A regional distributed energy visualization system and method based on digital twin

Abstract

The present invention relates to the field of energy management technology, and in particular to a regional distributed energy visualization system and method based on digital twins. The visualization system includes: a data center, a model building module, a decision support module, a simulation module, and a visualization display module. The visualization method includes: the data center collects the current operating data in the distributed energy in the set building area in real time and cleans it to generate energy management information; the model building module constructs a related digital twin model through the energy management information; the data center conducts a comprehensive analysis of the energy management information by using the hierarchical analysis method to find out the key factors of energy waste, and the decision support module provides different management plans according to the analysis results; the simulation module simulates different management plans to obtain the optimal management plan; and the visualization display module displays. The present invention reduces data collection errors, timely and accurately obtains the key factors of energy waste, and improves the accuracy of decision-making.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to a regional distributed energy visualization system and method based on digital twins. Background Art

[0002] Energy has become an indispensable basic element of human society. However, as my country's energy demand will continue to grow, energy is becoming increasingly tight and the environment is deteriorating, traditional energy management systems rely on manual records and paper reports. This method is not only inefficient, but also prone to errors and difficult to update in real time. It lacks networking functions, has a small number of information recipients, cannot realize data sharing and analysis, lacks online equipment monitoring, cannot detect faults and analyze utilization in a timely manner, and has many deficiencies in intelligent decision-making.

[0003] With the development of the Internet, big data and artificial intelligence technology, building energy management systems have gradually developed. However, general building energy management systems are aimed at traditional centralized energy management and only manage specific traditional energy. Regional distributed energy management systems need to manage multiple energy sources comprehensively. They need to collect a large amount of different data to establish prediction models and analyze and process them. There is a problem of large workload. If traditional centralized energy management systems are applied to regional distributed energy management for users, it is not easy to manage multiple energy sources at the same time, the simulation accuracy is poor, the configuration is not flexible enough, and the response speed to user energy needs is slow. Summary of the invention

[0004] The purpose of the present invention is to provide a regional distributed energy visualization system and method based on digital twins to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A regional distributed energy visualization system based on digital twins includes a data center, wherein the data center includes a data acquisition module, a data cleaning module, a data analysis module, and a data transmission module. The data acquisition module is used to collect the current operation data of the distributed energy in a set building area in real time; the data cleaning module is used to clean the current operation data collected in real time to generate energy management information; the data analysis module comprehensively analyzes the management plan of the distributed energy in the set building area within a set operation cycle according to the energy management information to find out the key factors causing energy waste; the data transmission module is used to transmit the energy management information to the model construction module and the key factors causing energy waste to the decision support module;

[0007] A model building module, wherein the model building module uses the digital twin technology to build a three-dimensional digital twin model related to the distributed energy of the set building area through energy management information, and maps the digital twin model to the visualization display module for real-time display;

[0008] A decision support module, wherein the decision support module provides different management solutions for distributed energy in a set building area according to key factors of energy waste;

[0009] A simulation module, which is used to simulate different management schemes to obtain simulation results, conduct a comprehensive analysis of all simulation results, and select the best management scheme;

[0010] A visualization display module, the visualization display module includes a two-dimensional panel display area and a three-dimensional scene display area, the two-dimensional panel display area is used to display real-time updated energy management information and the selected optimal management plan; the three-dimensional scene display area is used to display the digital twin model of the distributed energy of the set building area and the operation process of different management plans simulated in the digital twin model;

[0011] A user interaction module, the user interaction module is used to provide a user interaction interface for the user to input instructions;

[0012] A database module, which is used to save the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set established after data cleaning, and map the generated energy management information with the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set for user query and retrieval.

[0013] A regional distributed energy visualization method based on digital twins is applied to the regional distributed energy visualization system based on digital twins described above, and includes the following steps:

[0014] S1: The data acquisition module of the data center collects the current operating data of the distributed energy in the set building area in real time at a certain time interval. The current operating data includes energy conversion data, energy storage data, energy transmission data and user consumption data;

[0015] S2: The data cleaning module of the data center cleans the current operation data collected in real time during the current collection period, performs data standardization, removes duplicate data, fills in missing values, and identifies and corrects abnormal values ​​to generate energy management information. The energy management information includes energy conversion information, energy storage information, energy transmission information, and user consumption information;

[0016] S3: The model building module uses digital twin technology to build a digital twin model related to distributed energy in the set building area through energy management information and maps it to the visualization display module for real-time display;

[0017] S4: The data center conducts a comprehensive analysis of the energy management information by using the hierarchical analysis method, and divides the energy waste factors that affect the energy conversion information, energy storage information, energy transmission information and user consumption information into energy conversion factors, energy storage factors, energy transmission factors and user consumption factors, respectively, calculates the corresponding weights of the energy waste factors, determines the factors with weights greater than the set value as the key factors of energy waste, and transmits them to the decision support module;

[0018] S5: The decision support module provides different management schemes for the distributed energy in the set building area according to the key factors of energy waste; the simulation module uses the simulated annealing algorithm to simulate different management schemes to obtain simulation results and select the optimal management scheme;

[0019] S6: The visualization display module displays the real-time updated energy management information, the operation process of different management scheme simulations and the optimal management scheme obtained by analysis.

