Heat exchange station load prediction analysis system based on deep learning

Abstract

The invention belongs to the technical field of load prediction, and particularly discloses a heat exchange station load prediction analysis system based on deep learning. Comprising an indoor temperature calling module, a temperature setting information extraction module, a synchronous indoor temperature extraction module, a set temperature tendency association module, a set time tendency association module, a heating load information calling module, a heating temperature difference tendency association module and a heating load prediction module. According to the method, the indoor temperature data of the user is acquired, the set time is extracted, the preference set time of the user is identified, and the indoor temperature data of the preference set time is further acquired, so that the optimization of the temperature object and the selection range in the meteorological factors influencing the load prediction is realized, and the load prediction on the basis is more reasonable and accurate; and meanwhile, the problems that a large amount of meteorological data occupies storage space and the prediction efficiency is reduced are avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of load forecasting, and specifically discloses a heat exchange station load forecasting and analysis system based on deep learning. Background Art

[0002] A heat exchange station is a facility used to convert high-temperature hot water or steam generated by a heat source (such as a boiler, thermal power plant, etc.) into low-temperature hot water suitable for heating a building. It transfers heat to the building's heating system through a heat exchanger, thereby achieving efficient transmission and distribution of heat. In the process of heating a building, a heat exchange station will generate a heating load, that is, the total amount of heat provided to the building within a certain period of time. Accurately predicting the heating load of the heat exchange station can dynamically adjust the operating parameters of the heat exchange station, reduce energy waste, and improve the energy efficiency of the system and the comfort of users.

[0003] The prior art publication number CN114118862A discloses a method and system for predicting and regulating the dynamic heat load of a heat exchange station. The method obtains meteorological data and operation data of the heat exchange station in the area to be processed, wherein the meteorological data includes outdoor temperature, outdoor humidity, wind speed, etc., and the operation data of the heat exchange station includes operation time, operation target temperature, etc., and constructs and divides the meteorological data set after preprocessing, and then constructs a dynamic heat load prediction model for the heat exchange station. The prediction model is then trained using the constructed data set, and the model operation effect is evaluated and feedback is adjusted on the operation status of the heat exchange station to achieve a dynamic balance between the supply and demand of heat. This scheme lacks effective temporal screening of meteorological data when obtaining meteorological data. The essence of the heat exchange station's heating of a building is to heat the users in the building, and the users' activities in the building are not all-weather, so not all meteorological data in all time periods are necessary. In this case, using meteorological data at all times without screening may introduce noise into the irrelevant meteorological data, making the temporal pattern of user activities mismatched with the temporal resolution of meteorological data, affecting the accuracy of prediction. On the other hand, a large amount of meteorological data will take up more storage space, increase the cost of data management and storage, and easily increase the burden of data processing and analysis, affecting the prediction efficiency.

[0004] In addition, when heating a building, the indoor temperature is actually raised to the target temperature, rather than the outdoor temperature. There is a certain gap between the indoor temperature and the outdoor temperature, which is affected by the thermal insulation effect of the building. Generally speaking, the worse the thermal insulation effect of the building, the closer the indoor temperature is to the outdoor temperature. Therefore, the above scheme relies on outdoor temperature for load forecasting, which has certain limitations and affects the accuracy of the forecast results. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a heat exchange station load forecasting and analysis system based on deep learning. Since temperature is the most important meteorological factor affecting the load, the temperature object and selection range are optimized during the heat exchange station load forecasting process, which effectively improves the accuracy and rationality of the load forecast.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A heat exchange station load prediction and analysis system based on deep learning, including: an indoor temperature retrieval module, which is used to extract the real-time collected indoor temperature from the building temperature control center during the heating period to generate an indoor temperature time series.

[0007] The temperature setting information extraction module is used to retrieve the user's temperature setting records from the building temperature control center during the heating period, and extract the setting time, setting duration and setting temperature therefrom.

[0008] The synchronous indoor temperature extraction module is used to extract the indoor temperature corresponding to the set time from the indoor temperature time series based on the set time as the synchronous indoor temperature.

