A carbon emission prediction and control method for a hotel central air-conditioning system and related devices

Abstract

The present application discloses a carbon emission prediction and control method for a hotel central air-conditioning system and a related device, which relate to the technical field of carbon emission prediction and control. Based on the hotel occupancy rate and the operating time of a variable frequency water pump per unit time in a historical time period, a simultaneity coefficient is calculated. The hotel occupancy rate, weather data, holiday signs and tourism off-season and peak season signs per unit time in the historical time period are used as input. A trained hotel occupancy rate prediction model is used to determine the hotel occupancy rate per unit time in the prediction time period. Based on the simultaneity coefficient and the hotel occupancy rate per unit time in the prediction time period, the total operating time of the variable frequency water pump in the prediction time period is calculated. Based on the total operating time of the variable frequency water pump in the prediction time period, a control instruction is issued. The control instruction is used to modulate the frequency of the variable frequency water pump to achieve energy saving. The present application can achieve energy saving and emission reduction of the central air-conditioning system.

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission prediction and control, and in particular to a carbon emission prediction and control method and related devices for a hotel central air-conditioning system. Background Art

[0002] With global economic development and population growth, global carbon dioxide emissions are increasing. All sectors of society must strive for energy conservation and emission reduction. The construction industry contributes one-third of total carbon emissions. Taking into account the entire life cycle, the construction industry emits nearly half of all carbon dioxide emissions. Therefore, optimizing the construction industry for energy conservation and emission reduction is essential. With the update of various building energy efficiency standards, the requirements for controlling carbon emissions in the construction industry are becoming increasingly stringent. Central air conditioning systems account for approximately 40%-50% of energy consumption in public buildings, making them the largest energy consumption component. Compared to thermal optimization of building envelopes and lighting systems, optimizing central air conditioning systems offers the greatest potential for building energy optimization. Previous efforts in building energy conservation have focused on energy conservation in buildings, but it is also important to focus on energy conservation in central air conditioning systems, which account for a significant portion of a building's total energy consumption. The largest carbon emission component of central air conditioning systems comes from the electricity consumed during their operation. Therefore, achieving energy conservation and emission reduction in central air conditioning systems is a pressing issue. Summary of the Invention

[0003] The purpose of this application is to provide a carbon emission prediction and control method and related devices for a hotel central air-conditioning system, which can achieve energy conservation and emission reduction of the hotel central air-conditioning system.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a carbon emission prediction and control method for a hotel central air-conditioning system, the carbon emission prediction and control method for a hotel central air-conditioning system comprising:

[0006] Acquire the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air conditioning system, weather data, holiday flag, and tourist off-season and peak-season flag for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed, and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; the tourist off-season and peak-season flag is used to indicate whether the unit time is in the tourist off-season or in the tourist peak-season;

[0007] Based on the hotel occupancy rate and the operating time of the variable frequency water pump for each unit time in the historical time period, a simultaneity coefficient is calculated; the simultaneity coefficient is used to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump;

[0008] The hotel occupancy rate for each unit time in the historical time period, weather data, holiday flags, and tourism off-season flags are used as input, and the trained hotel occupancy rate prediction model is used to determine the hotel occupancy rate for each unit time in the prediction time period;

[0009] Based on the simultaneity coefficient and the hotel occupancy rate per unit time in the forecast time period, the total operating time of the variable frequency water pump in the forecast time period is calculated;

[0010] Based on the total operating time of the variable frequency water pump in the predicted time period, a control instruction is issued; the control instruction is used to adjust the frequency of the variable frequency water pump to achieve energy saving.

[0011] Optionally, a simultaneity coefficient is calculated based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in a historical time period, specifically including:

[0012] Calculate the average hotel occupancy rate for each unit time in the historical time period to obtain the average hotel occupancy rate for the historical time period;

[0013] Calculate the sum of the operating time of the variable frequency water pump per unit time in the historical time period to obtain the total operating time of the variable frequency water pump in the historical time period;

[0014] The simultaneity coefficient is calculated using the hotel's average occupancy rate and the total operating time of the variable frequency water pump in the historical period as input.

[0015] The calculation formula of the simultaneous coefficient is:

[0016]

[0017] Among them, A is the simultaneity coefficient; T1 is the total operating time of the variable frequency water pump in the time period; T is the total duration of the time period; B is the average occupancy rate of the hotel in the time period.

[0018] Optionally, the trained hotel occupancy rate prediction model adopts an improved informer model;

[0019] The informer model includes an encoder, a decoder, and a fully connected layer connected in sequence. The improved informer model is the model obtained by adding a TCN model and a GRU model between the decoder and the fully connected layer of the informer model. The improved informer model includes an encoder, a decoder, a TCN model, a GRU model, and a fully connected layer connected in sequence.

