User-side energy storage management method and system based on big data

Abstract

The present disclosure relates to the field of electric power technology, and discloses a user-side energy storage management method and system based on big data. The specific scheme is: when receiving a request instruction for reducing the power load from the power grid side, the first energy consumption demand of the air-conditioning group without the ventilation effect of the surrounding environment and the second energy consumption demand of the air-conditioning group under the ventilation effect of the surrounding environment are predicted for each air-conditioning group of each building on the user side. If the second energy consumption demand is less than the first energy consumption demand, and the difference between the two is greater than the power load required to be reduced by the request instruction, the air-conditioning group is controlled to work in the natural ventilation mode to reduce the power load on the user side.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a user-side energy storage management method, system, electronic device and storage medium based on big data. Background Art

[0002] There is a complex relationship between the building orientation and the natural ventilation mode of the building's air conditioning group. Different building orientations will affect the wind speed and wind direction distribution inside the building, which in turn affects the effect of natural ventilation. There is also a contradiction between the operation mode of the air conditioning system inside the building and natural ventilation. The operation of the air conditioning system will change the air flow distribution inside the building and affect the effect of natural ventilation. How to coordinate the air conditioning system with natural ventilation to ensure comfort while maximizing the use of natural wind and reducing the energy consumption of the air conditioning system is a complex technical challenge.

[0003] At the same time, the air conditioning group in the building can be used as a virtual energy storage resource. By coordinating and controlling the operation mode of the air conditioning group and adjusting the operation status of the air conditioning group when responding to grid demand, similar energy storage management functions can also be achieved. However, how to maximize the virtual energy storage potential of the air conditioning group while ensuring the comfort of the building is still a technical problem to be explored. This requires comprehensive consideration of multiple factors such as building orientation, natural ventilation, and air conditioning system operation, and balancing the needs of all aspects to achieve collaborative optimization. Summary of the invention

[0004] The present disclosure provides a user-side energy storage management method, system, electronic device and storage medium based on big data, which can solve at least one of the above problems.

[0005] The present disclosure provides a user-side energy storage management method based on big data, including:

[0006] In response to a request instruction for reducing the power load from the power grid side, an energy consumption demand prediction model is used to process the actual operating status and actual indoor temperature of the air conditioning group of each building on the user side, and first predicted energy consumption demand of the air conditioning group of each building is predicted respectively;

[0007] Using a ventilation effect prediction module, the wind speed and direction data of the environment where each of the buildings is located, as well as the orientation information of each of the buildings are processed to respectively predict the predicted ventilation effects of the environment where each of the buildings is located;

[0008] Based on the predicted ventilation effect of the environment to which each of the buildings belongs, respectively simulating the actual operating state and actual indoor temperature of the air conditioning group of each of the buildings, to obtain the predicted operating state and predicted indoor temperature of the air conditioning group of each of the buildings under the predicted ventilation effect;

[0009] The energy consumption demand prediction model is used to process the predicted operating state and predicted indoor temperature of each of the buildings under the predicted ventilation effect, and the second predicted energy consumption demand of the air conditioning group of each of the buildings is predicted respectively;

[0010] For any of the buildings, when the second predicted energy consumption demand of the building is less than the first predicted energy consumption demand of the building, and the difference between the second predicted energy consumption demand of the building and the first predicted energy consumption demand of the building is greater than the amount of power load reduction required by the request instruction, a natural ventilation instruction is issued to the air-conditioning group of the building to control each air-conditioner in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side.

[0011] According to another aspect of the present disclosure, a user-side energy storage management system based on big data is provided, comprising:

[0012] A first prediction module is used to respond to a request instruction for reducing power load from the power grid side, use an energy consumption demand prediction model to process the actual operating status and actual indoor temperature of the air conditioning group of each building on the user side, and respectively predict the first predicted energy consumption demand of the air conditioning group of each building;

[0013] The second prediction module is used to use the ventilation effect prediction module to process the wind speed and direction data of the environment where each of the buildings is located, and the orientation information of each of the buildings, and respectively predict the predicted ventilation effects of the environment where each of the buildings is located;

[0014] A simulation module is used to simulate the actual operation status and actual indoor temperature of the air conditioning group of each building based on the predicted ventilation effect of the environment to which each building belongs, so as to obtain the predicted operation status and predicted indoor temperature of the air conditioning group of each building under the predicted ventilation effect;

[0015] A third prediction module is used to use the energy consumption demand prediction model to process the predicted operating state and predicted indoor temperature of each of the buildings under the predicted ventilation effect, and respectively predict the second predicted energy consumption demand of the air conditioning group of each of the buildings;

[0016] The power load adjustment module is used to send a natural ventilation instruction to the air-conditioning group of any of the buildings, so as to control each air-conditioner in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side, when the second predicted energy consumption demand of the building is less than the first predicted energy consumption demand of the building, and the difference between the second predicted energy consumption demand of the building and the first predicted energy consumption demand of the building is greater than the power load reduction required by the request instruction.