[0009] The set temperature tendency association module is used to map the user's temperature setting records with the synchronized indoor temperature, generate an indoor temperature classification set by classifying the temperature setting records corresponding to the same synchronized indoor temperature, and then analyze the tendency association between the indoor temperature and the set temperature based on this.

[0010] The setting time tendency association module is used to classify the retrieved temperature setting records according to the same setting time to generate a setting time classification set, and analyze the preferred setting time and the tendency association between the preferred setting time and the setting duration.

[0011] The heating load information retrieval module is used to retrieve the heating operation records involved in the temperature setting records from the heating control center of the heat exchange station, and extract the unit heating load therefrom.

[0012] The heating temperature difference tendency correlation module is used to calculate the heating temperature difference using the retrieved temperature setting records, and then analyze the tendency correlation between the heating temperature difference and the unit heating load.

[0013] The heating load prediction module is used to predict the heating load by comprehensively considering the tendency correlation between the indoor temperature and the set temperature, the preferred setting time and the tendency correlation between the preferred setting time and the set duration, and the tendency correlation between the heating temperature difference and the unit heating load.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present invention retrieves the user's temperature setting records during the heating period, extracts the setting time therefrom to identify the user's preferred setting time, and further retrieves the indoor temperature data of these preferred setting times, thereby optimizing the temperature objects and selection ranges in the meteorological factors that affect load forecasting. The load forecasting performed on this basis can focus on the meteorological data during the user's activity period to ensure that the heating demand within these time periods is met, making the forecast results more reasonable and accurate, while avoiding the problem of a large amount of meteorological data occupying storage space and reducing forecasting efficiency.

[0015] 2. When performing load forecasting, the present invention takes into account that the target temperature may not be fixed, that is, the user's required target temperature varies at different indoor temperatures and has a certain correlation with the indoor temperature. For this reason, the tendency correlation analysis between the indoor temperature and the set temperature is performed by retrieving the user's temperature setting record and its corresponding indoor temperature, so that the tendency target temperature can be obtained for the current indoor temperature during load forecasting, thereby performing more accurate and targeted load forecasting, making the load forecast closer to the user's actual needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 It is a schematic diagram of the connection of each module of the system of the present invention.

[0018] Figure 2 This is a schematic diagram of the storage of indoor temperature and temperature setting records by the building temperature control center in the present invention.

[0019] Figure 3 It is a flow chart of the trend correlation analysis between the indoor temperature and the set temperature in the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] Reference Figure 1As shown, a heat exchange station load prediction and analysis system based on deep learning includes an indoor temperature retrieval module, a temperature setting information extraction module, a synchronous indoor temperature extraction module, a setting temperature tendency association module, a setting time tendency association module, a heating load information retrieval module, a heating temperature difference tendency association module and a heating load prediction module.

[0022] The indoor temperature retrieval module and the temperature setting information extraction module mentioned above are both connected to the synchronous indoor temperature extraction module, the temperature setting information extraction module and the synchronous indoor temperature extraction module are both connected to the set temperature tendency association module, the temperature setting information extraction module is connected to the set time tendency association module, the temperature setting information extraction module is connected to the heating load information retrieval module, the temperature setting information extraction module and the heating load information retrieval module are both connected to the heating temperature difference tendency association module, the set temperature tendency association module, the set time tendency association module and the heating temperature difference tendency association module are all connected to the heating load prediction module.

[0023] The indoor temperature acquisition module is used to extract the indoor temperature collected in real time from the building temperature control center during the heating period to generate an indoor temperature time series.

[0024] It should be added that, since the heating of buildings by the heat exchange station is limited to winter, rather than throughout the year, there is a specific heating period, namely the winter duration period. Due to the different climate types in different regions, the winter duration period in each region also varies. For example, for subtropical monsoon climate areas, the winter duration period is usually from December to February of the following year. In addition, more indoor temperature data is provided for load forecasting. The heating period mentioned above is not limited to the heating period of the current year, and the heating period data of several years away from the current year can be selected. Doing so can increase the diversity and representativeness of the data, thereby improving the accuracy and reliability of load forecasting.

