Photovoltaic wind power energy storage intelligent management method and system for building

Abstract

The invention provides a photovoltaic wind power energy storage intelligent management method and system for a building. The method comprises the following steps: acquiring operation parameters, environmental conditions and historical fault data records of system equipment, and preprocessing the acquired data; establishing health assessment indexes by using the comprehensive wind and light energy storage equipment performance model, and determining the health degrees of different equipment; the fault abnormity level is judged according to the fault alarm signal sending time and frequency of the system equipment; through combination of an autoregressive differential moving average model and a long-short-term memory model, the photovoltaic and wind power comprehensive electric quantity is predicted, and the loss abnormity level is judged; and in combination with the health degree, the fault abnormity level and the loss abnormity level of the equipment, making a patrol inspection and daily maintenance work plan, and sending out reminding and early warning. By analyzing and diagnosing key equipment and core performance of the system and early warning key events, energy waste and equipment damage caused by improper maintenance can be effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy power, and particularly to an intelligent management method and system for photovoltaic wind power energy storage in buildings. Background Art

[0002] Nowadays, the application of photovoltaic wind power energy storage devices in the construction field is becoming increasingly widespread. The daily maintenance of such unconventional building power equipment is crucial for ensuring building safety, power safety, personnel safety, and energy efficiency. Generally speaking, maintenance personnel should formulate inspection and daily maintenance work plans by combining the operating environment of new energy power stations, inspection records, and the status of operating indicators. However, during the comprehensive management of multiple energy devices, the operation data is redundant. Building users usually lack professional knowledge and analysis capabilities of new energy devices, and the dispatch and regular inspection personnel often have delays, resulting in difficulties in operation and maintenance management, leading to problems such as insufficient utilization rate of the energy system or even scrapping.

[0003] In addition, building users usually lack professional knowledge and analysis capabilities of new energy devices. At the same time, individuals are highly sensitive to the cost of purchasing professional operation and maintenance services, resulting in difficulties in operation and maintenance management during the operation of building new energy systems, leading to insufficient utilization rate of the energy system or even scrapping. Such management groups are not professional technical personnel in the field of electricity or new energy operation and maintenance management, and it is difficult to understand various energy system operation analysis indicators, resulting in neglect of management. The energy system fails to generate the due value, and there is even a situation where actions are taken to stop losses only when the building main body is damaged to a relatively serious degree, causing irreparable cost losses.

[0004] To solve the problems of difficult new energy management and low energy utilization efficiency in buildings, an intelligent management method for photovoltaic wind power energy storage devices is provided. Summary of the Invention

[0005] In view of the above-mentioned technical problems, an intelligent management method and system for photovoltaic wind power energy storage in buildings are provided. The present invention utilizes a data acquisition and processing module, an equipment performance evaluation module, a fault and anomaly diagnosis module, a loss and anomaly diagnosis module, and a reminder and warning module to optimize the management process of new energy devices through an intelligent solution, improve the energy utilization efficiency, and promote the sustainable development of the construction industry.

[0006] The technical means adopted by the present invention are as follows:

[0007] An intelligent management method for photovoltaic wind power energy storage in buildings, comprising:

[0008] Collecting the operating parameters, environmental conditions, and historical fault data records of system equipment, and preprocessing the collected data;

[0009] Using the performance model of the integrated wind-solar energy storage equipment, establish health assessment indicators to determine the health status of different equipment;

[0010] Based on the time and frequency of the fault alarm signals of the system equipment, judge the level of fault abnormality;

[0011] Through the combination of the autoregressive integrated moving average model and the long short-term memory model, predict the integrated photovoltaic and wind power, and judge the level of loss abnormality;

[0012] Combining the health status of the equipment, the level of fault abnormality and the level of loss abnormality, formulate inspection and daily maintenance work plans, and issue reminders and early warnings.

[0013] Furthermore, the preprocessing of the collected data specifically includes: setting the upper and lower limits of various types of data and eliminating communication abnormal data.

