A global energy intelligent dispatching system for building photovoltaic integration

Abstract

The present invention discloses a building photovoltaic integrated global energy intelligent scheduling system. The present invention collects and analyzes the historical energy consumption data of each device in the building, constructs and updates the energy prediction model, and not only predicts the daily energy consumption of the equipment in the next week, but also predicts the output of photovoltaic power generation, so as to provide basic data for subsequent energy consumption optimization and intelligent scheduling; at the same time, the influence of the use time and service life of the equipment in the building on the energy consumption is taken into account, and the predicted energy consumption data is adjusted by analyzing the difference between the planned use time of the equipment next week and the historical average use time, and combining the service life of the equipment, so as to obtain a more accurate energy consumption prediction, thereby providing an accurate data basis for the subsequent formulation of energy scheduling strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to a building photovoltaic integrated global energy intelligent dispatching system. Background Art

[0002] The use of renewable energy has become an important way to save energy, reduce emissions and promote sustainable development; building photovoltaic integration technology, as an innovative way to combine solar photovoltaic power generation systems with building structures, has received widespread attention and application in the field of green buildings.

[0003] However, the building photovoltaic energy dispatching system in the existing technology still has the following shortcomings in practical application:

[0004] The energy consumption data of each device in the building in the next time period is not considered in the historical data of energy consumption. At the same time, there is a lack of in-depth analysis of the equipment usage time and service life in the prediction process, and the predicted data is not optimized based on the results of the in-depth analysis, resulting in inaccurate subsequent energy scheduling decisions.

[0005] Secondly, the existing system usually adopts a relatively simple scheduling strategy for energy consumption scheduling, without fully considering the impact of expert advice, carbon emissions and economic cost factors, making it difficult to achieve optimal energy scheduling.

[0006] To this end, a building photovoltaic integrated global energy intelligent scheduling system is introduced. Summary of the invention

[0007] In view of this, the present invention provides a building photovoltaic integrated global energy intelligent scheduling system to solve the problems raised by the above background technology.

[0008] The purpose of the present invention can be achieved through the following technical solutions: A building photovoltaic integrated global energy intelligent scheduling system, comprising:

[0009] Model building module: collects and analyzes the historical energy consumption data of each device in the building, and builds and updates the energy prediction model based on it; outputs the estimated energy consumption data of each device corresponding to the building from next Monday to Sunday based on the energy prediction model;

[0010] It is also used to output the predicted photovoltaic power generation of the building photovoltaic corresponding to the next Monday to Sunday;

[0011] Energy consumption optimization module: extract the usage schedule of each equipment from next Monday to Sunday and the service life of the equipment, conduct a comprehensive analysis, and obtain the final energy consumption data of each equipment in the building from next Monday to Sunday based on the analysis results;

[0012] Intelligent scheduling module: According to the final energy consumption data and predicted photovoltaic power generation of each device in the building from next Monday to Sunday, formulate the energy scheduling strategies corresponding to each day from next Monday to Sunday, analyze the preferred evaluation index Yk of each energy scheduling strategy, and select the energy scheduling strategy with the largest priority evaluation index Yk from the energy scheduling strategies corresponding to each day from next Monday to Sunday as the preferred strategy to be applied by the building from next Monday to Sunday;

[0013] Energy storage module: stores excess photovoltaic power generation energy;

[0014] Abnormal response module: monitors the energy consumption data of each device in the building during use and analyzes it, thereby obtaining the energy consumption evaluation index Nhi of each device in the building during use, where i=1, 2, ..., k, k is the total number of devices in the building; based on the energy consumption evaluation index Nhi of each device in the building, evaluates the abnormal status of each device.

[0015] In some embodiments, the estimated energy consumption data of each device corresponding to the building from next Monday to Sunday is output based on the energy prediction model, specifically:

[0016] Taking the current time point as the starting time point, extract the energy consumption data used by each device in the building from Monday to Sunday every day for the last seven times before the starting time point, and take the average of the energy consumption data of the last seven Mondays as the estimated energy consumption data output by the energy prediction model for the building when it arrives next Monday; similarly, output the estimated energy consumption data output by the building when it arrives from next Tuesday to next Sunday;

[0017] At the end of next Monday, the actual energy consumption data of each device in the building on next Monday will be transmitted to the energy forecast model for updating.