[0025] It should be further added that the indoor temperature is collected by using the smart thermostat in the building temperature control center. This is because the smart thermostat is equipped with a temperature sensor, which collects and records temperature data at a high frequency (such as every minute) to ensure the integrity and accuracy of the data. The smart thermostat is equipped with a storage unit, and the indoor temperature collected by the temperature sensor can be stored locally in the storage unit in the form of collection time + indoor temperature, which is convenient for retrieval.

[0026] The temperature setting information extraction module is used to retrieve the user's temperature setting record from the building temperature control center during the heating period, and extract the setting time, setting duration and setting temperature therefrom.

[0027] It should be added that see Figure 2As shown, the smart thermostat in the building temperature control center is usually equipped with a touch screen or physical buttons. Users can set the temperature through these interfaces, and the temperature setting records are stored locally. In addition, when local storage is limited, the smart thermostat can transmit data to the cloud server through 4G / 5G mobile communication, Wi-Fi, Bluetooth and other wireless communication technologies. The cloud server stores a large amount of temperature setting history data and indoor temperature data, which not only ensures the security and integrity of the data, but also provides the convenience of remote management and analysis.

[0028] The synchronous indoor temperature extraction module is used to extract the indoor temperature corresponding to the temperature setting time from the indoor temperature time series data based on the setting time as the synchronous indoor temperature.

[0029] The present invention matches the set time in the temperature setting record with the indoor temperature collection time to select the indoor temperature that meets the set time collection, so as to synchronize the timestamps of the temperature setting record and the indoor temperature record to ensure that the two correspond in time.

[0030] It should be explained that the set time in the temperature setting record reflects the user's heating demand time in the building. Since the user will only have a heating demand after entering the building, the set time in the temperature setting record is used to filter out the indoor temperature data synchronized with the corresponding time. This can accurately reflect the indoor temperature at the heating demand time, and ensure that the load forecast uses the indoor temperature data at the user's heating demand time through time synchronization screening, avoid using data during non-demand time, reduce noise and interference, and improve the accuracy of the forecast.

[0031] See also Figure 3 As shown, the set temperature tendency association module is used to map the user's temperature setting records with the synchronized indoor temperature, and to generate an indoor temperature classification set by classifying the temperature setting records corresponding to the same synchronized indoor temperature, wherein the indoor temperature classification set is a set of temperature setting records corresponding to each indoor temperature, and then analyze the tendency association between the indoor temperature and the set temperature based on this. The specific analysis is as follows: extract the set temperature from each temperature setting record contained in the indoor temperature classification set.

[0032] Compare several set temperatures corresponding to the same indoor temperature to identify whether there is a mode. If there is a mode, the mode is used as the tendency set temperature corresponding to the corresponding indoor temperature. If there is no mode, the range of several set temperatures corresponding to the same indoor temperature is calculated and compared with the configured allowable range. For example, the allowable range is 0.1°C. If the calculated range is less than or equal to the allowable range, the average of several set temperatures corresponding to the same indoor temperature is taken as the tendency set temperature corresponding to the corresponding indoor temperature. Otherwise, the maximum value of several set temperatures corresponding to the same indoor temperature is taken as the tendency set temperature corresponding to the corresponding indoor temperature.

[0033] It should be pointed out that after synchronizing the temperature setting record with the indoor temperature, considering that in some cases, the same indoor temperature may correspond to multiple different temperature setting records, that is, the same indoor temperature corresponds to multiple set temperatures. This one-to-many relationship will lead to data redundancy and affect the accuracy and efficiency of load forecasting. Through tendency analysis, the most representative set temperature can be identified and selected, reducing data redundancy and improving data simplicity and representativeness.