[0020] The S2 specifically includes the following steps:

[0021] S21: The data cleaning module performs preliminary sorting of the current operation data, performs standardization processing on each data in the current operation data according to the set data transformation rules, and generates standardized data;

[0022] S22: Establish energy conversion data set, energy storage data set, energy transmission data set and user consumption data set, and map the standardized data to the corresponding data set according to the stage coding;

[0023] S23: traverse all standardized data of each data set;

[0024] S24: Find any two standardized data and determine whether the similarity is greater than or equal to the determination index. If yes, jump to S25; otherwise, jump to S26;

[0025] S25: determining that the two standardized data are duplicated, deleting one of them and retaining the other standardized data;

[0026] S26: Check whether there is missing data in the data set; if yes, jump to S27, if not, jump to S28;

[0027] S27: Use the moving average method to calculate the historical average value of the missing data, and use the historical average value as the standardized data to fill in the missing data;

[0028] Specifically, select the historical standardized data of n collection cycles before the current collection cycle t, and the historical average value The calculation formula is:

[0029] Where t-1 is the collection cycle before the current collection cycle t; the historical average As the predicted value of the current collection period t, the missing data is filled with standardized data;

[0030] S28: Compare the standardized data of the current collection cycle with the historical standardized data of the previous collection cycle, calculate the floating ratio, and determine whether the floating ratio exceeds the set floating threshold. If yes, jump to S29, otherwise jump to S210;

[0031] The floating ratio v is calculated as:

[0032]

[0033] S29: determining that the standardized data is abnormal data, deleting the abnormal data, using the moving average method to calculate the historical average value of the abnormal data, and adding a set tolerance amount to the historical average value, and replacing the abnormal data with the result obtained;

[0034] S210: Update the data set and determine whether the data set traversal is complete. If yes, output the cleaned data set to the database module and map it to the energy management information. If not, return to S23.

[0035] The S4 specifically comprises the following steps:

[0036] S41: The data center compares each data in the energy management information with a preset waste parameter range to find energy waste factors. If the data exceeds the preset range, it is determined that there are energy waste factors at the current collection location.

[0037] S42: Establish a hierarchical model of energy waste factors;

[0038] S43: Establish a judgment matrix A according to the hierarchical structure model.

[0039] A=(a ij ) m×m

[0040] Among them, a ij It represents the ratio of the influence degree of the i-th energy waste factor and the j-th energy waste factor in the judgment matrix A;

[0041] S44: Normalization processing and calculation of the maximum eigenvalue λ and the corresponding eigenvector ω of each level of judgment matrix A i ;

[0042] S45: consistency test of the judgment matrix A; if it passes, the eigenvector corresponding to the maximum eigenvalue of each level after normalization is the corresponding weight of the energy waste factor at each level; if it fails, the judgment matrix A is re-established according to the hierarchical structure model;

[0043] S46: Determine whether the weights of each level are greater than the set value; if so, the energy waste factor corresponding to the weight is the key factor of energy waste; if not, the energy waste factor corresponding to the weight is not the key factor causing energy waste.

[0044] The S5 simulation module uses a simulated annealing algorithm to simulate different management schemes to obtain simulation results, which specifically includes the following steps:

[0045] S51: obtaining management parameter information of the management scheme, presetting the requirements of the management scheme as the objective function, wherein the requirements of the management scheme are one or more of energy conversion efficiency, energy storage, energy transmission efficiency, and user consumption respectively related to energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors, and establishing the objective function of the management scheme;

[0046] S52: Set the initial temperature T0 and the end temperature T B , the maximum number of iterations K at each temperature, the cooling rate α, and 0<α<1;

[0047] S53: Assign the initial temperature T0 to

[0048] S54: randomly setting an initial solution S0 for the management parameter information, and calculating the initial objective function value f(S0) required by the management solution;

[0049] S55: The management parameter information generates a new optimal solution S1 in the neighborhood, and calculates the optimal solution objective function value f(S1) of the management solution requirements;

[0050] S56: According to the difference Δf between the optimal solution objective function value and the initial objective function value, if the difference Δf is less than zero, the new optimal solution is judged to be better than the initial solution, and the new optimal solution replaces the initial solution; otherwise, the new optimal solution is accepted with a specific probability M.