[0014] Furthermore, the health assessment indicators include: the deviation degree of the equipment standard performance, the equipment failure rate and the over-limit rate of the equipment key indicators, where:

[0015] The deviation degree of the equipment standard performance is determined by comparing the equipment with the theoretical performance under the standard working conditions or the benchmark equipment and statistically evaluating the degree to which the performance deviation between the equipment and the theoretical performance or the benchmark equipment exceeds the set threshold within the evaluation period;

[0016] The equipment failure rate is determined by obtaining the failure duration of the equipment from the historical failure data records of the equipment and statistically calculating the proportion of the equipment failure duration in the evaluation period within the evaluation period;

[0017] The over-limit rate of the equipment key indicators is determined by obtaining the key indicators corresponding to different equipment and statistically calculating the proportion of the equipment key indicators exceeding the set threshold within the evaluation period.

[0018] Furthermore, the prediction of the integrated photovoltaic and wind power through the combination of the autoregressive integrated moving average model and the long short-term memory model specifically includes:

[0019] Using the autoregressive integrated moving average model to predict the integrated photovoltaic and wind power:

[0020] Arrange the historical integrated photovoltaic and wind power sequence according to time as a time series, use the ADF test and the KPSS test to judge whether the time series is stationary, and use the p-value to evaluate the accuracy of the test results; if the p-value of the ADF test is less than 0.05 or the p-value of the KPSS test is greater than 0.05, it is determined that the time series data is stationary, otherwise perform a differencing operation until the time series data is stationary, and determine the differencing coefficient d;

[0021] The partial autocorrelation coefficient test is used to determine the autoregressive order m, the autocorrelation coefficient ACF test is used to determine the moving average order q, and the AIC value is calculated. The model parameters m and q with the smallest AIC value are selected to determine the autoregressive integrated moving average model;

[0022] The determined autoregressive integrated moving average model is evaluated by means of hypothesis testing to check whether the residual sequence of the model is a white noise sequence. If the residual sequence is not a white noise sequence, the model parameters and the model are re-determined; the determined autoregressive integrated moving average model is used to predict the combined photovoltaic and wind power;

[0023] The combined photovoltaic and wind power is predicted using a long short-term memory model:

[0024] The meteorological data within the evaluation period is collected and subjected to data standardization processing; the weather type, temperature, wind speed, and humidity parameter information are used as inputs on a daily basis, and the predicted combined photovoltaic and wind power is used as the output for training the long short-term memory model and saving the parameters; the meteorological data is input into the trained long short-term memory model for prediction to obtain the predicted combined photovoltaic and wind power;

[0025] Combining the prediction results of the autoregressive integrated moving average model and the long short-term memory model, the combined photovoltaic and wind power is comprehensively predicted:

[0026] According to the monthly meteorological forecast score information, the curve of the meteorological parameter error changing with time is obtained, and the different meteorological parameter error curves are fitted based on the correlation reflected by the correlation coefficient to obtain the initial value of the curve in an approximate exponential form:

[0027] X t = a H ×H t + a T ×T t + a W ×W t

[0028] where X t is the proportion of the autoregressive integrated moving average model; H t is the relative error value reflected by the humidity score on the t-th day, T t is the relative error value reflected by the temperature score on the t-th day, W t is the relative error value reflected by the wind speed score on the t-th day; a H , a T , a W are the normalization coefficients of the influence of meteorological parameters on power generation.

[0029] The historical data is substituted for optimization using the optimization rules:

[0030]

[0031] 2Y t -X t =1(0≤X t ≤1)

[0032] Among them, Y t -X t is the proportion of the long short-term memory model; is the predicted value of the autoregressive integrated moving average model on the t-th day, is the measured value of the long short-term memory model on the t-th day; r t is the actual value of the combined photovoltaic and wind power generation on the t-th day.