[0034] It should be explained that the mode is the value with the highest frequency, which can reflect the user's preference setting at a specific indoor temperature. If there is a mode, it means that the user has a clear preference setting at this indoor temperature, so it is reasonable to choose the mode as the preferred setting temperature. Of course, if there are multiple modes, the preferred setting temperature corresponding to the largest mode is taken. When there is no mode, the range of several set temperatures corresponding to the same indoor temperature is calculated. The range is the difference between the maximum and minimum values, which reflects the degree of data dispersion. By comparing the range with the allowable range, it can be judged whether the fluctuation range of the data is within the acceptable range. When the range is less than or equal to the allowable range, it means that the data fluctuation is small, and the user's set temperature at this indoor temperature is relatively consistent. At this time, it is reasonable to take the mean as the preferred setting temperature, because the mean can represent the user's setting preference. When the range is greater than the allowable range, it means that the data fluctuation is large, and the user's set temperature at this indoor temperature is very different. At this time, taking the maximum value as the preferred setting temperature may increase energy consumption, but it is necessary to ensure user comfort in extreme cases.

[0035] A coordinate system is constructed with the indoor temperature as the horizontal axis and the tendency setting temperature as the vertical axis, thereby marking several points in the constructed coordinate system for the tendency setting temperature corresponding to the indoor temperature to form a tendency correlation curve between the indoor temperature and the setting temperature.

[0036] The setting time tendency association module is used to classify the retrieved temperature setting records according to the same setting time to generate a setting time classification set, and analyze the preferred setting time and the tendency association between the preferred setting time and the setting duration.

[0037] It should be emphasized that the set time in the temperature setting record reflects the user's heating demand time in the building. These demand times may have certain periodic preferences, that is, the user's heating demand is more concentrated in a specific time period. For example, the user works outside during the day and prefers to enter the building at 6 pm after get off work. Therefore, 6 pm can be regarded as the user's preferred setting time, so that load forecasting at this time point can more accurately reflect the user's actual heating demand and improve the accuracy and reliability of the forecast. In addition, if load forecasting is performed for each set time in the temperature setting record, on the one hand, it will lead to complicated data and reduce the forecast efficiency; on the other hand, when the frequency of occurrence of a certain set time is extremely low, load forecasting for it may lead to invalid forecasting. Therefore, it is necessary to perform preference screening on the set time, and use the screened preferred set time as the key forecast object to improve the pertinence and accuracy of the forecast.

[0038] Preferably, the preferred temperature setting time is analyzed as follows: the occurrence frequency of the same setting time is summarized, and then the distribution uniformity of the occurrence frequency of each setting time is identified. If the distribution is not uniform, the setting time corresponding to the highest occurrence frequency is taken as the preferred setting time, otherwise all setting times are taken as the preferred setting time.

[0039] In the above preferred implementation, the uniformity of distribution can be identified by using a chi-square test. Specifically, the null hypothesis and the alternative hypothesis are firstly performed, and then the total frequency of occurrence of the set time is calculated, and the expected frequency is obtained by dividing it by the number of set times. Then, the chi-square statistic is calculated using the expected frequency. The chi-square statistic calculation formula is: Where O i represents the occurrence frequency of the i-th setting time, i represents the setting time number, and E represents the expected frequency. For example, the null hypothesis is that the occurrence frequency of each setting time is evenly distributed, and the alternative hypothesis is that the occurrence frequency of each setting time is unevenly distributed. At this time, the setting times in the temperature setting record are 18:00, 19:00, 18:30, 20:00, 18:00, 18:00, 19:00, 18:00, 18:30, 19:00, 18:00, 18:00, 18:30, 19:00, 18:00, 18:00, among which 18:00 appears 6 times, 19:00 appears 3 times, 18:30 appears 2 times, and 20:00 appears 1 time. The total occurrence frequency of the setting time is 12 times, and the number of setting times is 4. In this example, the expected frequency is The chi-square statistic is Then compare the calculated chi-square statistic with the critical value. If the chi-square statistic is greater than the critical value, reject the null hypothesis and consider that the frequency distribution is not uniform. If the chi-square statistic is less than or equal to the critical value, fail to reject the null hypothesis and consider that the frequency distribution is uniform. The critical value can be obtained by looking up the table. For example, the critical value with 23 degrees of freedom and a significance level of 0.05 is 35.17.