[0020] Optionally, based on the simultaneity coefficient and the hotel occupancy rate per unit time in the forecast time period, the total operating time of the variable frequency water pump in the forecast time period is calculated, specifically including:

[0021] Calculate the average hotel occupancy rate for each unit time in the forecast period to obtain the average hotel occupancy rate for the forecast period;

[0022] The total operating time of the variable frequency water pump in the forecast period is calculated using the simultaneous coefficient and the average hotel occupancy rate in the forecast period as inputs using the simultaneous coefficient calculation formula;

[0023] The calculation formula of the simultaneous coefficient is:

[0024]

[0025] Among them, A is the simultaneity coefficient; T1 is the total operating time of the variable frequency water pump in the time period; T is the total duration of the time period; B is the average occupancy rate of the hotel in the time period.

[0026] Optionally, the variable frequency water pump is a cooling water pump in a hotel's central air-conditioning system.

[0027] Optionally, the unit time is 1 day.

[0028] In a second aspect, the present application provides a carbon emission prediction and control device for a hotel central air-conditioning system, the carbon emission prediction and control device for the hotel central air-conditioning system comprising:

[0029] A data acquisition module is configured to acquire the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air conditioning system, weather data, a holiday flag, and a tourist off-season or peak season flag for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed, and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; and the tourist off-season or peak season flag is used to indicate whether the unit time is in the tourist off-season or in the tourist peak season;

[0030] A simultaneity coefficient calculation module is configured to calculate a simultaneity coefficient based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in a historical time period; the simultaneity coefficient is configured to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump;

[0031] The occupancy rate prediction module is used to use the hotel occupancy rate, weather data, holiday flags, and tourism off-season flags for each unit time in the historical time period as input, and use the trained hotel occupancy rate prediction model to determine the hotel occupancy rate for each unit time in the prediction time period;

[0032] An operating time calculation module, configured to calculate the total operating time of the variable frequency water pump in the predicted time period based on the simultaneity coefficient and the hotel occupancy rate per unit time in the predicted time period;

[0033] The frequency modulation control module is used to issue a control instruction based on the total operating time of the variable frequency water pump in the predicted time period; the control instruction is used to modulate the frequency of the variable frequency water pump to achieve energy saving.

[0034] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the carbon emission prediction and control method for a hotel central air-conditioning system as described above.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the carbon emission prediction and control method for a hotel central air-conditioning system as described above.

[0036] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the carbon emission prediction and control method for a hotel central air-conditioning system described in any one of the above.

[0037] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0038] The present application provides a carbon emission prediction and control method for a hotel central air-conditioning system and a related device. The method calculates a simultaneity coefficient based on the hotel occupancy rate and the operating time of a variable frequency water pump per unit time in a historical time period. The hotel occupancy rate, weather data, holiday flags, and tourism off-season and peak season flags per unit time in the historical time period are used as input. The trained hotel occupancy rate prediction model is used to determine the hotel occupancy rate per unit time in the prediction time period. The method calculates the total operating time of the variable frequency water pump in the prediction time period based on the simultaneity coefficient and the hotel occupancy rate per unit time in the prediction time period. The method issues a control instruction based on the total operating time of the variable frequency water pump in the prediction time period. The control instruction is used to frequency-regulate the variable frequency water pump to achieve energy saving. The method predicts the hotel occupancy rate and further predicts the total operating time of the variable frequency water pump in combination with the simultaneity coefficient. The method can frequency-regulate the variable frequency water pump of the central air-conditioning system in advance, so that the central air-conditioning system can operate in an energy-saving manner while meeting needs, reduce the power consumed during the operation of the central air-conditioning system, and thereby reduce the carbon emissions generated by the central air-conditioning system, thereby achieving energy saving and emission reduction of the central air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 This is an application environment diagram of a carbon emission prediction and control method for a hotel central air-conditioning system provided in Example 1 of the present application.

[0041] Figure 2 A flow chart of a carbon emission prediction and control method for a hotel central air-conditioning system provided in Example 1 of the present application.

[0042] Figure 3 This is a structural diagram of the hotel central air-conditioning system provided in Example 1 of the present application.

[0043] Figure 4 A detailed flow chart of a carbon emission prediction and control method for a hotel central air-conditioning system provided in Example 1 of the present application.

[0044] Figure 5 This is a schematic diagram of the network structure of the trained hotel occupancy rate prediction model provided in Example 1 of the present application.

[0045] Figure 6 This is a schematic diagram of the functional modules of a carbon emission prediction and control device for a hotel central air-conditioning system provided in Example 2 of the present application.