[0017] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any user-side energy storage management method based on big data in the embodiments of the present disclosure.

[0021] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any user-side energy storage management method based on big data in the embodiments of the present disclosure.

[0022] According to the technical solution disclosed in the present invention, in response to a request instruction from the power grid side for reducing the power load, an energy consumption demand prediction model is used to process the actual operating status and actual indoor temperature of the air-conditioning group of each building on the user side, and the first predicted energy consumption demand of the air-conditioning group of each building is predicted. In addition, a ventilation effect prediction module is used to process the wind speed and direction data of the environment where each building is located, as well as the orientation information of each building, and the predicted ventilation effect of the environment where each building is located is predicted; then, based on the predicted ventilation effect of the environment to which each building belongs, the actual operating status and actual indoor temperature of the air-conditioning group of each building are simulated, and the predicted operating status and predicted indoor temperature of the air-conditioning group of each building under the predicted ventilation effect are obtained; thus, the energy consumption demand prediction model is used to process the predicted operating status and predicted indoor temperature of each building under the predicted ventilation effect, and the second predicted energy consumption demand of each building is predicted. Furthermore, for any of the buildings, when the second predicted energy demand of the building is less than the first predicted energy demand of the building, and the difference between the second predicted energy demand of the building and the first predicted energy demand of the building is greater than the amount of power load required to be reduced by the request instruction, a natural ventilation instruction is issued to the air conditioning group of the building to control each air conditioner in the air conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side. In this way, the power load on the user side (virtual energy storage on the user side) can be managed by adopting the embodiment of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a user-side energy storage management method based on big data according to an embodiment of the present disclosure;

[0024] Figure 2 This is a structural block diagram of a user-side energy storage management system based on big data according to an embodiment of the present disclosure;

[0025] Figure 3 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0027] Figure 1It is a flow chart of a user-side energy storage management method based on big data according to an embodiment of the present disclosure.

[0028] like Figure 1 As shown, the method may include:

[0029] S110, in response to a request instruction for reducing power load from the grid side, an energy consumption demand prediction model is used to process the actual operating status and actual indoor temperature of the air conditioning group of each building on the user side, and respectively predict the first predicted energy consumption demand of the air conditioning group of each building;

[0030] S120, using a ventilation effect prediction module to process the wind speed and direction data of the environment where each building is located, as well as the orientation information of each building, and respectively predict the predicted ventilation effect of the environment where each building is located;

[0031] S130, based on the predicted ventilation effect of the environment to which each building belongs, respectively simulate the actual operation state and the actual indoor temperature of the air conditioning group of each building to obtain the predicted operation state and the predicted indoor temperature of the air conditioning group of each building under the predicted ventilation effect;

[0032] S140, using an energy consumption demand prediction model to process the predicted operating state and predicted indoor temperature of each building under the predicted ventilation effect, and respectively predict the second predicted energy consumption demand of the air conditioning group of each building;

[0033] S150: For any building, when the second predicted energy demand of the building is less than the first predicted energy demand of the building, and the difference between the second predicted energy demand of the building and the first predicted energy demand of the building is greater than the amount of power load reduction required by the request instruction, a natural ventilation instruction is sent to the air-conditioning group of the building to control each air-conditioner in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side.

[0034] It can be understood that the request instruction includes the specified time for reducing the power load and the amount of power load to be reduced, etc. For example, these instructions can be stored in a database, including fields such as instruction ID, specified time, load reduction amount, and receiving time.

[0035] It can be understood that the energy consumption demand prediction model and the ventilation effect prediction module are pre-trained neural networks.

[0036] Exemplarily, the energy consumption demand prediction model may adopt a support vector regression algorithm.

[0037] Exemplarily, the actual operating status and actual indoor temperature of the air-conditioning group of the building are input into the energy consumption demand prediction model to obtain a first predicted energy consumption demand of the air-conditioning group of the building output by the energy consumption demand prediction model.

[0038] For example, the actual operation status of the air conditioner group may include the switch status of each air conditioner in the air conditioner group, the air conditioner set temperature, the air conditioner operation mode and the air conditioner wind speed, etc. The actual indoor temperature refers to the temperature of the room where the air conditioner is located.

[0039] For example, the predicted energy consumption requirement or the actual energy consumption requirement of the air conditioner may be the power consumption of the air conditioner.