[0018] In some embodiments, the usage schedule of each device from Monday to Sunday next week is extracted and analyzed comprehensively, specifically:

[0019] Extract the required operating time of each device corresponding to the next Monday from the usage schedule of each device in the building and record it as the equipment usage time;

[0020] Extract the running time of each device in the building on each Monday for the past seven days from the model building module, and take the average to obtain the average running time of each device;

[0021] Compare the device usage time with the average operating time. If the device usage time is longer than the average operating time, calculate the time difference between the two and record the difference as the excess time.

[0022] If the device usage time is lower than the average operation time, the time difference between the two is calculated and the difference is recorded as the under-use time;

[0023] Preset the value ranges of each group of durations corresponding to the exceeded duration and the under-exit duration respectively, set a high-exit coefficient and a low-exit coefficient to correspond to each group of value ranges corresponding to the exceeded duration and the under-exit duration respectively, match the exceeded duration or under-exit duration of each device in the building corresponding to the next Monday with the corresponding preset value ranges of each group of durations, thereby obtaining the high-exit coefficient or low-exit coefficient of each device in the building corresponding to the next Monday;

[0024] Extract the estimated energy consumption data of each device in the building for the next Monday, and multiply it with the corresponding high output coefficient or low output coefficient obtained by matching, and use the multiplication result as the adjusted energy consumption data of each device in the building for the next Monday;

[0025] Similarly, the above-mentioned adjusted energy consumption data of each device in the building corresponding to next Tuesday to Sunday is obtained.

[0026] In some embodiments, the final energy consumption data of each device in the building corresponding to the next Monday to Sunday is obtained, specifically:

[0027] Obtain the service life of each device, preset each group of service life value ranges of each device, set each group of service life value ranges corresponding to each device to correspond to an optimization coefficient; match the service life of each device with the corresponding preset group of service life value ranges, so as to obtain the optimization coefficient matched by each device;

[0028] Extract the adjusted energy consumption data of each device in the building corresponding to the next Monday, and multiply it with the corresponding optimization coefficient, and use the multiplication result as the final energy consumption data of each device in the building corresponding to the next Monday;

[0029] Similarly, the final energy consumption data of each device in the building from next Tuesday to Sunday is obtained.

[0030] In some embodiments, the preferred evaluation index Yk of each group of energy scheduling strategies is analyzed, specifically:

[0031] Send the formulated energy scheduling strategies to the expert review system; the expert review system evaluates the formulated energy scheduling strategies and scores them; the scores of the energy scheduling strategies are recorded as expert scores Zd1;

[0032] The estimated carbon emissions generated by each group of energy scheduling strategies are marked as Zd2; the estimated economic costs of each group of energy scheduling strategies are marked as Zd3;

[0033] The expert passing score, the allowed carbon emissions and the maximum acceptable economic cost corresponding to the preset expert score Zd1, the estimated carbon emissions Zd2 and the estimated economic cost Zd3 are marked as Zr1, Zr2 and Zr3 respectively;

[0034] According to the formula , the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 of each group of energy scheduling strategies are weightedly calculated to obtain the optimal evaluation index Yk of each group of energy scheduling strategies; among which g1, g2 and g3 are the influencing weight factors of the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 respectively.

[0035] In some embodiments, the energy consumption data of each device in the building during use is monitored and analyzed, specifically:

[0036] Mark the time point when each device in the building starts to operate as the start time point, extract the energy consumption data of each device in the set time period after the start time point; set the baseline energy consumption of each device;

[0037] Extract the energy consumption data of the corresponding equipment at each time point in the set time period, and construct the energy consumption change graph of the corresponding equipment in the set time period; draw the numerical points corresponding to the energy consumption data of the corresponding equipment at each time point in the change graph, and connect the adjacent numerical points to obtain the energy consumption line; extract the baseline energy consumption of the corresponding equipment, set the upper limit of the allowable fluctuation value of the baseline energy consumption, add the baseline energy consumption and the corresponding set upper limit of the allowable fluctuation value as the peak energy consumption, take the baseline energy consumption of the corresponding equipment as the minimum value, and the peak energy consumption as the maximum value, and construct the reference energy consumption range of the corresponding equipment;

[0038] Draw the reference energy consumption range of the corresponding equipment corresponding to the threshold range in the change diagram; mark the numerical points above the threshold range, and count the number of marks as the number of excesses of the corresponding equipment within the set time period.