[0046] Figure 7 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] Example 1

[0049] The carbon emission prediction and control method of the hotel central air-conditioning system provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal communicates with the server via a network. The data storage system can store data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on a cloud or other server. The terminal can send historical data to be processed (i.e., hotel occupancy rates per unit time in a historical time period, operating hours of the variable frequency water pump in the hotel central air conditioning system, weather data, holiday indicators, and tourism off-season and peak season indicators) to the server. After receiving the historical data to be processed, the server calculates a simultaneity coefficient based on the hotel occupancy rates and operating hours of the variable frequency water pump in each unit time in the historical time period. Using the hotel occupancy rates, weather data, holiday indicators, and tourism off-season and peak season indicators in each unit time in the historical time period as input, the server uses a trained hotel occupancy rate prediction model to determine the hotel occupancy rate per unit time in the forecast time period. Based on the simultaneity coefficient and the hotel occupancy rates per unit time in the forecast time period, the server calculates the total operating hours of the variable frequency water pump in the forecast time period. Based on the total operating hours of the variable frequency water pump in the forecast time period, the server issues a control instruction, which is used to adjust the frequency of the variable frequency water pump to achieve energy saving. The server can feed back the obtained control instruction to the terminal.

[0050] In addition, in some embodiments, the carbon emission prediction and control method of the hotel central air-conditioning system can also be implemented independently by a server or a terminal. For example, the terminal can directly process the historical data to be processed, or the server can obtain the historical data to be processed from the data storage system and process the historical data to be processed.

[0051] Terminals include, but are not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices include smart watches, smart bracelets, and head-mounted devices. Servers can be implemented as standalone servers or server clusters consisting of multiple servers, or even cloud servers.

[0052] like Figure 2 As shown, a carbon emission prediction and control method for a hotel central air-conditioning system is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 Taking the server in the example as an example, the carbon emission prediction and control method of the hotel central air-conditioning system includes the following steps:

[0053] Step S1, obtaining the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air-conditioning system, weather data, holiday flag and tourism off-season and peak season flag for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; the tourism off-season and peak season flag is used to indicate whether the unit time is in the tourism off-season or in the tourism peak season.

[0054] Step S2: Calculate a simultaneity coefficient based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in the historical time period; the simultaneity coefficient is used to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump.

[0055] Step S3, taking the hotel occupancy rate, weather data, holiday flags and tourism peak and off-peak season flags of each unit time in the historical time period as input, and using the trained hotel occupancy rate prediction model to determine the hotel occupancy rate of each unit time in the prediction time period.

[0056] Step S4: Based on the simultaneity coefficient and the hotel occupancy rate per unit time in the prediction time period, the total operating time of the variable frequency water pump in the prediction time period is calculated.

[0057] Step S5: issuing a control instruction based on the total operating time of the variable frequency water pump in the predicted time period; the control instruction is used to adjust the frequency of the variable frequency water pump to achieve energy saving.

[0058] By implementing the above-mentioned steps S1 to S5, this embodiment constructs a simultaneous coefficient, first using the trained hotel occupancy rate prediction model to determine the hotel occupancy rate of each unit time in the prediction time period, and then based on the simultaneous coefficient and the hotel occupancy rate of each unit time in the prediction time period, calculate the total operating time of the variable frequency water pump in the prediction time period, and finally based on the total operating time of the variable frequency water pump in the prediction time period, issue a control instruction, and the control instruction is used to frequency-modulate the variable frequency water pump to achieve energy saving. Therefore, by predicting the hotel occupancy rate and further predicting the total operating time of the variable frequency water pump in combination with the simultaneous coefficient, the variable frequency water pump of the central air-conditioning system can be frequency-modulated in advance, so that the central air-conditioning system can operate in an energy-saving manner on the basis of meeting the needs, reduce the power consumption of the central air-conditioning system during operation, and then reduce the carbon emissions generated by the central air-conditioning system, thereby achieving energy saving and emission reduction of the central air-conditioning system.

[0059] Buildings consistently contribute the most to carbon emissions. Among public building energy consumption, central air conditioning systems account for approximately 40%-50%, the largest share of energy consumption. For central air conditioning systems, from a lifecycle perspective, the largest share of carbon emissions occurs during their operation phase. During this phase, the largest share comes from the power consumption of the system's various devices, such as compressors, condensers, and water pumps. In other words, the largest share of carbon emissions in a central air conditioning system comes from the power consumed during the system's operation. Based on this, this embodiment implements advance prediction and control of the power consumption of variable-frequency water pumps in the central air conditioning system to reduce carbon emissions. The cooling water pumps in hotel central air conditioning systems use variable-frequency water pumps. This embodiment correlates the hotel's occupancy rate and the operating time of the variable-frequency water pumps by calculating a simultaneous coefficient. By predicting the hotel occupancy rate, the operating time of the variable-frequency water pumps can be predicted in advance. Frequency modulation control of the variable-frequency water pumps is then implemented based on the operating time, controlling the frequency of the variable-frequency water pumps and reducing their power consumption, thereby achieving energy conservation and emission reduction for the central air conditioning system.