[0040] Exemplarily, the wind speed and direction data of the environment where the building is located and the orientation information of each building are input into the ventilation effect prediction module, and the ventilation effect prediction module outputs the predicted ventilation effect of the environment where the building is located.

[0041] Exemplarily, the wind speed and direction data may include wind speed levels divided by wind speed levels, and wind direction and wind position divided by azimuth. For example, the wind speed data is divided into three levels of less than 3 m / s, 3-5 m / s, and greater than 5 m / s according to the wind speed. For another example, the wind direction data is divided into eight directions, namely north (337.5°-22.5°), northeast (22.5°-67.5°), east (67.5°-112.5°), southeast (112.5°-157.5°), south (157.5°-202.5°), southwest (202.5°-247.5°), west (247.5°-292.5°), and northwest (292.5°-337.5°).

[0042] For example, the orientation information of the building may be specific longitude and latitude, or may be a pre-divided orientation, for example, north (337.5°-22.5°), northeast (22.5°-67.5°), east (67.5°-112.5°), southeast (112.5°-157.5°), south (157.5°-202.5°), southwest (202.5°-247.5°), west (247.5°-292.5°), northwest (292.5°-337.5°).

[0043] Exemplarily, the predicted operating status and predicted indoor temperature of each building under the predicted ventilation effect are input into the energy demand prediction model to obtain the second predicted energy demand of the building output by the model.

[0044] For example, the natural ventilation instruction may include ventilation time, ventilation mode, ventilation intensity, etc.

[0045] It can be understood that the first predicted energy consumption requirement is the energy consumption requirement of the air conditioning group without the ventilation effect of the surrounding environment. The second predicted energy consumption requirement is the energy consumption requirement of the air conditioning group under the ventilation effect of the surrounding environment.

[0046] According to the above-mentioned embodiment, when a request instruction for reducing the power load is received from the power grid side, the first energy consumption demand of the air-conditioning group without combining the ventilation effect of the surrounding environment and the second energy consumption demand of the air-conditioning group with the ventilation effect of the surrounding environment are predicted for the air-conditioning group of each building on the user side. If the second energy consumption demand is less than the first energy consumption demand, and the difference between the two is greater than the power load reduction required by the request instruction, the air-conditioning group is controlled to operate in natural ventilation mode to reduce the power load on the user side.

[0047] In one embodiment, the above method also includes training and generating an energy consumption demand prediction model, specifically including: obtaining a first training sample set, wherein each training sample in the first training sample set includes an air-conditioning related information sequence of an air-conditioning group sample, the air-conditioning related information sequence includes air-conditioning related information at each historical time point arranged in chronological order, and the air-conditioning related information includes historical operating status, historical indoor temperature and historical energy consumption demand; inputting the historical operating status and historical indoor temperature at each historical time point in the air-conditioning related information sequence into a support vector regression algorithm to obtain a third predicted energy consumption demand at each historical time point output by the support vector regression algorithm; determining a root mean square error based on the third predicted energy consumption demand at each historical time point and the historical energy consumption demand at each historical time point in the air-conditioning related information sequence; when the root mean square error is less than a preset threshold, determining an energy consumption demand prediction model based on the support vector regression algorithm.

[0048] Exemplarily, the historical operating status includes the air conditioner switch status, air conditioner set temperature, air conditioner operating mode and air conditioner wind speed of each air conditioner in the air conditioner group sample.

[0049] Exemplarily, the process of obtaining the first training sample set may be as follows: Using an intelligent sensor network to collect air-conditioning related information of each of the multiple air-conditioning groups. Then, preprocessing the original data includes: using a moving average method to remove abnormal air-conditioning related information from the collected air-conditioning related information, and then using a Z-score method to perform data standardization on the collected air-conditioning related information to obtain a sequence of air-conditioning related information arranged in chronological order. Each sequence corresponds to an air-conditioning group, and each training sample corresponds to an air-conditioning group.

[0050] For example, in an office building, the smart sensor network deploys 100 temperature sensors and 50 current sensors, and collects data every 5 minutes through the ZigBee protocol. At a certain moment, the data collected from air conditioner A is switch state 1 (on), the set temperature is 26°C, the operation mode is cooling, the wind speed gear is medium, the actual indoor temperature is 28°C, and the power is 1500W. In the data preprocessing stage, the moving average method with a 10-minute window is used to process abnormal values. If the power is detected to be 0W instantaneously, it is replaced by the average value of the previous and subsequent data, 1450W. Z-score standardization converts temperature data into a distribution with a mean of 0 and a standard deviation of 1.