[0039] In some embodiments, monitoring the energy consumption data of each device in the building during use and analyzing it further includes:

[0040] Taking the numerical points of each mark as reference points, construct vertical lines between each group of reference points and the threshold range, calculate the length of each group of vertical lines, and add them up as the excess line length of the corresponding device within the set time period;

[0041] Calculate the slope of each energy consumption line and the angle between it and the horizontal line. If the angle between an energy consumption line and the horizontal line is an acute angle, mark the slope of the energy consumption line as a descending slope. If the angle between an energy consumption line and the horizontal line is an obtuse angle, mark the slope of the energy consumption line as an ascending slope. Sum all the ascending slopes and descending slopes respectively to obtain the total ascending value and the total descending value of the corresponding equipment within the set time period.

[0042] Calculate the ratio of the total rising value to the total falling value, that is, the total rising value / the total falling value, and obtain the energy consumption change value of the corresponding equipment within the set time period;

[0043] The number of exceeded devices, the exceeded line length and the energy consumption change value of the corresponding devices within the set time period are marked as fa, fb and fc respectively;

[0044] Set the reference maximum values ​​corresponding to the number of devices exceeded fa, the line length exceeded fb, and the energy consumption change value fc, and mark them as , as well as ;

[0045] Substitute the excess number fa, excess line length fb and energy consumption change fc of the corresponding equipment into the formula , perform weighted calculation to obtain the energy consumption evaluation index Nhi of the corresponding equipment within the set time period; where t1, t2 and t3 are the influence weight factors of the excess number fa, excess line length fb and energy consumption change value fc respectively.

[0046] In some embodiments, based on the energy consumption evaluation index Nhi of each device in the building, the abnormal state of each device is evaluated, specifically:

[0047] A reference threshold index of the energy consumption assessment index Nhi of the corresponding equipment is preset. If the energy consumption assessment index Nhi of the corresponding equipment is greater than the corresponding preset reference threshold index, the state of the corresponding equipment will be marked as an abnormal energy consumption state, and the number and location of the corresponding equipment in the abnormal energy consumption state will be sent to the mobile terminal of the administrator.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention collects and analyzes the historical energy consumption data of each device in the building, constructs and updates the energy prediction model, and not only predicts the daily energy consumption of the equipment in the next week, but also predicts the output of photovoltaic power generation, providing basic data for subsequent energy consumption optimization and intelligent scheduling; at the same time, the impact of the use time and service life of the equipment in the building on energy consumption is considered, and the predicted energy consumption data is adjusted by analyzing the difference between the planned use time of the equipment next week and the historical average use time, and combining the service life of the equipment, to obtain a more accurate energy consumption forecast, thereby providing an accurate data basis for the subsequent formulation of energy scheduling strategies;

[0050] The present invention formulates energy dispatch strategies for each day of the week based on the adjusted energy consumption data and predicted photovoltaic power generation; obtains the priority evaluation index of each group of energy dispatch strategies by evaluating the expert scores of different strategies, estimating carbon emissions and economic costs, and selects the energy dispatch strategy with the largest priority evaluation index, thereby achieving optimization of energy dispatch and improving the accuracy of energy dispatch;

[0051] The present invention monitors the energy consumption data of equipment in the building in real time, analyzes the energy consumption change graph and calculates the energy consumption evaluation index, promptly discovers abnormal energy consumption status, and notifies management personnel to handle it, thereby realizing intelligent identification of abnormal energy consumption equipment while scheduling energy, thereby improving the degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0053] Figure 1 It is a principle block diagram of the present invention;

[0054] Figure 2 It is a schematic diagram of the energy consumption variation diagram in the present invention. DETAILED DESCRIPTION

[0055] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete, and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0056] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined as such herein.