[0060] like Figure 3 As shown, the hotel's central air-conditioning system includes a softener, a make-up water pump, an expansion water tank, a cooling tower, a cooling water pump, a chilled water pump, a manifold, an evaporator of the chiller and a condenser of the chiller. The softener is used to soften hard water, the make-up water pump is used to supply water to the expansion water tank and the cooling tower, the expansion water tank is used to accommodate the expansion of water, and also plays a role in constant pressure and water replenishment. The cooling tower is used to use water as a circulating coolant, absorb heat from a system and discharge it into the atmosphere to reduce the water temperature. The cooling water pump is used to transport water, the chilled water pump is used to transport water, the manifold is used to transport water, the evaporator is used to cool the water, and the condenser is used to heat the water.

[0061] Figure 3In the diagram, the solid line represents the supply water line, and the dashed line represents the return water line. After being softened by the softener, tap water is pumped to the cooling tower and expansion tank via a make-up water pump. The expansion tank then supplies water to the cooling tower. A central air conditioning system consists of two circuits: the chilled water circuit and the cooling water circuit. In the chilled water circuit, the chilled water pump pumps chilled water return (i.e., the return water from the manifold, 12°C) to the chiller's evaporator. Because the evaporator absorbs heat, the heat absorbed by the evaporator lowers the return temperature of the chilled water. Therefore, the chilled water leaving the chiller is at a low temperature (7°C). The typical supply and return water temperature is 7 / 12°C. The lower the temperature, the lower the chiller's efficiency. After leaving the chiller, the chilled water (7°C) passes through the manifold to the indoor air conditioning terminal, providing cooling to the room. Upon exiting the air conditioning terminal, the temperature rises (12°C) and is then pumped by the chilled water pump to the chiller's evaporator, completing the cycle. In the cooling water cycle, the cooling water return water (32°C) coming out of the cooling tower is transported to the condenser of the chiller through the cooling water pump. Because the condenser releases heat, if the heat cannot be removed in time, the condenser will continue to heat up, and finally the equipment will alarm and shut down. Therefore, the temperature of the cooling water return water (32°C) will rise after entering the condenser, so the cooling water coming out of the chiller is high temperature (37°C). After the cooling water returns to the cooling tower to cool down, it is again sent to the chiller through the cooling water pump to form a cycle.

[0062] In this embodiment, the variable frequency water pump is a cooling water pump in the hotel's central air-conditioning system. This embodiment performs carbon emission prediction and control on the hotel's central air-conditioning system. Specifically, the frequency of the variable frequency water pump in the central air-conditioning system is adjusted in advance by predicting the hotel's occupancy rate to control the power consumption of the variable frequency water pump, thereby achieving energy conservation and emission reduction.

[0063] like Figure 4 As shown, the steps of the carbon emission prediction and control method of this embodiment are as follows:

[0064] (1) Collect historical data first. First, determine a specific time period, such as one day, one week, or one month, as the time range for calculation. Record the hotel room occupancy rate data, variable frequency water pump operation data, and weather data within the time period. The occupancy rate refers to the occupancy status of the guest rooms within the time period. The variable frequency water pump operation data can include the operating time, flow rate, power, and other information of the variable frequency water pump. That is, the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel's central air-conditioning system, weather data, a holiday flag, and a tourism off-season or peak season flag are obtained for each unit time in a historical time period. The historical time period refers to the time period before the prediction time. The unit time can be 1 day, and the historical time period can include multiple days. The hotel occupancy rate refers to the ratio of the number of occupied rooms per unit time to the total number of hotel rooms. The operating time of the variable frequency water pump in the hotel's central air-conditioning system refers to the length of time the variable frequency water pump runs per unit time. The weather data includes at least one of temperature, wind speed, and sunshine intensity. The holiday flag is used to indicate whether the unit time is a holiday. As an example, if the date of the unit time is a holiday, the holiday flag can be 1; otherwise, the holiday flag can be 0. The tourism off-season or peak season flag is used to indicate whether the unit time is in the tourism off-season or in the tourism peak season. The off-season date and the tourism peak season date of the hotel's region are determined manually. As an example, if the date of the unit time is in the tourism off-season, the tourism off-season or peak season flag can be 1; if the date of the unit time is in the tourism peak season, the tourism off-season or peak season flag can be 0.