[0051] S57: k is the number of iterations, and k is initially 0, and the number of iterations k=k+1 is set to iterate, and S54 to S56 are repeated until k=K;

[0052] S58: If The termination temperature T is not reached B , according to the exponential cooling strategy, that is The order is reduced, and the process returns to step S53. If the termination temperature T is reached, B , and output the optimal solution finally obtained by S57 as the optimal solution of the management plan.

[0053] The data transformation rule in S21 is to extract field features of each data and encode each field feature accordingly, convert each data according to the corresponding code, sort the corresponding codes, and arrange the values ​​after data conversion according to the corresponding code sort.

[0054] In S24, the two standardized data are compared, and a judgment is made according to the corresponding coding of each field feature, and the judgment index takes a percentage greater than 0 and less than or equal to 1.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention provides a regional distributed energy visualization system and method based on digital twins. By collecting the current operating data of the regional distributed energy in real time, the current operating data is cleaned and energy management information is generated. It can monitor multiple energy sources at the same time and can minimize the defects and errors in the data collection stage. The management plan of the regional distributed energy is comprehensively analyzed according to the energy management information. This real-time monitoring and analysis greatly eliminates the impact of data collection errors on energy management, which not only makes the digital twin model more accurate, but also can promptly discover problems in the energy management plan in the later stage, thereby improving the accuracy of problem diagnosis and energy utilization.

[0057] The present invention provides a regional distributed energy visualization system and method based on digital twins. By analyzing energy management information through the hierarchical analysis method, the key factors of energy waste in energy management can be accurately obtained, thereby formulating more qualified management plans, reducing energy waste and unnecessary losses, reducing operating costs and optimizing resource allocation.

[0058] The present invention provides a regional distributed energy visualization system and method based on digital twins. Through a visualization display module, real-time updated energy management information, a regional distributed energy digital twin model, a simulated operation process and an optimal management solution are displayed. The simulation has high accuracy and flexible configuration, so that energy managers can monitor and manage the operation status of regional distributed energy in real time, improve management efficiency and decision-making accuracy, and thus meet user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a regional distributed energy visualization method based on digital twins according to the present invention;

[0060] Figure 2 This is a flow chart of step S2 of a regional distributed energy visualization method based on digital twins of the present invention;

[0061] Figure 3 This is a flow chart of step S4 of a regional distributed energy visualization method based on digital twins of the present invention;

[0062] Figure 4 This is a flow chart of step S5 of a regional distributed energy visualization method based on digital twins of the present invention;

[0063] Figure 5 This is a structural schematic diagram of a regional distributed energy visualization system based on digital twins in the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In the following description of the invention, it should be noted that the terms "upper", "lower", "left", "right", "inner", "outer", etc., indicating directions or positional relationships, are based on directions or positional relationships shown in the drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific direction or be constructed and operated in a specific direction. The term "connection" only indicates the connection between devices and has no special meaning.

[0066] In addition, the technical fields and installation methods involved in the embodiments of the present invention described below can be combined with each other as long as there is no conflict between them.

[0067] Specific implementation: Please refer to Figure 1-Figure 5 , a regional distributed energy visualization system based on digital twins, including a data center, the data center including a data acquisition module, a data cleaning module, a data analysis module, and a data transmission module, the data acquisition module is used to collect the current operation data of the distributed energy in a set building area in real time; the data cleaning module is used to clean the current operation data collected in real time to generate energy management information; the data analysis module comprehensively analyzes the management plan of the distributed energy in the set building area within the set operation cycle according to the energy management information, and finds out the key factors causing energy waste; the data transmission module is used to transmit the energy management information to the model construction module and the key factors causing energy waste to the decision support module;

[0068] A model building module, wherein the model building module uses the digital twin technology to build a three-dimensional digital twin model related to the distributed energy of the set building area through energy management information, and maps the digital twin model to the visualization display module for real-time display;

[0069] A decision support module, wherein the decision support module provides different management solutions for distributed energy in a set building area according to key factors of energy waste;

[0070] A simulation module, which is used to simulate different management schemes to obtain simulation results, conduct a comprehensive analysis of all simulation results, and select the best management scheme;

[0071] A visualization display module, the visualization display module includes a two-dimensional panel display area and a three-dimensional scene display area, the two-dimensional panel display area is used to display real-time updated energy management information and the selected optimal management plan; the three-dimensional scene display area is used to display the digital twin model of the distributed energy of the set building area and the operation process of different management plans simulated in the digital twin model;

[0072] In one embodiment, the three-dimensional scene display area uses VR and AR technology to display the digital twin model of the distributed energy system of the set building area and the simulated operation process of different management schemes in the digital twin model.

[0073] A user interaction module, the user interaction module is used to provide a user interaction interface for the user to input instructions;

[0074] A database module, which is used to save the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set established after data cleaning, and map the generated energy management information with the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set for user query and retrieval.