[0051] Exemplarily, the support vector regression algorithm uses the RBF kernel function, the penalty parameter C is set to 10, and the epsilon is set to 0.1.

[0052] It can be understood that if the test accuracy of the model decreases, for example, its root mean square error RMSE is greater than the above preset threshold, the above operation can also be started to continue training the model.

[0053] According to the above implementation, an energy consumption demand prediction model can be trained.

[0054] In one embodiment, the above method also includes: when the root mean square error is greater than a preset threshold, updating the parameters of the support vector regression algorithm, and based on the updated support vector regression algorithm, returning to continue to execute the following steps: inputting the historical operating status and historical indoor temperature at each historical time point in the air-conditioning related information sequence into the support vector regression algorithm to obtain the third predicted energy consumption demand at each historical time point output by the support vector regression algorithm; determining the root mean square error based on the third predicted energy consumption demand at each historical time point and the historical energy consumption demand at each historical time point in the air-conditioning related information sequence.

[0055] Exemplarily, during the model training process, the root mean square error RMSE gradually decreases from the initial 0.5. When the RMSE reaches 0.09, which is lower than the preset threshold of 0.1, the model training is completed and the trained model is output.

[0056] According to the above implementation, through multiple trainings, an energy consumption demand prediction model that meets the accuracy requirements can be generated.

[0057] In one embodiment, the above method may also include a training generation process for a ventilation effect prediction module, specifically including: obtaining a second training sample set, wherein the training samples in the second training sample set include orientation information of the building samples, wind speed and direction data of the environment where the building samples are located, and marked ventilation effects of the environment where the building samples are located; initializing the decision tree; randomly selecting any training sample from the second training sample set, and based on the selected training sample, determining the optimal segmentation feature for each tree node in the decision tree to obtain a new decision tree; and when the new decision tree meets the preset conditions, determining the ventilation effect prediction module based on the new decision tree.

[0058] In one embodiment, the above method may further include:

[0059] When the new decision tree does not meet the preset conditions, based on the new decision tree, return to continue to execute the step of randomly selecting any training sample from the second training sample set, and determining the best segmentation feature for each tree node in the decision tree based on the selected training sample to obtain a new decision tree.

[0060] Exemplarily, the orientation information of the building samples may be divided according to directions such as east, south, west, and north, and the orientations of different building samples may be different or the same.

[0061] Exemplarily, the wind speed data is divided into different levels according to the wind speed, for example, the wind speed data is divided into three levels: less than 3 m / s, 3-5 m / s, and greater than 5 m / s.

[0062] Exemplarily, the wind direction data is divided into eight directions, namely north (337.5°-22.5°), northeast (22.5°-67.5°), east (67.5°-112.5°), southeast (112.5°-157.5°), south (157.5°-202.5°), southwest (202.5°-247.5°), west (247.5°-292.5°), and northwest (292.5°-337.5°).

[0063] For example, the GPS positioning system is used to determine the longitude and latitude coordinates of the building, and the azimuth of the main facade of the building is calculated in combination with the digital elevation model. Wind speed and direction data can be collected by meteorological stations installed around the building and recorded every 10 minutes. For a building with coordinates of (116.3°E, 39.9°N), the azimuth of its main facade is 185°, which is classified as a south-facing building. At a certain moment, the wind speed was measured to be 4.2m / s and the wind direction was 62°, which are classified as 3-5m / s wind speed level and northeast wind direction respectively.

[0064] For example, marking ventilation effects may include ventilation intensity and heat, etc.

[0065] Exemplarily, the above data are combined into training samples, such as (south direction, 3-5m / s, northeast wind, ventilation intensity is level 2).

[0066] For example, when the random forest algorithm is used to train the model, the number of decision trees can be set to 100, the maximum depth of each tree can be set to 10, and the minimum number of leaf node samples can be set to 5.

[0067] Exemplarily, two of the three features of building orientation, wind speed level, and wind direction are randomly selected as segmentation features for each node.

[0068] For example, during the training process, 80% of the data is used as a training set and 20% is used as a validation set. The root mean square error RMSE is calculated by cross-validation, and when the RMSE is less than 0.5, it is considered that the model meets the preset accuracy requirements.

[0069] According to the above implementation, a ventilation effect prediction module can be trained.

[0070] In one embodiment, the above-mentioned predicted ventilation effect based on the environment of each building is used to simulate the actual operating status and actual indoor temperature of the air-conditioning group of each building, and the predicted operating status and predicted indoor temperature of the air-conditioning group of each building under the predicted ventilation effect are obtained, which may include: obtaining the indoor heat source information and wall heat transfer index of the building; using the heat balance equation, based on the indoor heat source information, the wall heat transfer index and the predicted ventilation effect, the actual operating status and actual indoor temperature of each air-conditioner in the air-conditioning group of each building are calculated, and the predicted operating status and predicted indoor temperature of each air-conditioner in the air-conditioning group of each building are obtained.