[0033] Furthermore, by combining the health degree, fault abnormality level and loss abnormality level of the equipment, a patrol inspection and daily maintenance work plan is formulated, specifically including:

[0034] According to weather data, equipment performance, patrol inspection records and abnormal events, by combining the health degree, fault abnormality level and loss abnormality level of the equipment, a patrol inspection and daily maintenance work plan is formulated, where:

[0035] According to the weather forecast, remind the management personnel to conduct safety inspections before and after special weather, and set the reminder event level according to the severity of the weather;

[0036] According to the equipment performance, when the equipment performance evaluation score is lower than the health threshold, remind the management personnel to increase the number of inspections, and set the reminder event level according to the deviation value between the current health value and the health threshold;

[0037] According to the patrol inspection record, when the number of days since the last patrol inspection exceeds the patrol inspection cycle threshold, remind the management personnel to conduct a patrol inspection in a timely manner;

[0038] According to the abnormal event, convert the losses, power usage conditions and electricity prices generated by the abnormal equipment and expected to be generated within the next week into economic loss values, and conduct hierarchical early warnings.

[0039] The present invention further includes a photovoltaic and wind power energy storage intelligent management system for buildings, including: a data acquisition and processing module, an equipment performance evaluation module, a fault abnormality diagnosis module, a loss abnormality diagnosis module, and a reminder and early warning module, where:

[0040] The data acquisition and processing module is used to collect the operation parameters, environmental conditions, and historical fault data records of the system equipment, and preprocess the collected data;

[0041] The equipment performance evaluation module is used to establish a health evaluation index by using a comprehensive wind and light energy storage equipment performance model, and determine the health degree of different equipment;

[0042] The fault and anomaly diagnosis module is used to judge the fault and anomaly level by the time and frequency of the fault alarm signals of the system devices;

[0043] The loss and anomaly diagnosis module is used to predict the integrated photovoltaic and wind power by combining the autoregressive integrated moving average model and the long short-term memory model, and judge the loss and anomaly level;

[0044] The reminder and early warning module is used to formulate inspection and daily maintenance work plans by combining the health status of the devices, the fault and anomaly level, and the loss and anomaly level, and issue reminders and early warnings.

[0045] Compared with the prior art, the present invention has the following advantages:

[0046] The intelligent management method and system for building photovoltaic and wind power energy storage provided by the present invention utilize the data acquisition and processing module, the device performance evaluation module, the fault and anomaly diagnosis module, the loss and anomaly diagnosis module, and the reminder and early warning module. By analyzing and diagnosing the key devices and core performance of the system and warning key events, it can reduce the dependence of new energy devices on the professional capabilities of management personnel during their participation in the building power system, reduce the operation and maintenance costs, thus effectively avoiding energy waste and equipment damage caused by improper maintenance, and ensuring the efficient and stable operation of the new energy system for buildings.

[0047] For the above reasons, the present invention can be widely promoted in the fields of new energy power and the like. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is the flow chart of the intelligent management method for building photovoltaic and wind power energy storage in the present invention.

[0050] Figure 2 It is the structure diagram of the intelligent management system for building photovoltaic and wind power energy storage in the present invention. Detailed Embodiments

[0051] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to describe the present invention in detail.

[0052] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part rather than all of the embodiments of the present invention. The following description of at least one exemplary embodiment is actually illustrative only and in no way limits the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0053] It should be noted that the terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the exemplary embodiments of the present invention. As used herein, unless the context clearly dictates otherwise, the singular forms are also intended to include the plural forms. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they specify the presence of the stated features, steps, operations, devices, components, and / or combinations thereof.

[0054] Unless otherwise specifically stated, the relative arrangements of the components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be clear that, for the convenience of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships. Technologies, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods and devices should be regarded as part of the authorization specification. In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as limitations. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0055] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the orientation words such as "front, rear, upper, lower, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom", etc. are generally based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description. Without contrary description, these orientation words do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and thus should not be construed as limiting the scope of protection of the present invention. The orientation words "inside, outside" refer to inside and outside the contour of each component itself.