[0057] See also Figure 1-Figure 2 As shown, a building photovoltaic integrated global energy intelligent scheduling system includes a model building module, an energy consumption optimization module, an intelligent scheduling module, an energy storage module and an abnormal response module;

[0058] The model building module is used to collect and analyze the historical energy consumption data of each device in the building, and to build and update the energy prediction model based on this data; the equipment includes air conditioners, televisions, and gas used in the building; based on the energy prediction model, the estimated energy consumption data of each device corresponding to the building from next Monday to Sunday is output;

[0059] It is also used to output the predicted photovoltaic power generation of the building photovoltaic corresponding to the next Monday to Sunday; the least squares support vector machine (LS-SVM) combined with the particle swarm optimization algorithm (PSO) is used to predict the photovoltaic power of the day;

[0060] It should be noted that the PSO-LSSVM model first uses the PSO algorithm to determine the penalty factor and kernel function parameters in the LS-SVM, which are crucial to improving prediction accuracy; then, the model is trained using historical data. After training, the model can predict future photovoltaic power generation based on input features, such as solar radiation, temperature, etc.

[0061] Specifically:

[0062] Taking the current time point as the starting time point, extract the energy consumption data used by each device in the building from Monday to Sunday every day for the last seven times before the starting time point, and take the average of the energy consumption data of the last seven Mondays as the estimated energy consumption data output by the energy prediction model for the building when it arrives next Monday; similarly, output the estimated energy consumption data output by the building when it arrives from next Tuesday to next Sunday;

[0063] At the end of the next Monday, the actual energy consumption data of each device in the building on the next Monday will be transmitted to the energy forecast model for updating;

[0064] The energy consumption optimization module is used to extract the usage schedule of each equipment in the building from next Monday to Sunday and the service life of the equipment, conduct a comprehensive analysis, and obtain the final energy consumption data of each equipment in the building from next Monday to Sunday based on the analysis results;

[0065] Specifically:

[0066] Extract the required operating time of each device corresponding to the next Monday from the usage schedule of each device in the building and record it as the equipment usage time;

[0067] Extract the running time of each device in the building on each Monday for the past seven days from the model building module, and take the average to obtain the average running time of each device;

[0068] Compare the device usage time with the average operating time. If the device usage time is longer than the average operating time, calculate the time difference between the two and record the difference as the excess time.

[0069] If the device usage time is lower than the average operation time, the time difference between the two is calculated and the difference is recorded as the under-use time;

[0070] Preset the value ranges of each group of durations corresponding to the exceeded duration and the under-exit duration respectively, set a high-exit coefficient and a low-exit coefficient to correspond to each group of value ranges corresponding to the exceeded duration and the under-exit duration respectively, match the exceeded duration or under-exit duration of each device in the building corresponding to the next Monday with the corresponding preset value ranges of each group of durations, thereby obtaining the high-exit coefficient or low-exit coefficient of each device in the building corresponding to the next Monday;

[0071] It should be noted that the high coefficient is greater than 1, and the low coefficient is less than 1 but greater than 0;

[0072] For example:

[0073] Determine how long the device is in use:

[0074] From the schedule, we learned that the air conditioning system of the office building is scheduled to run for 10 hours, the lighting system for 12 hours, the elevator for 8 hours, and the office computers for 8 hours next Monday;

[0075] Extract average runtime:

[0076] Looking at the energy consumption data for the past seven Mondays, we get the following average operating hours for each device: air conditioning system: 8.5 hours;

[0077] Lighting system: 11 hours;

[0078] Elevator: 7.5 hours;

[0079] Office computer: 9 hours;

[0080] Calculate the overtime or undertime:

[0081] Air conditioning system: 10 hours (use time) - 8.5 hours (average use time) = 1.5 hours (excess use time)

[0082] Lighting system: 12 hours (use time) - 11 hours (average use time) = 1 hour (excess use time)

[0083] Elevator: 8 hours (duration) - 7.5 hours (average duration) = 0.5 hours (excess duration)

[0084] Office computer: 9 hours (average time) - 8 hours (usage time) = 1 hour (low time)

[0085] Set the duration value range and coefficient:

[0086] Suppose we set the following range and excess factor for the duration: 0 to 1 hour: excess factor 1.1

[0087] 1 to 2 hours: 1.2 higher factor

[0088] More than 2 hours: 1.3 higher coefficient

[0089] The following value range and low-out coefficient are set for the low-out duration: 0 to 1 hour: low-out coefficient 0.9

[0090] 1 to 2 hours: Low output factor 0.8

[0091] More than 2 hours: low output coefficient 0.7

[0092] Match duration and calculate coefficients:

[0093] Air conditioning system: 1.5 hours falls within the range of 1 to 2 hours, with a factor of 1.2 above that.