[0071] Exemplarily, the indoor heat source information, wall heat transfer index and predicted ventilation effect, the actual operating status of each air conditioner in the air-conditioning group of each building and the actual indoor temperature are substituted into the heat balance equation, and then the substituted heat balance equation is calculated to obtain the predicted operating status and predicted indoor temperature of each air conditioner in the air-conditioning group of each building under the predicted ventilation effect.

[0072] For example, the current status of the air conditioner group (air conditioner A: 26°C, cooling mode, medium speed; air conditioner B: off; air conditioner C: 24°C, cooling mode, high speed) and the room temperature data are 27°C, 29°C, and 25°C respectively, the indoor heat source (500W / person, 50 people), wall heat transfer (U value 0.5W / m²K, area 1000m²), using the heat balance equation to calculate, it can be concluded that the room temperature will drop by 1.5°C after 4 hours. Then, the system can automatically adjust the air conditioning parameters, the set temperature of air conditioner A drops to 25.5°C, air conditioner B is turned on and set to 26°C, and air conditioner C remains unchanged.

[0073] According to the above-mentioned implementation, the predicted operating state of each air conditioner and the predicted change of the indoor temperature under the predicted ventilation effect can be predicted by using the heat balance equation.

[0074] In one embodiment, a natural ventilation instruction is issued to an air conditioning group of a building, including: obtaining the indoor and outdoor temperature difference of the building, wind speed and direction data of the environment, and air quality data; using a decision tree algorithm to calculate the indoor and outdoor temperature difference of the building, wind speed and direction data of the environment, and air quality data to obtain a ventilation mode, ventilation duration, and ventilation intensity; based on the ventilation mode, ventilation duration, and ventilation intensity, a natural ventilation instruction is generated; and a natural ventilation instruction is issued to the air conditioning group of the building.

[0075] It can be understood that the decision tree algorithm is a pre-trained algorithm.

[0076] Exemplarily, if the second predicted energy demand is less than the first predicted energy demand, the natural ventilation decision module is triggered. This module uses a decision tree algorithm to determine the ventilation mode, such as one-side ventilation or through-hall ventilation, ventilation duration and ventilation intensity, that is, the percentage of window open area, based on the current indoor and outdoor temperature difference, wind speed and air quality data.

[0077] For example, in a certain intelligent building, the system can obtain the latest energy consumption data according to the above implementation mode, that is, the first predicted energy consumption demand is 100kWh, and the second predicted energy consumption demand is 85kWh. The comparison result shows that natural ventilation can be implemented, and the decision module is triggered. The current outdoor temperature is 25°C, the indoor temperature is 28°C, the wind speed is 3m / s, and the PM2.5 concentration is 35μg / m³. The decision tree algorithm selects the through-hall ventilation mode based on these parameters, sets the ventilation time to 45 minutes, and the window opening area to 70%.

[0078] It can be understood that after adopting the natural ventilation mode, the user side can save energy for storage, thus achieving the effect of energy storage.

[0079] According to the above implementation, a natural ventilation instruction suitable for a specified air-conditioning group is generated, and the air-conditioning group is controlled to work according to the natural ventilation instruction, thereby achieving the effect of user-side energy management.

[0080] Figure 2 It is a structural block diagram of a user-side energy storage management system based on big data according to another embodiment of the present disclosure.

[0081] like Figure 2 As shown, the user-side energy storage management system based on big data may include:

[0082] The first prediction module 210 is used to respond to the request instruction for reducing the power load from the grid side, use the energy consumption demand prediction model to process the actual operation status and actual indoor temperature of the air conditioning group of each building on the user side, and predict the first predicted energy consumption demand of the air conditioning group of each building respectively;

[0083] The second prediction module 220 is used to use the ventilation effect prediction module to process the wind speed and direction data of the environment where each of the buildings is located, and the orientation information of each of the buildings, and respectively predict the predicted ventilation effects of the environment where each of the buildings is located;

[0084] The simulation module 230 is used to simulate the actual operation status and actual indoor temperature of the air conditioning group of each building based on the predicted ventilation effect of the environment to which each building belongs, so as to obtain the predicted operation status and predicted indoor temperature of the air conditioning group of each building under the predicted ventilation effect;

[0085] The third prediction module 240 is used to use the energy consumption demand prediction model to process the predicted operating state and predicted indoor temperature of each of the buildings under the predicted ventilation effect, and respectively predict the second predicted energy consumption demand of each of the buildings;

[0086] The power load adjustment module 250 is used to send a natural ventilation instruction to the air-conditioning group of any of the buildings, so as to control each air-conditioner in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side, when the second predicted energy demand of the building is less than the first predicted energy demand of the building, and the difference between the second predicted energy demand of the building and the first predicted energy demand of the building is greater than the power load reduction required by the request instruction.