[0075] Furthermore, the present invention also provides a regional distributed energy visualization method based on digital twins, which is applied to the regional distributed energy visualization system based on digital twins, and includes the following steps:

[0076] S1: The data acquisition module of the data center collects the current operating data of the distributed energy in the set building area in real time at a certain time interval. The current operating data includes energy conversion data, energy storage data, energy transmission data and user consumption data;

[0077] In one embodiment, the data acquisition module connects to a variety of sensors for real-time data collection, and uses the Internet of Things technology to transmit the collected current operating data. A variety of sensors respectively collect environmental signals and energy conversion equipment operating signals as energy conversion data. The distributed energy in this embodiment includes solar energy, wind energy, and air energy. The environmental signals include conventional meteorological parameters, wind parameters, and solar energy parameters. Conventional meteorological parameters include temperature, humidity, air pressure, air density, dustiness, etc. Wind parameters include wind speed, wind direction, wind energy density, wind power density, wind intensity, etc. Solar energy parameters include total solar radiation, solar radiation component, light intensity, sunshine hours, and solar Altitude angle, solar azimuth, etc.; energy conversion equipment operation signals include equipment operation parameters corresponding to power equipment and air conditioning equipment that convert distributed energy in a set building area into cold, heat and electricity, such as operating power, voltage, current, equipment temperature and frequency; energy storage data include storage parameters of energy storage equipment related to distributed energy in a set building area, such as storage medium parameters, storage capacity and real-time storage capacity; energy transmission data include transmission parameters of energy transmission pipelines, such as cold, heat and electricity transmission parameters, and user consumption data include user-side consumption data and consumption costs for the converted cold, heat and electricity.

[0078] S2: The data cleaning module of the data center cleans the current operation data collected in real time during the current collection period, performs data standardization, removes duplicate data, fills in missing values, and identifies and corrects abnormal values ​​to generate energy management information. The energy management information includes energy conversion information, energy storage information, energy transmission information, and user consumption information;

[0079] Furthermore, the data cleaning module of the data center in S2 cleans the current operation data collected in real time, performs data standardization, removes duplicate data, fills in missing values, and identifies and corrects abnormal values ​​to generate energy management information, including the following steps:

[0080] S21: The data cleaning module performs preliminary sorting of the current operation data, performs standardization processing on each data in the current operation data according to the set data transformation rules, and generates standardized data;

[0081] Specifically, the data transformation rule is to extract field features of each data and encode each field feature accordingly, convert each data according to the corresponding code, sort the corresponding codes, and arrange the converted values ​​according to the corresponding code sort.

[0082] The field characteristics include sensor location, sensor model, collected value, and data unit. The sensor location in the field characteristics is used to determine whether it belongs to the stage category of energy conversion data, energy storage data, energy transmission data, and user consumption data, and stage coding is performed. Similarly, position coding is performed according to the sensor location. The data unit in the field characteristics is used to determine the category of collected information to which it belongs, and information coding is performed. The stage coding, position coding, and information coding can all be in digital or alphabetic form. For example, the stage coding of energy conversion data, energy storage data, energy transmission data, and user consumption data are set to 1, 2, 3, and 4 respectively. The position coding of photovoltaic power generation in the energy conversion stage is set to 1, and the position coding of wind power generation in the energy conversion stage is set to 2. The temperature information coding in the information coding is set to H, and the power information coding is set to H. The code is set to P, the information code of the current is set to I, the information code of the voltage is set to U, the information code of the speed is set to V, and the values ​​after data conversion can be arranged in sequence according to the stage code, position code, information code and collected value format, and a separator is set between two adjacent codes. For example, the current collected at the photovoltaic power generation in the energy conversion stage is converted to 1*1*I*5; for different types of data collected at the same location, the data is sorted according to the set information coding order for subsequent search and call. For example, the current, voltage, and temperature collected at the photovoltaic power generation in the energy conversion stage are arranged in sequence as 1*1*I*5, 1*1*U*35, and 1*1*H*45; this setting can unify the standards of different types of collected data in different formats, facilitate subsequent call analysis, and reduce the time of system operation analysis;

[0083] S22: Establish energy conversion data set, energy storage data set, energy transmission data set and user consumption data set, and map the standardized data to the corresponding data set according to the stage coding;

[0084] S23: traverse all standardized data of each data set;

[0085] S24: Find any two standardized data and determine whether the similarity is greater than or equal to the determination index. If yes, jump to S25; otherwise, jump to S26;

[0086] Specifically, two standardized data are compared, and judgment is made based on the corresponding coding of each field feature, stage coding, position coding, information coding and collected numerical judgment, and the judgment index takes a percentage greater than 0 and less than or equal to 1, for example, set to 99%.