[0056] For ease of description, spatial relative terms such as "above", "over", "on the upper surface", "upper", etc. can be used here to describe the spatial positional relationship of a device or feature shown in the figure with other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation in addition to the orientation described in the figure for the device. For example, if the device in the attached drawing is inverted, the device described as "above other devices or structures" or "over other devices or structures" will then be positioned as "below other devices or structures" or "under other devices or structures". Thus, the exemplary term "above" can include both the orientations of "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and corresponding interpretations are made for the spatial relative descriptions used here.

[0057] In addition, it should be noted that using words such as "first", "second", etc. to limit components is only for the convenience of differentiating the corresponding components. Without additional statements, the above words have no special meanings, so they cannot be understood as limiting the protection scope of the present invention.

[0058] As Figure 1 shown, the present invention provides a method for intelligent management of photovoltaic wind power energy storage for buildings, which is characterized by including:

[0059] Collect the operating parameters, environmental conditions, and historical fault data records of system equipment, and preprocess the collected data;

[0060] In specific implementation, as a preferred implementation manner of the present invention, preprocessing the collected data specifically includes: setting upper and lower limits for various types of data and eliminating communication abnormal data.

[0061] Utilize the comprehensive performance model of wind-solar energy storage equipment to establish health assessment indicators and determine the health status of different equipment;

[0062] In specific implementation, as a preferred implementation manner of the present invention, the health assessment indicators include: equipment standard performance deviation degree, equipment failure rate, and equipment key index over-line rate, where:

[0063] The equipment standard performance deviation degree is determined by comparing the equipment with the theoretical performance under standard working conditions or a benchmark equipment and statistically evaluating the degree to which the deviation of the equipment performance from the theoretical performance or the benchmark equipment performance exceeds the set threshold within the evaluation period;

[0064] The equipment failure rate is determined by obtaining the failure duration of the equipment from the historical fault data records of the equipment and statistically calculating the proportion of the equipment failure duration in the evaluation period within the evaluation period;

[0065] The out-of-limit rate of key device indicators is determined by obtaining the key indicators corresponding to different devices and statistically calculating the proportion of key device indicators exceeding the set threshold within the evaluation period. The final score of device performance evaluation can be obtained by weighted summation and scoring through the expert experience method based on the deviation degree of device standard performance, device failure rate, and out-of-limit rate of key device indicators, so as to determine the health status of different devices.

[0066] An optional statistical method is: statistically calculate the specific number of frames of key indicators within the evaluation period, and calculate the proportion of the number of frames exceeding the set threshold in the total number of frames.

[0067] Judge the abnormal level of faults through the occurrence time and frequency of fault alarm signals of system devices;

[0068] Through the combination of autoregressive integrated moving average model and long short-term memory model, predict the comprehensive photovoltaic and wind power generation, and judge the abnormal level of losses;

[0069] In specific implementation, as a preferred implementation mode of the present invention, through the combination of autoregressive integrated moving average model and long short-term memory model, predict the comprehensive photovoltaic and wind power generation, specifically including:

[0070] Use the autoregressive integrated moving average model to predict the comprehensive photovoltaic and wind power generation:

[0071] Arrange the historical comprehensive photovoltaic and wind power generation sequence according to time as a time series, use ADF test and KPSS test to judge whether the time series is stationary, and use the p-value to evaluate the accuracy of the test results; if the p-value of the ADF test is less than 0.05 or the p-value of the KPSS test is greater than 0.05, it is determined that the time series data is stationary, otherwise perform differencing operations until the time series data is stationary, and determine the differencing coefficient d;

[0072] Use the partial autocorrelation coefficient test to determine the autoregressive order m, use the autocorrelation coefficient ACF test to determine the moving average order q, calculate the AIC value, select the model parameters m and q with the smallest AIC value, and determine the autoregressive integrated moving average model;