[0094] Lighting system: 1 hour falls within the range of 0 to 1 hour, with an excess factor of 1.1.

[0095] Elevator: 0.5 hours falls within the range of 0 to 1 hour, with a factor of excess of 1.1.

[0096] Office computer: 1 hour falls within the range of 0 to 1 hour, with a low coefficient of 0.9.

[0097] Apply the coefficients to adjust the energy consumption forecast:

[0098] According to these factors, the estimated energy consumption data is adjusted. For example: Air conditioning system:

[0099] Original predicted energy consumption × 1.2;

[0100] Lighting system: original predicted energy consumption × 1.1

[0101] Elevator: original predicted energy consumption × 1.1

[0102] Office computers: original predicted energy consumption × 0.9.

[0103] Extract the estimated energy consumption data of each device in the building for the next Monday, and multiply it with the corresponding high output coefficient or low output coefficient obtained by matching, and use the multiplication result as the adjusted energy consumption data of each device in the building for the next Monday;

[0104] Obtain the service life of each device, preset each group of service life value ranges of each device, set each group of service life value ranges corresponding to each device to correspond to an optimization coefficient; match the service life of each device with the corresponding preset group of service life value ranges, so as to obtain the optimization coefficient matched by each device;

[0105] Set the reference years of service life of each device to adjust the optimization coefficient. For example, if the service life of the device is higher than the set reference years, the optimization coefficient obtained by the corresponding matching is greater than 1. If the service life of the device is lower than the set reference years, the optimization coefficient obtained by the corresponding matching is less than 1 and greater than 0.

[0106] The maintenance status and aging of equipment will affect its energy consumption. As the equipment is used for a longer time, the operating efficiency of the equipment will decrease due to mechanical wear, component performance degradation, insufficient maintenance and other factors, resulting in increased energy consumption.

[0107] Extract the adjusted energy consumption data of each device in the building corresponding to next Monday, and multiply it with the corresponding optimization coefficient, and use the multiplication result as the final energy consumption data of each device in the building corresponding to next Monday; similarly, obtain the final energy consumption data of each device in the building corresponding to next Tuesday to Sunday;

[0108] The intelligent scheduling module is used to formulate various energy scheduling strategies corresponding to the building from Monday to Sunday next week according to the final energy consumption data of each device in the building from Monday to Sunday next week and the predicted photovoltaic power generation, analyze the preferred evaluation index Yk of each energy scheduling strategy, and select the energy scheduling strategy with the largest priority evaluation index Yk from the various energy scheduling strategies corresponding to Monday to Sunday next week as the preferred strategy to be applied by the building from Monday to Sunday next week;

[0109] Specifically:

[0110] First, the formulated energy scheduling strategies are sent to the expert review system; the strategy can be sent to a mailbox pre-created by the expert review system; the expert review system evaluates the formulated energy scheduling strategies and gives scores to the energy scheduling strategies; the score range is set to 50-100 and is a positive integer; the score of each energy scheduling strategy is recorded as the expert score Zd1;

[0111] The estimated carbon emissions generated by each group of energy scheduling strategies are marked as Zd2; the estimated economic costs of each group of energy scheduling strategies are marked as Zd3;

[0112] By comprehensively analyzing the estimated carbon emissions and estimated economic costs of each group of energy scheduling strategies, the feasibility of each group of energy scheduling strategies was comprehensively evaluated;

[0113] The expert passing score, the allowed carbon emissions and the maximum acceptable economic cost corresponding to the preset expert score Zd1, the estimated carbon emissions Zd2 and the estimated economic cost Zd3 are marked as Zr1, Zr2 and Zr3 respectively;

[0114] It should be noted that the expert passing score, allowable carbon emissions and acceptable maximum economic cost are set by technical personnel based on the authority of the experts, the requirements of the building's environment and the economic affordability.