[0087] S25: determining that the two standardized data are duplicated, deleting one of them and retaining the other standardized data;

[0088] S26: Check whether there is missing data in the data set; if yes, jump to S27, if not, jump to S28;

[0089] Specifically, check whether the current position information code is missing according to the position code of the standardized data. If the information code is missing, further check whether the historical standardized data information codes of multiple adjacent collection cycles corresponding to the position code are missing. If yes, determine that the corresponding sensor is not set at the position code to collect the corresponding information. If not, determine that the corresponding information at the position code is missing. For example, in the energy conversion stage, the photovoltaic power generation should arrange the collected current, voltage, and temperature as 1*1*I*5, 1*1*U*35, and 1*1*H*45 in sequence, but the currently collected voltage value is missing, which is only 1*1*I*5 and 1*1*H*45. Then, it is necessary to find out whether the information code corresponding to the current at the current position code is missing in the historical standardized data of multiple adjacent collection cycles in the past. If it is always missing, the current data is not collected at this place. If it is not missing, there is a problem of missing data in this collection cycle, which needs to be filled.

[0090] S27: Use the moving average method to calculate the historical average value of the missing data, and use the historical average value as the standardized data to fill in the missing data;

[0091] Specifically, select the historical standardized data of n collection cycles before the current collection cycle t, and the historical average value The calculation formula is:

[0092] Where t-1 is the collection cycle before the current collection cycle t; the historical average As the predicted value of the current collection period t, the missing data is filled with standardized data;

[0093] S28: Compare the standardized data of the current collection cycle with the historical standardized data of the previous collection cycle, calculate the floating ratio, and determine whether the floating ratio exceeds the set floating threshold. If yes, jump to S29, otherwise jump to S210;

[0094] The floating ratio v is calculated as:

[0095]

[0096] For example, the floating threshold can be set to ±θ, where θ is a number greater than 0. If |θ|≥|v|, it means that the floating ratio does not exceed the set floating threshold. If |θ|<|v|, it means that the floating ratio exceeds the set floating threshold.

[0097] S29: determining that the standardized data is abnormal data, deleting the abnormal data, using the moving average method to calculate the historical average value of the abnormal data, and adding a set tolerance amount to the historical average value, and replacing the abnormal data with the result obtained;

[0098] If v is a negative value, it means that the standardized data at the location of the abnormal data has a decreasing trend, and the tolerance is a negative value. If v is a positive value, it means that the standardized data at the location of the abnormal data has an increasing trend; the tolerance is a positive value, and the absolute value of the tolerance is a percentage of the historical average value. According to the specific value settings of different standardized data, the floating threshold and tolerance settings can correct the abnormal values ​​more accurately.

[0099] S210: Update the data set and determine whether the data set traversal is complete. If yes, output the cleaned data set to the database module and map it to the energy management information. If not, return to S23.

[0100] In a specific embodiment, if abnormal data appears, it is necessary to obtain the stage code, position code, and model code corresponding to the abnormal data, find the corresponding sensor, record and prompt in the visual display module, and remind the user to check and repair the corresponding sensor.

[0101] The energy conversion data set, the energy storage data set, the energy transmission data set, and the user consumption data set are mapped one by one to the energy conversion information, the energy storage information, the energy transmission information, and the user consumption information of the energy management information.

[0102] S3: The model building module uses digital twin technology to build a digital twin model related to distributed energy in the set building area through energy management information and maps it to the visualization display module for real-time display;

[0103] S4: The data center conducts a comprehensive analysis of the energy management information by using the hierarchical analysis method, and divides the energy waste factors that affect the energy conversion information, energy storage information, energy transmission information and user consumption information into energy conversion factors, energy storage factors, energy transmission factors and user consumption factors, respectively, calculates the corresponding weights of the energy waste factors, determines the factors with weights greater than the set value as the key factors of energy waste, and transmits them to the decision support module;

[0104] The factors that lead to energy waste include energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors. Energy conversion factors include variables that affect energy conversion, such as power, speed, cleanliness, heat dissipation, and failure rate of power equipment and air conditioning equipment. The existence of energy conversion factors may lead to low energy conversion rate and unreasonable resource allocation, making it impossible to maximize the utilization of distributed energy; energy storage factors include variables that affect energy storage, such as storage capacity, storage medium temperature, storage medium life, storage medium charging and discharging capacity, etc. Energy storage factors may cause energy to be unable to be stored and released in time during the storage link, resulting in waste; energy transmission factors include variables that affect energy transmission, such as the distance of the transmission line, loss, resistance value, voltage value, current value, etc. Energy transmission factors may lead to unreasonable allocation of energy during transmission and cause waste; user consumption factors include variables that affect user consumption, such as indoor temperature, user-end equipment power, failure rate, heat dissipation, cleanliness, operating time, etc. The existence of user consumption factors may lead to additional waste when energy is used improperly by users. Finding the key factors of energy waste within the set operating cycle can manage energy in a timely and reasonable manner and reduce unnecessary waste and losses.