[0065] (2) This embodiment further calculates the simultaneity coefficient, determines that the time period is a historical time period, calculates the sum of the operating time of the variable frequency water pump and the average hotel occupancy rate in the time period, obtains the actual operating time of the water pump (i.e., the total operating time of the variable frequency water pump in the historical time period) and the average hotel occupancy rate, and then calculates the simultaneity coefficient of the operating time of the variable frequency water pump and the hotel occupancy rate. The calculation formula is as follows: simultaneity coefficient = actual operating time of the water pump / (average hotel occupancy rate * time period), where the time period is the total length of the time period. The simultaneity coefficient is calculated based on this calculation formula. According to the calculated simultaneity coefficient, the degree of correlation between the operating time of the variable frequency water pump and the hotel occupancy rate can be evaluated. The required total operating time of the variable frequency water pump can also be inferred from the known simultaneity coefficient and the predicted hotel occupancy rate.

[0066] In S2, the simultaneity coefficient is calculated based on the hotel occupancy rate and the operating time of the variable frequency water pump in each unit time in the historical time period, including:

[0067] 1) Calculate the average hotel occupancy rate for each unit time in the historical time period to obtain the average hotel occupancy rate for the historical time period.

[0068] 2) Calculate the sum of the operating time of the variable frequency water pump per unit time in the historical time period to obtain the total operating time of the variable frequency water pump in the historical time period.

[0069] 3) The average occupancy rate of the hotel in the historical time period and the total operating time of the variable frequency water pump in the historical time period are used as input, and the simultaneity coefficient is calculated using the simultaneity coefficient calculation formula.

[0070] At the same time, the coefficient calculation formula is:

[0071]

[0072] Among them, A is the simultaneity coefficient; T1 is the total operating time of the variable frequency water pump in the time period; T is the total duration of the time period; B is the average occupancy rate of the hotel in the time period.

[0073] When calculating the simultaneous coefficient, the time period is the historical time period.

[0074] (3) This embodiment further predicts the occupancy rate by using the informer-TCN (Temporal Convolutional Network)-GRU (Gated Recurrent Unit) model to predict the hotel occupancy rate. Specifically, historical data of hotel occupancy rate and influencing factors (temperature, wind speed, sunshine intensity, holidays, tourist off-season, etc.) are input into the model for prediction.

[0075] The informer model is a prediction model based on probabilistic sparse self-attention, proposed by Zhou Haoyi et al. in 2021. Unlike traditional neural networks, the informer model employs a separate encoder-decoder architecture. During the prediction process, the encoder output is processed by the decoder, resulting in the decoder output, which is then processed by a fully connected layer to produce the prediction result. The informer model offers the following advantages over traditional neural networks: Its use of a sparse self-attention mechanism significantly reduces time complexity and memory usage, and demonstrates comparable performance in sequence dependency comparison. The proposed self-attention extraction operation effectively handles very long input sequences. While conceptually simple, the generative decoder employs a single forward-operation step, rather than a step-by-step approach, significantly improving inference speed for long-term series prediction. For prediction tasks involving multiple influencing factors, capturing the underlying information within feature data is crucial for accurate prediction. While the informer model has been widely used in long-term series prediction, it still suffers from insufficient feature information extraction when processing multidimensional time series data. For multidimensional time series data, causal convolution has greater feature extraction advantages. This embodiment adds causal convolution on the basis of the informer model to enhance the model's ability to extract feature information. Causal convolution can better capture the causal relationship in the data, thereby better understanding the dynamic characteristics of the data. Compared with the original informer model, the model after adding causal convolution can more effectively extract the feature information of multidimensional time series data, and learn the potential connections between the extracted features through the GRU model, thereby improving the model's prediction accuracy.

[0076] like Figure 5 As shown, this embodiment adds a TCN model to the informer model to enhance the model's ability to extract feature information, and adds a GRU model to learn the potential connections between the extracted features, thereby improving the model's prediction accuracy for prediction tasks involving multiple influencing factors. The trained hotel occupancy rate prediction model uses the improved informer model. The informer model includes an encoder, a decoder, and a fully connected layer connected in sequence. The improved informer model is the model obtained by adding a TCN model and a GRU model between the decoder and the fully connected layer of the informer model. The improved informer model includes an encoder, a decoder, a TCN model, a GRU model, and a fully connected layer connected in sequence.

[0077] At this time, the hotel occupancy rate, weather data, holiday signs and tourism peak and off-peak season signs for each unit time in the historical time period are used as input, and the trained hotel occupancy rate prediction model is used to determine the hotel occupancy rate for each unit time in the prediction time period.

[0078] For the decoder in the informer model, the input time series is divided into two parts: the known sequence before the prediction time t and the predicted sequence that needs to mask future data, namely:

[0079]

[0080] in, is the time series input to the decoder; Concat(·) represents the concatenation operation; is a known sequence; is the prediction sequence; L token is the length of the known sequence; L y is the length of the predicted sequence; d model The dimensions of the model.