[0115] According to the formula , the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 of each group of energy scheduling strategies are weighted and calculated to obtain the optimal evaluation index Yk of each group of energy scheduling strategies; where g1, g2 and g3 are the influencing weight factors of the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 respectively;

[0116] The energy storage module is used to store excess photovoltaic power generation energy;

[0117] Releasing energy during times of peak demand or low sunlight to smooth out fluctuations in electricity supply;

[0118] The abnormal response module is used to monitor the energy consumption data of each device in the building during use and analyze it, thereby obtaining the energy consumption evaluation index Nhi of each device in the building during use, where i=1, 2, ..., k, k is the total number of devices in the building; based on the energy consumption evaluation index Nhi of each device in the building, the abnormal state of each device is evaluated;

[0119] Specifically:

[0120] The time point when each device in the building starts to operate is marked as the start time point, and the energy consumption data of each device in the set time period after the start time point is extracted; the set time period is, for example, one hour or half an hour, which is specifically set by the technical staff;

[0121] Set the baseline energy consumption of each device; set it according to the type and purpose of the device, and the baseline energy consumption is set according to the average energy consumption of the corresponding device's historical data;

[0122] Extract the energy consumption data of the corresponding equipment at each time point in the set time period, and construct the energy consumption change graph of the corresponding equipment in the set time period;

[0123] Draw the energy consumption data of the corresponding equipment at each time point corresponding to the numerical points in the change diagram, and connect the adjacent numerical points to obtain the energy consumption line;

[0124] Extract the baseline energy consumption of the corresponding equipment, set the upper limit of the allowable fluctuation value of the baseline energy consumption, add the baseline energy consumption and the corresponding set upper limit of the allowable fluctuation value to obtain the peak energy consumption, take the baseline energy consumption of the corresponding equipment as the minimum value and the peak energy consumption as the maximum value, and construct the reference energy consumption range of the corresponding equipment; the upper limit of the allowable fluctuation value indicates the maximum value that the baseline energy consumption of the corresponding equipment is allowed to exceed, and is set by the technical staff;

[0125] Draw the reference energy consumption range of the corresponding equipment corresponding to the threshold range in the change diagram; mark the value points above the threshold range, and count the number of marks as the number of exceeding the corresponding equipment in the set time period;

[0126] Taking the numerical points of each mark as reference points, construct vertical lines between each group of reference points and the threshold range, calculate the length of each group of vertical lines, and add them up as the excess line length of the corresponding device within the set time period;

[0127] Calculate the slope of each energy consumption line and the angle between it and the horizontal line. If the angle between an energy consumption line and the horizontal line is an acute angle, mark the slope of the energy consumption line as a descending slope. If the angle between an energy consumption line and the horizontal line is an obtuse angle, mark the slope of the energy consumption line as an ascending slope. Sum all the ascending slopes and descending slopes respectively to obtain the total ascending value and the total descending value of the corresponding equipment within the set time period.

[0128] Calculate the ratio of the total rising value to the total falling value, that is, the total rising value / the total falling value, and obtain the energy consumption change value of the corresponding equipment within the set time period;

[0129] The number of exceeded devices, the exceeded line length and the energy consumption change value of the corresponding devices within the set time period are marked as fa, fb and fc respectively;

[0130] Set the reference maximum values ​​corresponding to the number of devices exceeded fa, the line length exceeded fb, and the energy consumption change value fc, and mark them as , as well as ;

[0131] Substitute the excess number fa, excess line length fb and energy consumption change fc of the corresponding equipment into the formula , perform weighted calculation to obtain the energy consumption evaluation index Nhi of the corresponding equipment within the set time period; where t1, t2 and t3 are the influence weight factors of the excess number fa, excess line length fb and energy consumption change value fc respectively;

[0132] It should be noted that, in summary, by accurately monitoring and analyzing the energy consumption of equipment to obtain the energy consumption assessment index Nhi of the corresponding equipment, it is possible to identify energy consumption anomalies, thereby taking measures to optimize energy use and reduce unnecessary energy waste.