[0105] Furthermore, the S4 specifically includes the following steps:

[0106] S41: The data center compares each data in the energy management information with a preset waste parameter range to find energy waste factors. If the data exceeds the preset range, it is determined that there are energy waste factors at the current collection location.

[0107] S42: Establish a hierarchical model of energy waste factors;

[0108] Furthermore, the establishment of the hierarchical structure model of energy waste factors specifically includes: dividing energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors into primary energy waste factors, and dividing specific influencing factors under energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors into secondary energy waste factors;

[0109] S43: Establish a judgment matrix A according to the hierarchical structure model.

[0110] A=(a ij ) m×m

[0111] Among them, a ij It represents the ratio of the influence degree of the i-th energy waste factor to the j-th energy waste factor in the judgment matrix A. The judgment matrix is ​​constructed by comparing the elements pairwise, and m is the order of the judgment matrix;

[0112] S44: Normalization processing and calculation of the maximum eigenvalue λ and the corresponding eigenvector ω of each level of judgment matrix A i ; ω=(ω1ω2…ω m ) T is the approximate eigenvector, where

[0113] S45: consistency test of judgment matrix A;

[0114] If the test is passed, the eigenvector corresponding to the maximum eigenvalue of each level after normalization is the corresponding weight of the energy waste factor at each level; if the test is not passed, the judgment matrix A is re-established according to the hierarchical structure model;

[0115] The consistency check specifically includes: calculating the consistency index

[0116] CI = (λ-m) / (m-1)

[0117] Among them, when the consistency ratio CR=CI / RI<0.1, the inconsistency of A is within the allowable range and passes the consistency test, otherwise it fails the consistency test; CR is the consistency ratio, and RI is the random consistency index, which can be calculated according to the saaty table;

[0118] S46: Determine whether the weights of each level are greater than the set value; if so, the energy waste factor corresponding to the weight is the key factor of energy waste; if not, the energy waste factor corresponding to the weight is not the key factor causing energy waste.

[0119] S5: The decision support module provides different management schemes for the distributed energy in the set building area according to the key factors of energy waste; the simulation module uses the simulated annealing algorithm to simulate different management schemes to obtain simulation results and select the optimal management scheme;

[0120] Furthermore, the S5 simulation module uses a simulated annealing algorithm to simulate different management schemes to obtain simulation results, which specifically includes the following steps:

[0121] S51: obtaining management parameter information of the management scheme, presetting the requirements of the management scheme as the objective function, wherein the requirements of the management scheme are one or more of energy conversion efficiency, energy storage, energy transmission efficiency, and user consumption respectively related to energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors, and establishing the objective function of the management scheme;

[0122] S52: Set the initial temperature T0 and the end temperature T B, the maximum number of iterations K at each temperature, the cooling rate α, and 0<α<1;

[0123] S53: Assign the initial temperature T0 to k is the number of iterations, and k is initially 0;

[0124] S54: randomly setting an initial solution S0 for the management parameter information, and calculating the initial objective function value f(S0) required by the management solution;

[0125] S55: The management parameter information generates a new optimal solution S1 in the neighborhood, and calculates the optimal solution objective function value f(S1) of the management solution requirements;

[0126] S56: According to the difference Δf between the optimal solution objective function value and the initial objective function value, if the difference Δf is less than zero, the new optimal solution is judged to be better than the initial solution, and the new optimal solution replaces the initial solution; otherwise, the new optimal solution is accepted with a specific probability M.

[0127] S57: set the number of iterations k=k+1, and repeat S54 to S56 until k=K;

[0128] S58: If The termination temperature T is not reached B , according to the exponential cooling strategy, that is The order is reduced, and the process returns to step S53. If the termination temperature T is reached, B , and output the optimal solution finally obtained by S57 as the optimal solution of the management plan.

[0129] The management parameter information is the variable parameters related to energy conversion factors, energy storage factors, energy transmission factors and user consumption factors, such as the speed and power of power equipment and air conditioning equipment in the energy conversion stage, the storage medium temperature in the energy storage stage, the medium temperature, voltage value or current value of the transmission line in the energy transmission stage, and the indoor temperature in the user consumption stage.

[0130] S6: The visualization display module displays the real-time updated energy management information, the operation process of different management scheme simulations and the optimal management scheme obtained by analysis.

[0131] In the above visualization method, steps S1-S6 can be operated by inputting relevant instructions through the user interaction module, and the user interaction interface facilitates instruction input.