[0081] The original informer model uses ordinary convolution in the encoder and decoder to reduce the temporal length of the input sequence, while the TCN model added in this embodiment uses causal convolution, which performs causal convolution on the number of features in the model after the decoder. When calculating each output, causal convolution only considers the current and past values ​​in the input sequence, and does not consider future values. This can avoid the model from using future information when predicting, thereby reducing the risk of information leakage. Since causal convolution only considers current and past values, it can avoid operating on future values ​​during calculations, which helps to improve computational efficiency, especially when processing long sequence data, causal convolution can reduce computational costs. Compared with ordinary convolution, causal convolution usually has fewer parameters. This is because in causal convolution, future values ​​do not affect the current output, so more parameters can be shared during calculations, thereby reducing the complexity of the model.

[0082] After further extracting input features using the TCN model, the GRU model learns the underlying connections between the extracted features. The GRU model uses a gating mechanism to address long-term dependencies and can be used for modeling and predicting sequential data. Compared to the LSTM model, the GRU model combines the input gate and forget gate into a single update gate. In addition, it includes a reset gate, which determines the influence of the previous hidden state on the current hidden state, and an update gate, which determines the influence of the current hidden state on the next hidden state. This method effectively preserves long-term dependencies while reducing the number of parameters and improving computational efficiency.

[0083] The informer model has been widely used in long-term time series prediction tasks, but it still suffers from issues such as insufficient feature extraction when processing multidimensional time series data. When faced with prediction tasks involving multiple influencing factors, capturing the potential information in the feature data is crucial for accurate prediction. This example involves predicting hotel room occupancy rates, which are influenced by many factors, such as weather, holidays, and peak and off-season travel. For such prediction tasks involving multiple factors, causal convolution offers a greater advantage in feature extraction. Therefore, this example adds a TCN model to the informer model to enhance the model's feature extraction capabilities. After feature extraction is performed on the input sequence using the original informer model's encoder-decoder, causal convolution is performed before the fully connected layer to reduce the number of input features and their dimensionality. This allows for more efficient feature extraction of multidimensional time series data. The GRU model is then used to learn the potential connections between the extracted features, thereby improving the model's prediction accuracy for prediction tasks involving multiple influencing factors.

[0084] (4) Calculate the average value of the prediction results, infer the actual operating time required by the variable frequency water pump based on the calculated simultaneous coefficient, and further adjust the frequency of the variable frequency water pump. The cold / hot water in the central air conditioning system is transported by the chilled water pump and the cooling water pump to the manifold and then enters the fan coil unit in each room for heat exchange, achieving cooling or heating of the indoor room. In this embodiment, the variable frequency water pump can be adjusted in advance through prediction to adjust the operating speed and reduce the unnecessary high load operation of the variable frequency water pump for a long time, thereby reducing unnecessary energy consumption and the power consumption of the variable frequency water pump, thereby achieving energy saving effects.

[0085] Then, in S4, based on the simultaneity coefficient and the hotel occupancy rate per unit time in the forecast period, the total operating time of the variable frequency water pump in the forecast period is calculated, specifically including:

[0086] 1) Calculate the average hotel occupancy rate for each unit time in the forecast period to obtain the average hotel occupancy rate for the forecast period.

[0087] 2) Using the simultaneity coefficient and the average hotel occupancy rate during the forecast period as input, use the simultaneity coefficient calculation formula to calculate the total operating time of the variable frequency pump during the forecast period. In this case, the time period in the simultaneity coefficient calculation formula is the forecast period.

[0088] This embodiment further issues control instructions based on the total operating time of the variable frequency pump during the predicted time period. These control instructions are used to adjust the frequency of the variable frequency pump to achieve energy savings. The variable frequency pump has a built-in inverter equipped with a control panel, on which the operating time and frequency can be set directly. The specific frequency adjustment steps are as follows: access the inverter's settings menu through the control panel, find the parameters related to the operating time, enter the desired operating time (i.e., the total operating time of the variable frequency pump), confirm and save the settings, and ensure that the inverter operates according to the new operating time, thereby completing the frequency adjustment control.

[0089] This embodiment uses the carbon emission coefficient method to calculate the carbon emissions of the entire central air-conditioning system. The formula is as follows:

[0090]

[0091] Where E is the carbon emission of the central air-conditioning system during operation; n is the total amount of energy; C j is the consumption of the jth energy; α j is the net calorific value of the jth energy; F j is the CO2 emission factor per unit calorific value of the jth energy; α je is the carbon oxidation rate of the jth energy; C e F is the power consumption of the central air-conditioning system when it is running; e is the average CO2 emission factor of the regional power grid.