[0133] Based on the energy consumption evaluation index Nhi of each device in the building, the abnormal status of each device is evaluated, specifically:

[0134] A reference threshold index of the energy consumption evaluation index Nhi of the corresponding device is preset. If the energy consumption evaluation index Nhi of the corresponding device is greater than the corresponding preset reference threshold index, the state of the corresponding device is marked as an abnormal energy consumption state, and the number and location of the corresponding device in the abnormal energy consumption state are sent to the mobile terminal of the manager;

[0135] Managers can use mobile terminals to remotely shut down the operation of corresponding equipment and go to the location of the corresponding equipment to inspect and repair the equipment;

[0136] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factor and specific coefficient value in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0137] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A building photovoltaic integrated global energy intelligent dispatching system, characterized in that: include: Model building module: collects and analyzes the historical energy consumption data of each device in the building, and builds and updates the energy prediction model based on it; outputs the estimated energy consumption data of each device corresponding to the building from next Monday to Sunday based on the energy prediction model; It is also used to output the predicted photovoltaic power generation of the building photovoltaic corresponding to the next Monday to Sunday; Based on the energy prediction model, the estimated energy consumption data of each device corresponding to the building from next Monday to Sunday is output, specifically: Taking the current time point as the starting time point, extract the energy consumption data used by each device in the building from Monday to Sunday every day for the last seven times before the starting time point, and take the average of the energy consumption data of the last seven Mondays as the estimated energy consumption data output by the energy prediction model for the building when it arrives next Monday; similarly, output the estimated energy consumption data output by the building when it arrives from next Tuesday to next Sunday; At the end of the next Monday, the actual energy consumption data of each device in the building on the next Monday will be transmitted to the energy forecast model for updating; Energy consumption optimization module: extract the usage schedule of each equipment from next Monday to Sunday and the service life of the equipment, conduct a comprehensive analysis, and obtain the final energy consumption data of each equipment in the building from next Monday to Sunday based on the analysis results; Extract the usage schedule of each equipment from next Monday to Sunday and conduct a comprehensive analysis. The specific steps are as follows: S1: Extract the required operating time of each device corresponding to the next Monday from the usage schedule of each device in the building, and record it as the equipment usage time; Extract the running time of each device in the building on each Monday for the past seven days from the model building module, and take the average to obtain the average running time of each device; Compare the device usage time with the average operating time. If the device usage time is longer than the average operating time, calculate the time difference between the two and record the difference as the excess time. If the device usage time is lower than the average operation time, the time difference between the two is calculated and the difference is recorded as the under-use time; Preset the value ranges of each group of durations corresponding to the exceeded duration and the under-exit duration respectively, set a high-exit coefficient and a low-exit coefficient to correspond to each group of value ranges corresponding to the exceeded duration and the under-exit duration respectively, match the exceeded duration or under-exit duration of each device in the building corresponding to the next Monday with the corresponding preset value ranges of each group of durations, thereby obtaining the high-exit coefficient or low-exit coefficient of each device in the building corresponding to the next Monday; S2: extract the estimated energy consumption data of each device in the building corresponding to the next Monday, and multiply it with the corresponding matching high output coefficient or low output coefficient, and use the multiplication result as the adjusted energy consumption data of each device in the building corresponding to the next Monday; Similarly, steps S1 to S2 are performed to obtain the adjusted energy consumption data of each device in the building corresponding to next Tuesday to Sunday; Get the final energy consumption data of each device in the building from next Monday to Sunday. The specific steps are: M1: Obtain the service life of each device, preset the service life value ranges of each device, set an optimization coefficient for each service life value range corresponding to each device; match the service life of each device with the preset service life value ranges, so as to obtain the optimization coefficient matched by each device; M2: Extract the adjusted energy consumption data of each device in the building corresponding to the next Monday, and multiply it with the corresponding optimization coefficient, and use the multiplication result as the final energy consumption data of each device in the building corresponding to the next Monday; Similarly, steps M1 to M2 are repeated to obtain the final energy consumption data of each device in the building from next Tuesday to Sunday; Intelligent scheduling module: According to the final energy consumption data and predicted photovoltaic power generation of each device in the building from next Monday to Sunday, formulate the energy scheduling strategies corresponding to each day from next Monday to Sunday, analyze the preferred evaluation index Yk of each energy scheduling strategy, and select the energy scheduling strategy with the largest priority evaluation index Yk from the energy scheduling strategies corresponding to