[0132] The present invention provides a regional distributed energy visualization system and method based on digital twins. By collecting the current operating data of the regional distributed energy in real time, the current operating data is cleaned and energy management information is generated. It can monitor multiple energy sources at the same time and can minimize the defects and errors in the data collection stage. The management plan of the regional distributed energy is comprehensively analyzed according to the energy management information. This real-time monitoring and analysis greatly eliminates the impact of data collection errors on energy management, which not only makes the digital twin model more accurate, but also can promptly discover problems in the energy management plan in the later stage, thereby improving the accuracy of problem diagnosis and energy utilization.

[0133] The present invention provides a regional distributed energy visualization system and method based on digital twins. By analyzing energy management information through the hierarchical analysis method, the key factors of energy waste in energy management can be accurately obtained, thereby formulating more qualified management plans, reducing energy waste and unnecessary losses, reducing operating costs and optimizing resource allocation.

[0134] The present invention provides a regional distributed energy visualization system and method based on digital twins. Through a visualization display module, real-time updated energy management information, a regional distributed energy digital twin model, a simulated operation process and an optimal management solution are displayed. The simulation has high accuracy and flexible configuration, so that energy managers can monitor and manage the operation status of regional distributed energy in real time, improve management efficiency and decision-making accuracy, and thus meet user needs.

Claims

1. A regional distributed energy visualization system based on digital twins, characterized by: It includes a data center, which includes a data acquisition module, a data cleaning module, a data analysis module, and a data transmission module. The data acquisition module is used to collect the current operation data of the distributed energy in the set building area in real time; the data cleaning module is used to clean the current operation data collected in real time to generate energy management information; The data analysis module comprehensively analyzes the management scheme of distributed energy in a set building area within a set operation cycle according to the energy management information to find out the key factors leading to energy waste; the data transmission module is used to transmit the energy management information to the model building module and the key factors leading to energy waste to the decision support module; A model building module, wherein the model building module uses the digital twin technology to build a three-dimensional digital twin model related to the distributed energy of the set building area through energy management information, and maps the digital twin model to the visualization display module for real-time display; A decision support module, wherein the decision support module provides different management solutions for distributed energy in a set building area according to key factors of energy waste; A simulation module, which is used to simulate different management schemes to obtain simulation results, conduct a comprehensive analysis of all simulation results, and select the best management scheme; A visualization display module, the visualization display module includes a two-dimensional panel display area and a three-dimensional scene display area, the two-dimensional panel display area is used to display real-time updated energy management information and the selected optimal management solution; The three-dimensional scene display area is used to display the digital twin model of the distributed energy in the set building area and the operation process of the simulation of different management schemes in the digital twin model; A user interaction module, the user interaction module is used to provide a user interaction interface for the user to input instructions; A database module, which is used to save the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set established after data cleaning, and map the generated energy management information with the energy conversion data set, energy storage data set, energy delivery data set and user consumption data set for user query and retrieval.

2. A regional distributed energy visualization method based on digital twins, applied to a regional distributed energy visualization system based on digital twins as described in claim 1, characterized in that: The following steps are involved: S1: The data acquisition module of the data center collects the current operating data of the distributed energy in the set building area in real time at a certain time interval. The current operating data includes energy conversion data, energy storage data, energy transmission data and user consumption data; S2: The data cleaning module of the data center cleans the current operation data collected in real time during the current collection period, performs data standardization, removes duplicate data, fills in missing values, and identifies and corrects abnormal values ​​to generate energy management information. The energy management information includes energy conversion information, energy storage information, energy transmission information, and user consumption information; S3: The model building module uses digital twin technology to build a digital twin model related to distributed energy in the set building area through energy management information and maps it to the visualization display module for real-time display; S4: The data center conducts a comprehensive analysis of the energy management information by using the hierarchical analysis method, and divides the energy waste factors that affect the energy conversion information, energy storage information, energy transmission information and user consumption information into energy conversion factors, energy storage factors, energy transmission factors and user consumption factors, respectively, calculates the corresponding weights of the energy waste factors, determines the factors with weights greater than the set value as the key factors of energy waste, and transmits them to the decision support module; S5: The decision support module provides different management schemes for the distributed energy in the set building area according to the key factors of energy waste; the simulation module uses the simulated annealing algorithm to simulate different management schemes to obtain simulation results and select the optimal management scheme; S6: The visualization display module displays the real-time updated energy management information, the operation process of different management scheme simulations and the optimal management scheme obtained by analysis.