[0092] The above formula is used to calculate the carbon emissions of the central air-conditioning system before and after the carbon emission prediction and control method of this embodiment is adopted. The results show that the carbon emission prediction and control method of this embodiment can achieve good energy-saving and emission reduction effects.

[0093] This embodiment mainly focuses on the carbon emission prediction and control of the hotel central air-conditioning system. A carbon emission prediction and control method for the hotel central air-conditioning system based on the informer-TCN-GRU model is designed. The hotel occupancy rate is associated with the operating time of the variable frequency water pump in the central air-conditioning system. The frequency of the variable frequency water pump is controlled in advance by predicting the hotel occupancy rate. The power consumption of the variable frequency water pump is reduced by frequency modulation of the variable frequency water pump in the central air-conditioning system, thereby achieving carbon emission reduction of the hotel central air-conditioning system and realizing energy conservation and emission reduction.

[0094] The embodiment of the present application also provides an application scenario, which applies the above-mentioned carbon emission prediction and control method of the hotel central air-conditioning system. Specifically, the carbon emission prediction and control method of the hotel central air-conditioning system provided by this embodiment can be applied in the hotel central air-conditioning system control scenario. The hotel central air-conditioning system control scenario includes a data acquisition link, a data processing link and a frequency modulation control link. The data acquisition link is used to acquire historical data, and the data processing link is used to process the historical data, predict the hotel occupancy rate of each unit time in the prediction time period, and further combine the simultaneity coefficient to determine the total operating time of the variable frequency water pump in the prediction time period, output the control instruction, and the frequency modulation control link is used to modulate the frequency of the variable frequency water pump in the central air-conditioning system based on the control instruction to achieve energy saving. The carbon emission prediction and control method of the hotel central air-conditioning system provided by this embodiment belongs to the data processing link.

[0095] Example 2

[0096] Based on the same inventive concept, the present application also provides a carbon emission prediction and control device for a hotel central air conditioning system, which is used to implement the aforementioned carbon emission prediction and control method for a hotel central air conditioning system. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the embodiment of the carbon emission prediction and control device for a hotel central air conditioning system provided below can be found in the above-mentioned limitations of the carbon emission prediction and control method for a hotel central air conditioning system, and will not be repeated here.

[0097] like Figure 6 As shown, a carbon emission prediction and control device for a hotel central air-conditioning system is provided, and the carbon emission prediction and control device for the hotel central air-conditioning system includes:

[0098] The data acquisition module M1 is used to obtain the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air-conditioning system, weather data, holiday flags and tourist off-season and peak-season flags for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; the tourist off-season and peak-season flag is used to indicate whether the unit time is in the tourist off-season or in the tourist peak season.

[0099] The simultaneity coefficient calculation module M2 is used to calculate the simultaneity coefficient based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in the historical time period; the simultaneity coefficient is used to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump.

[0100] The occupancy rate prediction module M3 is used to take the hotel occupancy rate, weather data, holiday flags and tourism peak and off-peak season flags of each unit time in the historical time period as input, and use the trained hotel occupancy rate prediction model to determine the hotel occupancy rate of each unit time in the prediction time period.

[0101] The operation time calculation module M4 is used to calculate the total operation time of the variable frequency water pump in the prediction time period based on the simultaneity coefficient and the hotel occupancy rate of each unit time in the prediction time period.

[0102] The frequency modulation control module M5 is used to issue a control instruction based on the total operating time of the variable frequency water pump in the predicted time period; the control instruction is used to modulate the frequency of the variable frequency water pump to achieve energy saving.

[0103] Example 3

[0104] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data to be processed. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a carbon emission prediction and control method for a hotel central air-conditioning system is implemented.

[0105] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0106] In an exemplary embodiment, a computer device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the carbon emission prediction and control method for the hotel central air-conditioning system described in Example 1.

[0107] Example 4

[0108] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the carbon emission prediction and control method for the hotel central air-conditioning system described in Example 1 is implemented.

[0109] Example 5

[0110] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the carbon emission prediction and control method for the hotel central air-conditioning system described in Example 1.

[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0112] Any reference to memory used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0113] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A carbon emission prediction and control method for a hotel central air-conditioning system, characterized in that: The carbon emission prediction and control method of the hotel central air-conditioning system includes: Acquire the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air conditioning system, weather data, holiday flag, and tourist off-season and peak-season flag for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed, and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; the tourist off-season and peak-season flag is used to indicate whether the unit time is in the tourist off-season or in the tourist peak-season; Based on the hotel occupancy rate and the operating time of the variable frequency water pump for each unit time in the historical time period, a simultaneity coefficient is calculated; the simultaneity coefficient is used to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump; The hotel occupancy rate for each unit time in the historical time period, weather data, holiday flags, and tourism off-season flags are used as input, and the trained hotel occupancy rate prediction model is used to determine the hotel occupancy rate for each unit time in the prediction time period; Based on the simultaneity coefficient and the hotel occupancy rate per unit time in the forecast time period, the total operating time of the variable frequency water pump in the forecast time period is calculated; Based on the total operating time of the variable frequency water pump in the predicted time period, a control instruction is issued; the control instruction is used to adjust the frequency of the variable frequency water pump to achieve energy saving.