[0073] Use the hypothesis test method to evaluate the determined autoregressive integrated moving average model, and test whether the residual sequence of the model is a white noise sequence. If the residual sequence is not a white noise sequence, re-determine the model parameters and the model; use the determined autoregressive integrated moving average model to predict the comprehensive photovoltaic and wind power generation;

[0074] Use the long short-term memory model to predict the comprehensive photovoltaic and wind power generation:

[0075] Collect meteorological data within the evaluation period and perform data standardization processing; use weather type, temperature, wind speed, and humidity parameter information as inputs on a daily basis, and the predicted combined photovoltaic and wind power generation as the output to train a long short-term memory model and save the parameters; input the meteorological data into the trained long short-term memory model for prediction to obtain the predicted combined photovoltaic and wind power generation.

[0076] Combine the prediction results of the autoregressive integrated moving average model and the long short-term memory model to comprehensively predict the combined photovoltaic and wind power generation:

[0077] Obtain the curve of meteorological parameter error over time based on the monthly meteorological forecast score information, and fit the error curves of different meteorological parameters according to the correlation reflected by the correlation coefficient to obtain the initial value of the curve in an approximate exponential form:

[0078] X t =a H ×H t +a T ×T t +a w ×W t

[0079] Where X t is the proportion of the autoregressive integrated moving average model; H t is the relative error value reflected by the humidity score on the t-th day, T t is the relative error value reflected by the temperature score on the t-th day, W t is the relative error value reflected by the wind speed score on the t-th day; a H , a T , a W are the normalization coefficients of the influence of meteorological parameters on power generation.

[0080] Use the optimization rule to substitute historical data for optimization:

[0081]

[0082] 2Y t -X t =1(0≤X t ≤1)

[0083] Where Y t -X t is the proportion of the long short-term memory model; is the predicted value of the autoregressive integrated moving average model on the t-th day, is the predicted value of the long short-term memory model on the t-th day; r t is the actual value of the combined photovoltaic and wind power generation on the r-th day.

[0084] Based on the health condition of the equipment, the fault abnormality level, and the loss abnormality level, formulate inspection and daily maintenance work plans, and issue reminders and warnings.

[0085] When specifically implementing, as a preferred implementation mode of the present invention, based on the health condition of the equipment, the fault abnormality level, and the loss abnormality level, formulate inspection and daily maintenance work plans, specifically including:

[0086] Based on weather data, equipment performance, inspection records, and abnormal events, and in combination with the health condition of the equipment, the fault abnormality level, and the loss abnormality level, formulate inspection and daily maintenance work plans, where:

[0087] According to the weather forecast, remind the management personnel to conduct safety inspections before and after special weather, and set the reminder event level according to the severity of the weather;

[0088] According to the equipment performance, when the equipment performance evaluation score is lower than the health threshold, remind the management personnel to increase the number of inspections, and set the reminder event level according to the deviation value between the current health value and the health threshold;

[0089] According to the inspection records, when the number of days since the last inspection exceeds the inspection cycle threshold, remind the management personnel to conduct inspections in a timely manner;

[0090] According to abnormal events, convert the losses, power usage, and electricity prices already incurred by abnormal equipment and expected to be incurred within the next week into economic loss values, and conduct classified warnings.

[0091] When implementing, for events where the power system is severely damaged, causing risks such as fire to the building body, and the losses already incurred or expected to be incurred exceed the loss threshold, the system issues a first-level warning; for events that do not pose a safety risk but are expected to result in losses not exceeding the loss threshold, the system issues a second-level warning; for events that do not pose a safety risk and do not result in losses, the system issues a third-level warning.