each day from next Monday to Sunday as the preferred strategy to be applied by the building from next Monday to Sunday; Analyze the optimal evaluation index Yk of each group of energy scheduling strategies, specifically: Send the formulated energy scheduling strategies to the expert review system; after the experts evaluate the formulated energy scheduling strategies, they score the energy scheduling strategies; the scores of the energy scheduling strategies are recorded as expert scores Zd1; The estimated carbon emissions generated by each group of energy scheduling strategies are marked as Zd2; the estimated economic costs of each group of energy scheduling strategies are marked as Zd3; The expert passing score, the allowed carbon emissions and the maximum acceptable economic cost corresponding to the preset expert score Zd1, the estimated carbon emissions Zd2 and the estimated economic cost Zd3 are marked as Zr1, Zr2 and Zr3 respectively; According to the formula , the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 of each group of energy scheduling strategies are weighted and calculated to obtain the optimal evaluation index Yk of each group of energy scheduling strategies; where g1, g2 and g3 are the influencing weight factors of the expert score Zd1, estimated carbon emissions Zd2 and estimated economic cost Zd3 respectively; Energy storage module: stores excess photovoltaic power generation energy; Abnormal response module: monitors the energy consumption data of each device in the building during use and analyzes it, thereby obtaining the energy consumption evaluation index Nhi of each device in the building during use, where i=1, 2, ..., k, k is the total number of devices in the building; based on the energy consumption evaluation index Nhi of each device in the building, evaluates the abnormal status of each device; Monitor the energy consumption data of each device in the building during use and analyze it, specifically: Mark the time point when each device in the building starts to operate as the start time point, extract the energy consumption data of each device in the set time period after the start time point; set the baseline energy consumption of each device; Extract the energy consumption data of the corresponding equipment at each time point in the set time period, and construct the energy consumption change graph of the corresponding equipment in the set time period; draw the numerical points corresponding to the energy consumption data of the corresponding equipment at each time point in the change graph, and connect the adjacent numerical points to obtain the energy consumption line; Extract the baseline energy consumption of the corresponding equipment, set the upper limit of the allowable fluctuation value of the baseline energy consumption, add the baseline energy consumption and the corresponding set upper limit of the allowable fluctuation value as the peak energy consumption, take the baseline energy consumption of the corresponding equipment as the minimum value and the peak energy consumption as the maximum value, and construct the reference energy consumption range of the corresponding equipment; Draw the reference energy consumption range of the corresponding equipment corresponding to the threshold range in the change diagram; mark the value points above the threshold range, and count the number of marks as the number of exceeding the corresponding equipment in the set time period; Monitor the energy consumption data of each device in the building during use and analyze it, including: Taking the numerical points of each mark as reference points, construct vertical lines between each group of reference points and the threshold range, calculate the length of each group of vertical lines, and add them up as the excess line length of the corresponding device within the set time period; Calculate the slope of each energy consumption line and the angle between it and the horizontal line. If the angle between an energy consumption line and the horizontal line is an acute angle, mark the slope of the energy consumption line as a descending slope. If the angle between an energy consumption line and the horizontal line is an obtuse angle, mark the slope of the energy consumption line as an ascending slope. Sum all the ascending slopes and descending slopes respectively to obtain the total ascending value and the total descending value of the corresponding equipment within the set time period. Calculate the ratio of the total rising value to the total falling value, that is, the total rising value / the total falling value, and obtain the energy consumption change value of the corresponding equipment within the set time period; The number of exceeded devices, the exceeded line length and the energy consumption change value of the corresponding devices within the set time period are marked as fa, fb and fc respectively; Set the reference maximum values ​​corresponding to the number of devices exceeded fa, the line length exceeded fb, and the energy consumption change value fc, and mark them as , as well as ; Substitute the excess number fa, excess line length fb and energy consumption change fc of the corresponding equipment into the formula , perform weighted calculation to obtain the energy consumption evaluation index Nhi of the corresponding equipment within the set time period; where t1, t2 and t3 are the influence weight factors of the excess number fa, excess line length fb and energy consumption change value fc respectively.

2. A building photovoltaic integrated global energy intelligent dispatching system according to claim 1, characterized in that: Based on the energy consumption evaluation index Nhi of each device in the building, the abnormal status of each device is evaluated, specifically: A reference threshold index of the energy consumption assessment index Nhi of the corresponding equipment is preset. If the energy consumption assessment index Nhi of the corresponding equipment is greater than the corresponding preset reference threshold index, the state of the corresponding equipment will be marked as an abnormal energy consumption state, and the number and location of the corresponding equipment in the abnormal energy consumption state will be sent to the mobile terminal of the administrator.

Images