3. According to claim 2, a regional distributed energy visualization method based on digital twins is characterized by: The S2 specifically includes the following steps: S21: The data cleaning module performs preliminary sorting of the current operation data, performs standardization processing on each data in the current operation data according to the set data transformation rules, and generates standardized data; S22: Establish energy conversion data set, energy storage data set, energy transmission data set and user consumption data set, and map the standardized data to the corresponding data set according to the stage coding; S23: traverse all standardized data of each data set; S24: Find any two standardized data and determine whether the similarity is greater than or equal to the determination index. If yes, jump to S25; otherwise, jump to S26; S25: determining that the two standardized data are duplicated, deleting one of them and retaining the other standardized data; S26: Check whether there is missing data in the data set; if yes, jump to S27, if not, jump to S28; S27: Use the moving average method to calculate the historical average value of the missing data, and use the historical average value as the standardized data to fill in the missing data; Specifically, select the historical standardized data of n collection cycles before the current collection cycle t, and the historical average value The calculation formula is: Where t-1 is the collection cycle before the current collection cycle t; the historical average As the predicted value of the current collection period t, the missing data is filled with standardized data; S28: Compare the standardized data of the current collection cycle with the historical standardized data of the previous collection cycle, calculate the floating ratio, and determine whether the floating ratio exceeds the set floating threshold. If yes, jump to S29, otherwise jump to S210; The floating ratio v is calculated as: S29: determining that the standardized data is abnormal data, deleting the abnormal data, using the moving average method to calculate the historical average value of the abnormal data, and adding a set tolerance amount to the historical average value, and replacing the abnormal data with the result obtained; S210: Update the data set and determine whether the data set traversal is complete. If yes, output the cleaned data set to the database module and map it to the energy management information. If not, return to S23.

4. According to claim 2, a regional distributed energy visualization method based on digital twins is characterized by: The S4 specifically comprises the following steps: S41: The data center compares each data in the energy management information with a preset waste parameter range to find energy waste factors. If the data exceeds the preset range, it is determined that there are energy waste factors at the current collection location. S42: Establish a hierarchical model of energy waste factors; S43: Establish a judgment matrix A according to the hierarchical structure model. A=(a ij ) m×m Among them, a ij It represents the ratio of the influence degree of the i-th energy waste factor and the j-th energy waste factor in the judgment matrix A; S44: Normalization processing and calculation of the maximum eigenvalue λ and the corresponding eigenvector ω of each level of judgment matrix A i ; S45: consistency test of the judgment matrix A; if it passes, the eigenvector corresponding to the maximum eigenvalue of each level after normalization is the corresponding weight of the energy waste factor at each level; if it fails, the judgment matrix A is re-established according to the hierarchical structure model; S46: Determine whether the weights of each level are greater than the set value; if so, the energy waste factor corresponding to the weight is the key factor of energy waste; if not, the energy waste factor corresponding to the weight is not the key factor causing energy waste.

5. The regional distributed energy visualization method based on digital twin according to claim 2 is characterized by: The S5 simulation module uses a simulated annealing algorithm to simulate different management schemes to obtain simulation results, which specifically includes the following steps: S51: obtaining management parameter information of the management scheme, presetting the requirements of the management scheme as the objective function, wherein the requirements of the management scheme are one or more of energy conversion efficiency, energy storage, energy transmission efficiency, and user consumption respectively related to energy conversion factors, energy storage factors, energy transmission factors, and user consumption factors, and establishing the objective function of the management scheme; S52: Set the initial temperature T0 and the end temperature T B , the maximum number of iterations K at each temperature, the cooling rate α, and 0<α<1; S53: Assign the initial temperature T0 to S54: randomly setting an initial solution S0 for the management parameter information, and calculating the initial objective function value f(S0) required by the management solution; S55: The management parameter information generates a new optimal solution S1 in the neighborhood, and calculates the optimal solution objective function value f(S1) of the management solution requirements; S56: According to the difference Δf between the optimal solution objective function value and the initial objective function value, if the difference Δf is less than zero, the new optimal solution is judged to be better than the initial solution, and the new optimal solution replaces the initial solution; otherwise, the new optimal solution is accepted with a specific probability M. S57: k is the number of iterations, and k is initially 0, and the number of iterations k=k+1 is set to iterate, and S54 to S56 are repeated until k=K; S58: If The termination temperature T is not reached B , according to the exponential cooling strategy, that is The order is reduced, and the process returns to step S53. If the termination temperature T is reached, B , and output the optimal solution finally obtained by S57 as the optimal solution of the management plan.

6. The regional distributed energy visualization method based on digital twin according to claim 3 is characterized by: The data transformation rule in S21 is to extract field features of each data and encode each field feature accordingly, convert each data according to the corresponding code, sort the corresponding codes, and arrange the values ​​after data conversion according to the corresponding code sort.

7. The regional distributed energy visualization method based on digital twin according to claim 2 is characterized by: In S24, the two standardized data are compared, and a judgment is made according to the corresponding coding of each field feature, and the judgment index takes a percentage greater than 0 and less than or equal to 1.

Images