[0092] Corresponding to the building-integrated photovoltaic-wind energy storage intelligent management method in this application, this application also provides a building-integrated photovoltaic-wind energy storage intelligent management system, including: a data acquisition and processing module, an equipment performance evaluation module, a fault abnormality diagnosis module, a loss abnormality diagnosis module, and a reminder and warning module, where:

[0093] The data acquisition and processing module is used to collect the operation parameters, environmental conditions, and historical fault data records of system equipment including photovoltaic, wind power, energy storage, etc., and preprocess the collected data;

[0094] The equipment performance evaluation module is used to establish health evaluation indicators and determine the health condition of different equipment by using an integrated wind-solar-storage equipment performance model;

[0095] In implementation, the devices that can be evaluated by the device performance evaluation module include key system devices such as photovoltaic inverters, wind turbines, and energy storage subsystems. There is no need to separately establish and construct models for evaluation index systems with different energy attributes, and a unified health evaluation index is established.

[0096] The fault and abnormality diagnosis module is used to judge the fault and abnormality level by the time and frequency of the fault alarm signals of the system devices.

[0097] The loss and abnormality diagnosis module is used to combine the autoregressive integrated moving average model and the long short-term memory model to predict the comprehensive power of photovoltaic and wind power, and judge the loss and abnormality level.

[0098] The reminder and early warning module is used to formulate inspection and daily maintenance work plans in combination with the health degree of the device, the fault and abnormality level, and the loss and abnormality level, and issue reminders and early warnings.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent management of photovoltaic and wind power energy storage for buildings, characterized in that: include: Collect the operating parameters, environmental conditions, and historical fault data of system equipment, and pre-process the collected data; Using the comprehensive wind, solar and energy storage equipment performance model, establish health assessment indicators to determine the health level of different equipment; Determine the fault abnormality level through the time and frequency of fault alarm signals from system equipment; By combining the autoregressive difference moving average model with the long short-term memory model, the comprehensive amount of photovoltaic and wind power is predicted to determine the abnormal level of loss; Based on the health of the equipment, abnormal fault level and abnormal loss level, formulate inspection and daily maintenance work plans, and issue reminders and warnings.

2. The intelligent management method for photovoltaic and wind power energy storage for buildings according to claim 1 is characterized in that: The preprocessing of the collected data specifically includes: setting upper and lower limits for various types of data, and eliminating abnormal communication data.

3. The intelligent management method for photovoltaic and wind power energy storage for buildings according to claim 1 is characterized in that: The health assessment indicators include: equipment standard performance deviation, equipment failure rate and equipment key indicator off-line rate, among which: The equipment standard performance deviation is determined by comparing the equipment with the theoretical performance or benchmark equipment under standard working conditions, and statistically determining the degree to which the deviation of the equipment from the theoretical performance or benchmark equipment performance exceeds a set threshold during the evaluation period; The equipment failure rate is determined by obtaining the equipment failure duration through the equipment's historical failure data records and calculating the proportion of the equipment failure duration in the evaluation period to the evaluation period; The device key indicator exceeding the limit rate is determined by obtaining key indicators corresponding to different devices and statistically analyzing the proportion of device key indicators exceeding the set threshold within an evaluation period.