[0040] The present invention uses the chi-square test to identify whether the frequency of occurrence of each set time is evenly distributed, which can provide a statistically significant indicator and quantify the distribution characteristics of the data. This method is not only applicable to various types of classified data, but also the results are intuitive and easy to understand, which helps to simplify data processing.

[0041] It should be understood that when the recognition distribution is uneven, it means that the occurrence frequencies of various setting times vary greatly. At this time, the setting time with the highest occurrence frequency reflects the setting time selected by the user in most cases, which is usually the setting time that the user is most accustomed to. Therefore, selecting the setting time with the highest frequency can ensure that the setting time is highly representative. When the recognition distribution is uniform, it means that the occurrence frequencies of various setting times are relatively close, and there is no separate representative setting time. At this time, all setting times are regarded as preferred setting times.

[0042] Further preferably, the tendency association between the preferred setting time and the setting duration refers to the following analysis process: selecting a preferred setting time classification set from the setting time classification set, and extracting the setting duration from each temperature setting record included in the preferred setting time classification set.

[0043] The preferred setting time is classified and the setting time of each temperature setting record is concentrated. Similarly, the tendency setting time corresponding to the preferred setting time is obtained according to the analysis method of the indoor temperature corresponding to the tendency setting temperature.

[0044] It should be understood that the set time in the temperature setting record reflects the user's heating demand time in the building, and the set duration corresponding to the set time reflects the user's heating demand duration within the heating demand time. For example, the user prefers to enter the building at 6 pm and leave the building at 7 am, so the time between 6 pm and 7 am is the user's heating demand duration. By analyzing the user's tendency to set the duration corresponding to the preferred setting time, it can reflect the user's heating demand duration within different heating demand times. The heating demand duration determines the operating time of the heat exchange station. The longer the heat exchange station operates, the greater the impact on the load.

[0045] The heating load information retrieving module is used to retrieve the heating operation records involved in the temperature setting records from the heating control center of the heat exchange station, and extract the unit heating load therefrom.

[0046] It should be pointed out that the heating control center of the heat exchange station is the central control unit responsible for managing and controlling the entire heating system. It can record the heating operation status, including operation time, heating load, etc. when the user sets the temperature to start the heating operation, and generate a heating operation record.

[0047] In the preferred implementation of the above scheme, the heating operation records involved in the temperature setting records are retrieved as follows: the operation time and operation duration are extracted from the heating operation records retrieved from the heating control center of the heat exchanger station, and matched with the set time and set duration in the temperature setting record, thereby selecting the heating operation records with successful matching as the heating operation records involved in the temperature setting record.

[0048] The running time mentioned above refers to the initial running time, and successful matching means that the running time matches the set time and the running duration matches the set duration, wherein matching means that the time is consistent or close.

[0049] It should be noted that by matching the operation time in the heating operation record with the operation duration, the heating operation record associated with the temperature setting record can be screened out. Since the temperature setting record reflects the user's heating demand, screening out the heating operation record associated with the temperature setting record can accurately reflect the heat exchanger operation status of the user under each heating demand, which is conducive to targetedly refining the heat exchanger heating load under each heating demand.

[0050] It should be further explained that the unit heating load mentioned above refers to the heating load within a unit operating time. Specifically, the unit heating load can be obtained by extracting the heating load from the heating operation record and dividing it by the operating time.

[0051] The heating temperature difference tendency association module is used to calculate the heating temperature difference using the retrieved temperature setting records, and then analyze the tendency association between the heating temperature difference and the unit heating load.

[0052] In the manner in which the above scheme can be implemented, the heating temperature difference is calculated as follows: extract the set temperature from the temperature setting record, and subtract it from the synchronized indoor temperature mapped by the corresponding temperature setting record to obtain the heating temperature difference. Generally speaking, the larger the heating temperature difference, the greater the heating load.

[0053] The heating temperature differences of the temperature setting records are classified according to the same heating temperature differences to generate temperature setting record sets corresponding to each heating temperature difference.