[0087] In one embodiment, the system may further include:

[0088] A first sample acquisition module is used to acquire a first training sample set, wherein each training sample in the first training sample set includes an air-conditioning related information sequence of an air-conditioning group sample, the air-conditioning related information sequence includes air-conditioning related information of each historical time point arranged in chronological order, the air-conditioning related information includes a historical operating state, a historical indoor temperature and a historical energy consumption demand, and the historical operating state includes an air-conditioning switch state, an air-conditioning set temperature, an air-conditioning operating mode and an air-conditioning wind speed of each air-conditioning in the air-conditioning group sample;

[0089] A model calculation module, used for inputting the historical operating status and the historical indoor temperature at each historical time point in the air-conditioning related information sequence into the support vector regression algorithm, and obtaining the third predicted energy consumption demand at each historical time point output by the support vector regression algorithm;

[0090] A root mean square error calculation module, used to determine a root mean square error based on the third predicted energy consumption demand at each of the historical time points and the historical energy consumption demand at each of the historical time points in the air-conditioning related information sequence;

[0091] The first model determination module is used to determine the energy consumption demand prediction model based on the support vector regression algorithm when the root mean square error is less than a preset threshold.

[0092] In one embodiment, the above system may further include:

[0093] A model adjustment module is used to update the parameters of the support vector regression algorithm when the root mean square error is greater than the preset threshold, and return to continue to execute the following steps based on the updated support vector regression algorithm:

[0094] The historical operating status and the historical indoor temperature at each historical time point in the air-conditioning related information sequence are input into the support vector regression algorithm to obtain the third predicted energy consumption demand at each historical time point output by the support vector regression algorithm;

[0095] The root mean square error is determined by the third predicted energy consumption demand based on each of the historical time points and the historical energy consumption demand at each of the historical time points in the air-conditioning related information sequence.

[0096] In one embodiment, the above system may further include:

[0097] A second sample acquisition module is used to acquire a second training sample set, wherein the training samples in the second training sample set include orientation information of building samples, wind speed and direction data of the environment where the building samples are located, and marked ventilation effects of the environment where the building samples are located;

[0098] Decision tree initialization module, used to initialize the decision tree;

[0099] A decision tree training module, used for randomly selecting any training sample from the second training sample set, and determining the best segmentation feature for each tree node in the decision tree based on the selected training sample, so as to obtain a new decision tree;

[0100] The second module is a determination module, which is used to determine the ventilation effect prediction module based on the new decision tree when the new decision tree meets the preset conditions.

[0101] In one embodiment, the above system may further include:

[0102] A loop training module is used to return to the step of randomly selecting any training sample from the second training sample set based on the new decision tree when the new decision tree does not meet the preset conditions, and determine the best segmentation feature for each tree node in the decision tree based on the selected training sample to obtain a new decision tree.

[0103] In one implementation, the simulation module 230 includes:

[0104] A first data acquisition unit, used to acquire indoor heat source information and wall heat transfer index of the building;

[0105] The equation calculation unit is used to use a heat balance equation to calculate the actual operating status and actual indoor temperature of each air conditioner in the air-conditioning group of each building based on the indoor heat source information, the wall heat transfer index and the predicted ventilation effect, so as to obtain the predicted operating status and predicted indoor temperature of each air conditioner in the air-conditioning group of each building under the predicted ventilation effect.

[0106] In one implementation, the power load adjustment module 250 includes:

[0107] A second data acquisition unit is used to acquire the indoor and outdoor temperature difference of the building, wind speed and direction data of the environment, and air quality data;

[0108] A decision calculation unit, used to calculate the indoor and outdoor temperature difference of the building, the wind speed and direction data of the environment and the air quality data by using a decision tree algorithm to obtain a ventilation mode, ventilation duration and ventilation intensity;

[0109] a ventilation instruction determination unit, configured to generate the natural ventilation instruction based on the ventilation mode, the ventilation duration and the ventilation intensity;

[0110] The ventilation instruction sending unit is used to send natural ventilation instructions to the air conditioning group of the building.

[0111] According to an embodiment of the present disclosure, the above method of the present disclosure may be applied to an electronic device and a readable storage medium.