4. The intelligent management method for photovoltaic and wind power energy storage for buildings according to claim 1 is characterized in that: The above method combines the autoregressive difference moving average model with the long short-term memory model to predict the comprehensive amount of photovoltaic and wind power, specifically including: Using the autoregressive difference moving average model to predict the comprehensive power of photovoltaic and wind power: The historical photovoltaic and wind power comprehensive electricity series are arranged into a time series according to time, and the ADF test and KPSS test are used to determine whether the time series is stable, and the p-value is used to evaluate the accuracy of the test results; if the p-value of the ADF test is less than 0.05 or the p-value of the KPSS test is greater than 0.05, the time series data is determined to be stable, otherwise, the difference operation is performed until the time series data is stable, and the difference coefficient d is determined; The partial autocorrelation coefficient test is used to determine the autoregressive order m, the autocorrelation coefficient ACF test is used to determine the moving average order q, and the AIC value is calculated. The model parameters m and q with the smallest AIC value are selected to determine the autoregressive difference moving average model; The determined autoregressive difference moving average model is evaluated by hypothesis testing to test whether the residual sequence of the model is a white noise sequence. If the residual sequence is not a white noise sequence, the model parameters and model are re-determined; the determined autoregressive difference moving average model is used to predict the comprehensive power of photovoltaic and wind power; Using the long short-term memory model to predict the comprehensive power of photovoltaic and wind power: Collect meteorological data within the evaluation period and perform data standardization processing; take weather type, temperature, wind speed, and humidity parameter information as input on a daily basis, take the predicted photovoltaic and wind power comprehensive power as output, train the long-term and short-term memory model and save the parameters; input the meteorological data into the trained long-term and short-term memory model for prediction, and obtain the predicted photovoltaic and wind power comprehensive power; Combining the prediction results of the autoregressive difference moving average model and the long short-term memory model, the comprehensive prediction of photovoltaic and wind power is made: The curve of meteorological parameter error changing with time is obtained according to the monthly meteorological forecast score information. Different meteorological parameter error curves are fitted according to the correlation reflected by the correlation coefficient to obtain the initial value of the curve in approximate exponential form: X t =a H ×H t +a T ×T t +a W ×W t Among them, X t is the proportion of autoregressive difference moving average model; H t is the relative error value reflected by the humidity score on day t, T t is the relative error value reflected by the temperature score on day t, W t is the relative error value reflected by the wind speed score on day t; a H 、a T 、a W is the normalization coefficient of the impact of meteorological parameters on power generation. Use optimization rules to substitute historical data into optimization: 2Y t -X t =1(0≤X t ≤1) Among them, Y t -X t is the proportion of long and short-term memory models; f t ARIMA is the forecast value of the autoregressive difference moving average model on day t, f t LSTM is the measured value of the long short-term memory model on day t; r t It is the actual value of the comprehensive photovoltaic and wind power on the day.

5. The intelligent management method for photovoltaic and wind power energy storage for buildings according to claim 1 is characterized in that: The above mentioned inspection and routine maintenance work plan is formulated based on the health level, fault abnormality level and loss abnormality level of the equipment, including: According to weather data, equipment performance, inspection records and abnormal events, combined with the health of the equipment, abnormal fault level and abnormal loss level, formulate inspection and daily maintenance work plans, including: According to the weather forecast, remind management personnel to conduct safety inspections before and after special weather conditions, and set reminder event levels according to the severity of the weather; According to the equipment performance, when the equipment performance evaluation score is lower than the health threshold, the management personnel are reminded to increase the number of maintenance times, and the reminder event level is set according to the deviation value between the current health value and the health threshold; According to the inspection records, when the number of days from the last inspection exceeds the inspection cycle threshold, the management personnel are reminded to conduct inspections in a timely manner; According to the abnormal events, the losses incurred and expected to be incurred by the abnormal equipment in the next week, the power usage and the electricity price are converted into economic loss values, and graded warnings are issued.

6. A building photovoltaic wind power storage intelligent management system implemented based on the building photovoltaic wind power storage intelligent management method according to any one of claims 1 to 5, characterized in that: include: Data acquisition and processing module, equipment performance evaluation module, fault abnormality diagnosis module, loss abnormality diagnosis module and reminder and early warning module, including: The data acquisition and processing module is used to collect operating parameters, environmental conditions, and historical fault data records of system equipment, and pre-process the collected data; The equipment performance evaluation module is used to establish health evaluation indicators and determine the health level of different equipment using the comprehensive wind-solar-energy storage equipment performance model; The fault abnormality diagnosis module is used to determine the fault abnormality level according to the time and frequency of the fault alarm signal of the system equipment; The loss anomaly diagnosis module is used to predict the comprehensive amount of photovoltaic and wind power and determine the level of loss anomaly by combining the autoregressive difference moving average model and the long short-term memory model; The reminder and warning module is used to formulate inspection and daily maintenance work plans based on the health status, fault abnormality level and loss abnormality level of the equipment, and issue reminders and warnings.

Images