[0054] Based on the heating operation records involved in the temperature setting records, the temperature setting record sets corresponding to the respective heating temperature differences are converted into heating operation record sets involved in the respective heating temperature differences.

[0055] The heating operation records involved in each heating temperature difference are concentrated, and the unit heating load of each heating operation record is similarly analyzed according to the indoor temperature corresponding to the tendency set temperature to obtain the tendency unit heating load corresponding to each heating temperature difference.

[0056] A coordinate system is constructed with the heating temperature difference as the horizontal axis and the tendency unit heating load as the vertical axis, thereby marking several points in the constructed coordinate system for the tendency unit heating load corresponding to each heating temperature difference to form a tendency correlation curve between the heating temperature difference and the unit heating load.

[0057] The heating load prediction module is used to predict the heating load by comprehensively considering the tendency correlation between the indoor temperature and the set temperature, the preferred setting time and the tendency correlation between the preferred setting time and the set duration, and the tendency correlation between the heating temperature difference and the unit heating load.

[0058] In a further embodiment of the above scheme, the heating load forecast is implemented as follows: the indoor temperature is collected in real time by the building temperature control center, and the human body sensing terminal is used to sense the human body in real time, and the human body sensing time is compared with the preferred setting time. If the human body sensing time is consistent with the preferred setting time, the preferred setting time corresponding to the preferred setting time is retrieved as the current preferred heating time.

[0059] It should be pointed out that the building human body sensing terminal can use an infrared sensor to detect human activities. When the infrared sensor senses the human body, it can be determined that the user has entered the building.

[0060] The set temperature corresponding to the indoor temperature in the tendency correlation curve of the human body sensing time is captured from the tendency correlation curve of the indoor temperature and the set temperature as the current tendency set temperature;

[0061] The current room temperature is matched with the synchronized indoor temperature mapped by the temperature setting record, and the current tendency setting temperature, the current tendency heating time and the human body sensing time are matched with the set temperature, the set time and the set time in the temperature setting record. If the match is successful, the heating load of the heating operation record involving the successfully matched temperature setting record is used as the predicted current heating load.

[0062] The successful matching mentioned above refers to that the room temperature, set temperature, set time and set duration are all matched successfully, and the heating load mentioned above refers to the total heating load.

[0063] It needs to be explained that, when the current room temperature, the current preferred setting temperature, the current preferred heating time and the human body sensing time all match a certain temperature setting record, it means that the current user's heating demand is highly consistent with a certain heating demand in history. In this case, directly predicting the heating load in the heating operation record involving the matched temperature setting record can improve the prediction accuracy, reduce the calculation complexity and improve the system response speed.

[0064] When the matching fails, it means that the current user's heating demand is not highly consistent with the historical heating demand. At this time, the set temperature corresponding to the indoor temperature at the human body sensing time in the tendency correlation curve of the indoor temperature and the set temperature is captured, and the difference is made with the indoor temperature corresponding to the human body sensing time to obtain the current tendency heating temperature difference.

[0065] The tendency unit heating load corresponding to the current heating temperature difference is captured from the tendency correlation curve between the heating temperature difference and the unit heating load.

[0066] The current heating load is predicted by multiplying the current heating load duration with the heating load corresponding to the current heating temperature difference.

[0067] It is further explained that when the current user's heating demand is not highly consistent with the historical heating demand, the focus is on the heating temperature difference and heating time. The heating temperature difference reflects the gap between the current indoor temperature and the expected temperature, which is an important factor affecting the heating load. The heating time reflects the user's actual demand time in the building, which directly affects the operating load of the heating system. Combining the temperature difference and time, the heating demand can be evaluated more comprehensively. Even if the current user's heating demand is not completely consistent with historical data, by paying attention to the temperature difference and time, the accuracy of the load forecast can be maximized, while avoiding complex mathematical models and algorithms, simplifying the load forecasting process.