[0112] Figure 3A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0113] like Figure 3 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0114] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a user-side energy storage management method based on big data. For example, in some embodiments, a user-side energy storage management method based on big data may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of a user-side energy storage management method based on big data described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute a user-side energy storage management method based on big data in any other appropriate manner (for example, by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0120] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0121] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A user-side energy storage management method based on big data, characterized in that: include: In response to a request instruction for reducing the power load from the power grid side, an energy consumption demand prediction model is used to process the actual operating status and actual indoor temperature of the air conditioning group of each building on the user side, and first predicted energy consumption demand of the air conditioning group of each building is predicted respectively; Using a ventilation effect prediction module, the wind speed and direction data of the environment where each of the buildings is located, as well as the orientation information of each of the buildings are processed to respectively predict the predicted ventilation effects of the environment where each of the buildings is located; Based on the predicted ventilation effect of the environment to which each of the buildings belongs, the actual operating state and the actual indoor temperature of the air-conditioning group of each of the buildings are simulated respectively to obtain the predicted operating state and predicted indoor temperature of the air-conditioning group of each of the buildings under the predicted ventilation effect, which specifically includes: obtaining the indoor heat source information and the wall heat transfer index of the building; using the heat balance equation, based on the indoor heat source information, the wall heat transfer index and the predicted ventilation effect, the actual operating state and the actual indoor temperature of each air-conditioning in the air-conditioning group of each of the buildings are calculated to obtain the predicted operating state and the predicted indoor temperature of each air-conditioning in the air-conditioning group of each of the buildings under the predicted ventilation effect; The energy consumption demand prediction model is used to process the predicted operating state and predicted indoor temperature of each of the buildings under the predicted ventilation effect, and the second predicted energy consumption demand of the air conditioning group of each of the buildings is predicted respectively; For any of the buildings, when the second predicted energy consumption demand of the building is less than the first predicted energy consumption demand of the building, and the difference between the second predicted energy consumption demand of the building and the first predicted energy consumption demand of the building is greater than the amount of power load reduction required by the request instruction, a natural ventilation instruction is issued to the air-conditioning group of the building to control each air-conditioner in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side; The training process of the energy consumption demand prediction model includes: Acquire a first training sample set, wherein each training sample in the first training sample set includes an air-conditioning related information sequence of an air-conditioning group sample, the air-conditioning related information sequence includes air-conditioning related information of each historical time point arranged in chronological order, the air-conditioning related information includes a historical operating state, a historical indoor temperature, and a historical energy consumption demand, and the historical operating state includes an air-conditioning switch state, an air-conditioning set temperature, an air-conditioning operating mode, and an air-conditioning wind speed of each air-conditioning in the air-conditioning group sample; Inputting the historical operating status and the historical indoor temperature at each historical time point in the air-conditioning related information sequence into a support vector regression algorithm to obtain a third predicted energy consumption demand at each historical time point output by the support vector regression algorithm; Determine a root mean square error based on the third predicted energy consumption demand at each of the historical time points and the historical energy consumption demand at each of the historical time points in the air-conditioning related information sequence; When the root mean square error is less than a preset threshold, determining the energy consumption demand prediction model based on the support vector regression algorithm; The training process of the ventilation effect prediction module includes: Acquire a second training sample set, wherein the training samples in the second training sample set include orientation information of building samples, wind speed and direction data of the environment where the building samples are located, and marked ventilation effects of the environment where the building samples are located; Initialize the decision tree; Randomly selecting any training sample from the second training sample set, and based on the selected training sample, determining the best segmentation feature for each tree node in the decision tree to obtain a new decision tree; In the case where the new decision tree meets the preset conditions, determining the ventilation effect prediction module based on the new decision tree; The step of issuing a natural ventilation instruction to the air conditioning group of the building includes: Obtaining the indoor and outdoor temperature difference of the building, wind speed and direction data of the environment, and air quality data; A decision tree algorithm is used to calculate the indoor and outdoor temperature difference of the building, the wind speed and direction data of the environment, and the air quality data to obtain the ventilation mode, ventilation duration, and ventilation intensity; generating the natural ventilation instruction based on the ventilation mode, the ventilation duration and the ventilation intensity; A natural ventilation instruction is issued to the air conditioning group of the building.

2. The method according to claim 1, characterized in that Also includes: When the root mean square error is greater than the preset threshold, update the parameters of the support vector regression algorithm, and return to continue to perform the following steps based on the updated support vector regression algorithm: The historical operating status and the historical indoor temperature at each historical time point in the air-conditioning related information sequence are input into the support vector regression algorithm to obtain the third predicted energy consumption demand at each historical time point output by the support vector regression algorithm; The root mean square error is determined by the third predicted energy consumption demand based on each of the historical time points and the historical energy consumption demand at each of the historical time points in the air-conditioning related information sequence.

