response characteristic matrix to simulate load mutations in the periodic step load scenario of the response system group and evaluate the degree of coordinated response mismatch between subsystems; Type analysis module: Based on the degree of response mismatch between subsystems, it performs correlation analysis on the heterogeneity of subsystem communication protocols and physical dynamic characteristics, identifies the dominant mismatch factor, and determines whether the mismatch type corresponding to the mismatch factor is the dominant type; Control and analysis module: If the mismatch is dominated by physical characteristics, a timing compensation strategy is dynamically constructed to generate targeted instruction pre-compilation and dynamic timing alignment solutions, obtain a dynamic timing alignment instruction sequence, and track the coordinated state of the subsystems after compensation, to perceive and suppress the ripple diffusion effect of load mutations.

[0028] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A coordinated control method for a building energy system, characterized by: The steps include: Obtain the dynamic response characteristics of heterogeneous energy subsystems in the building, construct a dynamic response characteristic matrix, conduct coupling analysis on the dynamic response characteristics of any two subsystems based on the dynamic response characteristic matrix, and determine the response system group; Obtain the load data of the subsystems and combine it with the dynamic response characteristic matrix to simulate the load mutation of the response system group's periodic step load scenario and evaluate the degree of coordinated response mismatch between subsystems; Based on the degree of response mismatch between subsystems, the heterogeneity of subsystem communication protocols and physical dynamic characteristics are correlated and analyzed to identify the dominant mismatch factor and determine whether the mismatch type corresponding to the mismatch factor is the dominant type. If the mismatch is dominated by physical characteristics, a timing compensation strategy is dynamically constructed to generate targeted instruction precompilation and dynamic timing alignment solutions, obtain a dynamic timing alignment instruction sequence, and track the coordinated state of the subsystems after compensation to perceive and suppress the ripple diffusion effect of load mutations.

2. The coordinated control method of a building energy system according to claim 1, characterized in that: The response system group is determined as follows: Extract the response characteristics of any two subsystems from the dynamic response characteristic matrix and construct the corresponding response characteristic sequences respectively; Perform cross-correlation analysis on the response characteristic sequences of any two subsystems and obtain the correlation coefficient corresponding to the maximum delay lag value as the coupling contribution; Obtain the two groups of subsystems with the highest coupling contribution and construct the response system group.

3. The coordinated control method of a building energy system according to claim 1, characterized in that: The method for evaluating the degree of cooperative response mismatch between the subsystems is as follows: Construct a load mutation model, obtain historical load constraints, and input the historical load constraints into the load mutation model. Set a simulation cycle to perform load mutation simulation on the response system group, and extract the response characteristics of the response system group after the load mutation simulation. Obtaining the response characteristics of two subsystems in the response system group of multiple simulation cycles, respectively constructing a response characteristic sequence of the simulation output of each subsystem to obtain a characteristic simulation sequence; Perform response mismatch analysis on the characteristic simulation sequence and extract the simulation mismatch segments within all simulation cycles: Extract the mismatch coverage ratio and coupling deviation ratio of the simulated mismatch segment, and calculate the cooperative mismatch coefficient of the response system group based on the mismatch coverage ratio and coupling deviation ratio; The degree of synergistic response mismatch between subsystems within a response system group is evaluated based on the synergistic mismatch coefficient.

4. The coordinated control method of a building energy system according to claim 3, characterized in that: The method for obtaining the historical load constraint condition is: Obtain historical load data of the building energy system and identify the step load mutation characteristics of periodic step load scenarios; Based on the periodic step load mutation characteristics, the historical load constraint conditions with historical step load mutation characteristics are constructed through genetic algorithm.

5. The coordinated control method of a building energy system according to claim 3, characterized in that: The method of extracting the mismatch coverage ratio and coupling deviation ratio of the simulated mismatch segment is: Obtain the single duration period of the simulation mismatch segment and the single duration period of the periodic step load scenario; The coverage ratio of a single duration period of the simulated mismatch segment and a single duration period of the periodic step load scenario is calculated to obtain the mismatch coverage ratio. The coupling contribution peak value of a single duration period of the characteristic simulation sequence in the simulation mismatch segment is obtained, and the deviation ratio between the coupling contribution peak value and the target boundary of the coupling contribution is calculated to obtain the coupling deviation ratio.

6. The coordinated control method of a building energy system according to claim 1, characterized in that: The dominant mismatch factor is identified as follows: If there is a mismatch risk in the coordinated response between subsystems within the response system group, the historical communication characteristics of each subsystem in the response system group are obtained from the log of the building energy system and input into the load mutation model; Among them, historical communication characteristics include communication delay peak and protocol compatibility index; Obtain the communication characteristic sequences of all simulated mismatch segments and the characteristic simulation sequences of the subsystems, construct a mismatch factor matrix, and classify the mismatch factors into mismatch types; A synergistic factor model is constructed based on the random forest algorithm, and the mismatch factor matrix is input into the synergistic factor model to extract the mismatch dominant factor. A matching correspondence analysis is performed based on the mismatch dominant factor to determine whether the mismatch type corresponding to the mismatch factor is the dominant type.

7. The coordinated control method of a building energy system according to claim 6, characterized in that: The matching correspondence analysis is performed as follows: Perform simulation verification based on the mismatch dominant factor and the corresponding mismatch type, optimize the mismatch dominant factor, and output the optimized synergistic mismatch coefficient; Calculate the deviation of the synergistic mismatch coefficient before and after optimization, perform type matching evaluation on the optimization results, and determine whether the mismatch type corresponding to the mismatch factor is the dominant type.

8. The coordinated control method of a building energy system according to claim 1, characterized in that: The method of dynamically constructing the timing compensation strategy is as follows: Precompile control instructions based on the load mutation model of the building energy subsystem; Dynamic timing alignment is performed based on the timing deviation characteristics of the simulated mismatch segment; Perform load smoothing on the sudden amplitude overload and build dynamic timing alignment instructions.

9. The coordinated control method of a building energy system according to claim 1, characterized in that: The way to sense and suppress the ripple diffusion effect of the load mutation is: Obtain the load change and coupling contribution of the subsystems in the response system group after tracking compensation, and construct the load mutation vector and coupling strength matrix; Construct a ripple effect propagation equation and perform recursive filtering based on historical parameters to implement the ripple effect triggering criteria; After determining that a ripple effect occurs, the instruction timing is adjusted to the subsystem to suppress the ripple effect.

10. The coordinated control method of a building energy system according to claim 9, characterized in that: The ripple effect triggering criterion is implemented as follows: Establish the system state vector and mutation impact coefficient vector of the response system group, and construct the ripple effect propagation equation by combining the load mutation vector and coupling strength matrix; Recursively filter the ripple effect propagation equation and calculate the Euclidean distance deviation value of the system state vector; When the Euclidean distance deviation value is higher than a preset Euclidean distance deviation threshold, it is determined that there is a ripple effect between the subsystems.

Images