[0068] In the innovative implementation of the above scheme, the human body sensing time is compared with the preference setting time. If the human body sensing time does not match the preference setting time, it means that the time when the current user enters the building does not belong to the regular preference time. In this case, the human body sensing time may be higher than the preference setting time or lower than the preference setting time. At this time, the tendency setting time corresponding to each preference setting time is averaged to predict the current tendency heating time. This can provide a relatively stable reference value and avoid prediction deviations caused by individual abnormal data.

[0069] In the above case, the current user heating demand is consistent with the historical heating demand.

[0070] The current heating load is predicted by combining the predicted current heating duration with the current heating temperature difference corresponding to the unit heating load. The heating load is predicted in the same way as the matching failure.

[0071] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A heat exchange station load prediction and analysis system based on deep learning, characterized in that ,include: The indoor temperature acquisition module is used to extract the real-time indoor temperature collected from the building temperature control center during the heating period to generate an indoor temperature time series; The temperature setting information extraction module is used to retrieve the user's temperature setting records from the building temperature control center during the heating period, and extract the setting time, setting duration and setting temperature from them; A synchronous indoor temperature extraction module is used to extract the indoor temperature corresponding to the set time from the indoor temperature time series based on the set time as the synchronous indoor temperature; The set temperature tendency association module is used to map the user's temperature setting record with the synchronized indoor temperature, classify the temperature setting records corresponding to the same synchronized indoor temperature to generate an indoor temperature classification set, and then analyze the tendency association between the indoor temperature and the set temperature based on this; A setting time tendency association module is used to classify the retrieved temperature setting records according to the same setting time to generate a setting time classification set, and analyze the preferred setting time and the tendency association between the preferred setting time and the setting duration; The heating load information retrieval module is used to retrieve the heating operation records involved in the temperature setting records from the heating control center of the heat exchange station, and extract the unit heating load therefrom; The heating temperature difference tendency correlation module is used to calculate the heating temperature difference using the retrieved temperature setting records, and then analyze the tendency correlation between the heating temperature difference and the unit heating load; The heating load prediction module is used to predict the heating load by comprehensively considering the tendency correlation between the indoor temperature and the set temperature, the preferred setting time and the tendency correlation between the preferred setting time and the set duration, and the tendency correlation between the heating temperature difference and the unit heating load.

2. A heat exchange station load prediction and analysis system based on deep learning as claimed in claim 1, characterized in that: The analysis of the trend correlation between the indoor temperature and the set temperature is shown in the following process: Extracting the set temperature from each temperature setting record contained in the indoor temperature classification set; Compare several set temperatures corresponding to the same indoor temperature to identify whether there is a mode. If there is a mode, the mode is used as the tendency set temperature corresponding to the corresponding indoor temperature. If there is no mode, the range of several set temperatures corresponding to the same indoor temperature is calculated and compared with the allowable range of the system configuration. If the calculated range is less than or equal to the allowable range, the average of several set temperatures corresponding to the same indoor temperature is taken as the tendency set temperature corresponding to the corresponding indoor temperature. Otherwise, the maximum value of several set temperatures corresponding to the same indoor temperature is taken as the tendency set temperature corresponding to the corresponding indoor temperature. A coordinate system is constructed with the indoor temperature as the horizontal axis and the tendency setting temperature as the vertical axis, thereby marking several points in the constructed coordinate system for the tendency setting temperature corresponding to the indoor temperature to form a tendency correlation curve between the indoor temperature and the setting temperature.

3. The heat exchange station load prediction and analysis system based on deep learning according to claim 1, characterized in that: The analysis preference setting time is as follows: The occurrence frequencies of the same setting time are summarized, and then the occurrence frequencies of each setting time are identified for distribution uniformity. If the distribution is identified to be uneven, the setting time corresponding to the highest occurrence frequency is taken as the preferred setting time, otherwise all setting times are taken as the preferred setting time.

4. The heat exchange station load prediction and analysis system based on deep learning according to claim 2, characterized in that: The tendency correlation between the preferred setting time and the setting duration is shown in the following analysis process: Selecting a preferred setting time classification set from the setting time classification set, and extracting the setting duration from each temperature setting record included in the preferred setting time classification set; The setting time is classified and the setting time of each temperature setting record is concentrated. Similarly, the tendency setting time corresponding to the preference setting time is obtained according to the analysis method of the indoor temperature corresponding to the tendency setting temperature.