3. The method according to claim 1, characterized in that Also includes: When the new decision tree does not meet the preset conditions, based on the new decision tree, return to continue executing the step of randomly selecting any training sample from the second training sample set, and determining the best segmentation feature for each tree node in the decision tree based on the selected training sample to obtain a new decision tree.

4. A user-side energy storage management system based on big data, characterized in that: include: A first prediction module is used to respond to a request instruction for reducing power load from the power grid side, use an energy consumption demand prediction model to process the actual operating status and actual indoor temperature of the air conditioning group of each building on the user side, and respectively predict the first predicted energy consumption demand of the air conditioning group of each building; The second prediction module is used to use the ventilation effect prediction module to process the wind speed and direction data of the environment where each of the buildings is located, and the orientation information of each of the buildings, and respectively predict the predicted ventilation effects of the environment where each of the buildings is located; A simulation module is used to simulate the actual operation status and actual indoor temperature of the air conditioning group of each building based on the predicted ventilation effect of the environment to which each building belongs, so as to obtain the predicted operation status and predicted indoor temperature of the air conditioning group of each building under the predicted ventilation effect; A third prediction module is used to use the energy consumption demand prediction model to process the predicted operating state and predicted indoor temperature of each of the buildings under the predicted ventilation effect, and respectively predict the second predicted energy consumption demand of the air conditioning group of each of the buildings; The power load adjustment module is used for, for any of the buildings, when the second predicted energy consumption demand of the building is less than the first predicted energy consumption demand of the building, and the difference between the second predicted energy consumption demand of the building and the first predicted energy consumption demand of the building is greater than the power load reduction required by the request instruction, issuing a natural ventilation instruction to the air-conditioning group of the building to control each air-conditioning in the air-conditioning group to operate in the natural ventilation mode, thereby reducing the power load on the user side; The training process of the energy consumption demand prediction model includes: Acquire a first training sample set, wherein each training sample in the first training sample set includes an air-conditioning related information sequence of an air-conditioning group sample, the air-conditioning related information sequence includes air-conditioning related information of each historical time point arranged in chronological order, the air-conditioning related information includes a historical operating state, a historical indoor temperature, and a historical energy consumption demand, and the historical operating state includes an air-conditioning switch state, an air-conditioning set temperature, an air-conditioning operating mode, and an air-conditioning wind speed of each air-conditioning in the air-conditioning group sample; Inputting the historical operating status and the historical indoor temperature at each historical time point in the air-conditioning related information sequence into a support vector regression algorithm to obtain a third predicted energy consumption demand at each historical time point output by the support vector regression algorithm; Determine a root mean square error based on the third predicted energy consumption demand at each of the historical time points and the historical energy consumption demand at each of the historical time points in the air-conditioning related information sequence; When the root mean square error is less than a preset threshold, determining the energy consumption demand prediction model based on the support vector regression algorithm; The training process of the ventilation effect prediction module includes: Acquire a second training sample set, wherein the training samples in the second training sample set include orientation information of building samples, wind speed and direction data of the environment where the building samples are located, and marked ventilation effects of the environment where the building samples are located; Initialize the decision tree; Randomly selecting any training sample from the second training sample set, and based on the selected training sample, determining the best segmentation feature for each tree node in the decision tree to obtain a new decision tree; In the case where the new decision tree meets the preset conditions, determining the ventilation effect prediction module based on the new decision tree; Wherein, the simulation module includes: A first data acquisition unit, used to acquire indoor heat source information and wall heat transfer index of the building; an equation calculation unit, for calculating the actual operating state and the actual indoor temperature of each air conditioner in the air conditioning group of each of the buildings by using a heat balance equation based on the indoor heat source information, the wall heat transfer index and the predicted ventilation effect, and obtaining the predicted operating state and the predicted indoor temperature of each air conditioner in the air conditioning group of each of the buildings under the predicted ventilation effect; Wherein, the power load adjustment module includes: A second data acquisition unit is used to acquire the indoor and outdoor temperature difference of the building, wind speed and direction data of the environment, and air quality data; A decision calculation unit, used to calculate the indoor and outdoor temperature difference of the building, the wind speed and direction data of the environment and the air quality data by using a decision tree algorithm to obtain a ventilation mode, ventilation duration and ventilation intensity; a ventilation instruction determination unit, configured to generate the natural ventilation instruction based on the ventilation mode, the ventilation duration and the ventilation intensity; The ventilation instruction sending unit is used to send natural ventilation instructions to the air conditioning group of the building.

5. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-3.

Images