2. The carbon emission prediction and control method for a hotel central air-conditioning system according to claim 1, characterized in that: Based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in the historical time period, the simultaneity coefficient is calculated, including: Calculate the average hotel occupancy rate for each unit time in the historical time period to obtain the average hotel occupancy rate for the historical time period; Calculate the sum of the operating time of the variable frequency water pump per unit time in the historical time period to obtain the total operating time of the variable frequency water pump in the historical time period; The simultaneity coefficient is calculated using the hotel's average occupancy rate and the total operating time of the variable frequency water pump in the historical period as input. The calculation formula of the simultaneous coefficient is: Among them, A is the simultaneity coefficient; T1 is the total operating time of the variable frequency water pump in the time period; T is the total duration of the time period; B is the average occupancy rate of the hotel in the time period.

3. The carbon emission prediction and control method for a hotel central air-conditioning system according to claim 1, characterized in that: The trained hotel occupancy rate prediction model adopts the improved informer model; The informer model includes an encoder, a decoder, and a fully connected layer connected in sequence. The improved informer model is the model obtained by adding a TCN model and a GRU model between the decoder and the fully connected layer of the informer model. The improved informer model includes an encoder, a decoder, a TCN model, a GRU model, and a fully connected layer connected in sequence.

4. The carbon emission prediction and control method for a hotel central air-conditioning system according to claim 1, characterized in that: Based on the simultaneity coefficient and the hotel occupancy rate per unit time in the forecast time period, the total operating time of the variable frequency water pump in the forecast time period is calculated, specifically including: Calculate the average hotel occupancy rate for each unit time in the forecast period to obtain the average hotel occupancy rate for the forecast period; The total operating time of the variable frequency water pump in the forecast period is calculated using the simultaneous coefficient and the average hotel occupancy rate in the forecast period as inputs using the simultaneous coefficient calculation formula; The calculation formula of the simultaneous coefficient is: Among them, A is the simultaneity coefficient; T1 is the total operating time of the variable frequency water pump in the time period; T is the total duration of the time period; B is the average occupancy rate of the hotel in the time period.

5. The carbon emission prediction and control method for a hotel central air-conditioning system according to claim 1, characterized in that: The variable frequency water pump is a cooling water pump in the hotel's central air-conditioning system.

6. The carbon emission prediction and control method for a hotel central air-conditioning system according to claim 1, characterized in that: The unit time is 1 day.

7. A carbon emission prediction and control device for a hotel central air-conditioning system, characterized in that: The carbon emission prediction control device of the hotel central air-conditioning system includes: A data acquisition module is configured to acquire the hotel occupancy rate, the operating time of the variable frequency water pump in the hotel central air conditioning system, weather data, a holiday flag, and a tourist off-season or peak season flag for each unit time in a historical time period; the weather data includes at least one of temperature, wind speed, and sunshine intensity; the holiday flag is used to indicate whether the unit time is a holiday; and the tourist off-season or peak season flag is used to indicate whether the unit time is in the tourist off-season or in the tourist peak season; A simultaneity coefficient calculation module is configured to calculate a simultaneity coefficient based on the hotel occupancy rate and the operating time of the variable frequency water pump per unit time in a historical time period; the simultaneity coefficient is configured to characterize the correlation between the hotel occupancy rate and the operating time of the variable frequency water pump; The occupancy rate prediction module is used to use the hotel occupancy rate, weather data, holiday flags, and tourism off-season flags for each unit time in the historical time period as input, and use the trained hotel occupancy rate prediction model to determine the hotel occupancy rate for each unit time in the prediction time period; An operating time calculation module, configured to calculate the total operating time of the variable frequency water pump in the predicted time period based on the simultaneity coefficient and the hotel occupancy rate per unit time in the predicted time period; The frequency modulation control module is used to issue a control instruction based on the total operating time of the variable frequency water pump in the predicted time period; the control instruction is used to modulate the frequency of the variable frequency water pump to achieve energy saving.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the carbon emission prediction and control method for a hotel central air-conditioning system according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the carbon emission prediction and control method for a hotel central air-conditioning system according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the carbon emission prediction and control method for a hotel central air-conditioning system according to any one of claims 1 to 6 is implemented.

Images