5. The heat exchange station load prediction and analysis system based on deep learning according to claim 1, characterized in that: The heating operation record involved in retrieving the temperature setting record is performed as follows: The operation time and operation duration are extracted from the heating operation records retrieved from the heating control center of the heat exchange station, and matched with the set time and set duration in the temperature setting record, thereby selecting the heating operation records with successful matching as the heating operation records involved in the temperature setting record.

6. The heat exchange station load prediction and analysis system based on deep learning according to claim 1, characterized in that: The calculation of the heating temperature difference using the retrieved temperature setting record is implemented as follows: The set temperature is extracted from the temperature setting record, and the heating temperature difference is obtained by subtracting the set temperature from the synchronous indoor temperature mapped by the corresponding temperature setting record.

7. The heat exchange station load prediction and analysis system based on deep learning according to claim 4, characterized in that: The analysis of the heating temperature difference and the tendency of the unit heating load is as follows: Classify the heating temperature differences of the temperature setting records according to the same heating temperature difference to generate a temperature setting record set corresponding to each heating temperature difference; Based on the heating operation records involved in the temperature setting records, the temperature setting record sets corresponding to the heating temperature differences are converted into heating operation record sets involved in the heating temperature differences; The heating operation records involved in each heating temperature difference are concentrated, and the unit heating load of each heating operation record is similarly analyzed according to the indoor temperature corresponding to the tendency set temperature to obtain the tendency unit heating load corresponding to each heating temperature difference; A coordinate system is constructed with the heating temperature difference as the horizontal axis and the tendency unit heating load as the vertical axis, thereby marking several points in the constructed coordinate system for the tendency unit heating load corresponding to each heating temperature difference to form a tendency correlation curve between the heating temperature difference and the unit heating load.

8. The heat exchange station load prediction and analysis system based on deep learning according to claim 7, characterized in that: The heating load forecasting is implemented as follows: The indoor temperature is collected in real time by the building temperature control center, and the human body sensing terminal is used to sense the human body in real time, and the human body sensing time is compared with the preferred setting time. If the human body sensing time is consistent with the preferred setting time, the preferred setting time corresponding to the preferred setting time is retrieved as the current preferred heating time. The set temperature corresponding to the indoor temperature in the tendency correlation curve of the human body sensing time is captured from the tendency correlation curve of the indoor temperature and the set temperature as the current tendency set temperature; The current room temperature is matched with the synchronized indoor temperature mapped by the temperature setting record, and the current tendency setting temperature, the current tendency heating time and the human body sensing time are matched with the set temperature, the set time and the set time in the temperature setting record. If the match is successful, the heating load of the heating operation record involving the successfully matched temperature setting record is used as the predicted current heating load.

9. A heat exchange station load prediction and analysis system based on deep learning as claimed in claim 8, characterized in that: The heating load forecasting also includes the following process: When the matching fails, the set temperature corresponding to the indoor temperature at the time of human body induction is captured from the trend correlation curve of the indoor temperature and the set temperature, and the difference is made with the indoor temperature corresponding to the time of human body induction to obtain the current trend heating temperature difference; The tendency unit heating load corresponding to the current heating temperature difference is captured from the tendency correlation curve between the heating temperature difference and the unit heating load; The current heating load is predicted by combining the current heating load duration with the unit heating load corresponding to the current heating temperature difference.

10. A heat exchange station load prediction and analysis system based on deep learning according to claim 9, characterized in that: The heating load forecasting further includes the following process: Compare the human body sensing time with the preference setting time. If the human body sensing time does not match the preference setting time, then average the preference setting time corresponding to each preference setting time to obtain the predicted current preference heating time. The current heating load is predicted by combining the predicted current tendency heating time with the tendency unit heating load corresponding to the current tendency heating temperature difference.

Images