CN118442676A - Cold station temperature control method and device, electronic equipment and readable storage medium - Google Patents
Cold station temperature control method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN118442676A CN118442676A CN202410650038.7A CN202410650038A CN118442676A CN 118442676 A CN118442676 A CN 118442676A CN 202410650038 A CN202410650038 A CN 202410650038A CN 118442676 A CN118442676 A CN 118442676A
- Authority
- CN
- China
- Prior art keywords
- prediction
- cold
- layer
- training
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 140
- 230000007613 environmental effect Effects 0.000 claims abstract description 32
- 238000002790 cross-validation Methods 0.000 claims abstract description 12
- 238000012795 verification Methods 0.000 claims description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 17
- 238000010801 machine learning Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000005094 computer simulation Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 10
- 230000001276 controlling effect Effects 0.000 description 8
- 238000001816 cooling Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010200 validation analysis Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F5/00—Air-conditioning systems or apparatus not covered by F24F1/00 or F24F3/00, e.g. using solar heat or combined with household units such as an oven or water heater
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of computer models, and provides a cold station temperature control method, a cold station temperature control device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring operation parameters of cold station equipment and corresponding environment parameters; inputting environmental parameters and operation parameters into a cold demand prediction model to perform cold demand prediction, wherein the cold demand prediction model comprises a plurality of layers of prediction modules, the layers of prediction modules are obtained by cross-validation training of at least one initial prediction model of each layer of prediction module, at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and at least one prediction result of each layer is used as input of a next layer of prediction module; and obtaining a predicted value of the cold energy demand to control the temperature of the cold station. The method can remarkably improve the accuracy of cold energy demand prediction, and further accurately control the temperature of the cold station by utilizing the cold energy demand prediction, thereby achieving the purpose of reducing energy waste.
Description
Technical Field
The present application relates to the field of computer models, and in particular, to a cold station temperature control method, apparatus, electronic device, and readable storage medium.
Background
With rapid advancement of urbanization and vigorous development of commercial activities, energy consumption problems in public places such as markets are increasingly concerned. In these public places, the cold station system, which is a key facility for regulating indoor temperature, has energy consumption that occupies a large part of total energy consumption of the market, and has significant influence on operation cost and environmental impact of the market. Conventional cold station systems typically employ temperature regulation methods based on human experience and simple feedback control. Such methods often rely on fixed parameter settings and manual adjustments, lacking adaptability to real-time environmental changes. In actual operation of a market, the indoor temperature frequently fluctuates due to the influence of various factors such as weather changes, indoor and outdoor temperature differences and the like. However, the conventional cold station system often cannot respond to the environmental factor change timely and accurately, so that the temperature control is inaccurate, and the problem of energy waste is caused.
Disclosure of Invention
In view of the above, embodiments of the present application provide a method, an apparatus, an electronic device, and a readable storage medium for controlling a cold station temperature, so as to solve the problem in the prior art that the temperature control is inaccurate and energy waste is caused due to the fact that environmental factor changes cannot be responded accurately in time.
In a first aspect of the embodiment of the present application, there is provided a cold station temperature control method, including:
Acquiring operation parameters of cold station equipment and environment parameters corresponding to the operation of the cold station equipment; the method comprises the steps of inputting environmental parameters and operation parameters into a trained cold energy demand prediction model, and predicting the cold energy demand of a cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-validation training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction. And acquiring a cold energy demand predicted value output by the cold energy demand predicted model, and controlling the temperature of the cold station based on the cold energy demand predicted value.
In a second aspect of the embodiment of the present application, there is provided a cold station temperature control apparatus, the method comprising:
The acquisition module is configured to acquire the operation parameters of the cold station equipment and acquire the environment parameters corresponding to the operation of the cold station equipment; the cold energy demand prediction module comprises a plurality of layers of prediction modules, wherein the layers of prediction modules are obtained by cross verification training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of the next layer of prediction module for further prediction. And the control module is configured to acquire the predicted value of the cold energy demand output by the cold energy demand prediction model and control the temperature of the cold station based on the predicted value of the cold energy demand.
In a third aspect of the embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect of the embodiments of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.
Compared with the prior art, the embodiment of the application has the beneficial effects that:
Acquiring operation parameters of cold station equipment and environment parameters corresponding to the operation of the cold station equipment; the method comprises the steps of inputting environmental parameters and operation parameters into a trained cold energy demand prediction model, and predicting the cold energy demand of a cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-validation training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction. And acquiring a cold energy demand predicted value output by the cold energy demand predicted model, and controlling the temperature of the cold station based on the cold energy demand predicted value. According to the application, the nonlinear relation between the operation parameters and the environment parameters and the cold energy demand can be fully excavated through the multi-layer prediction modules, so that the accuracy and the stability of cold energy demand prediction are obviously enhanced, meanwhile, the robustness, the generalization and the self-adaptive capacity of the cold energy demand prediction model can be further improved through the diversity and the cross-validation training of at least one initial prediction model combination in each layer of prediction module, the accuracy of cold energy demand prediction is enhanced, a more accurate cold energy demand prediction value is obtained, and the cold energy demand prediction value can be used for accurately controlling the temperature of the cold station, so that the purposes of reducing the energy waste of the cold station and reducing the operation cost are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a cold station temperature control method according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of a cold station temperature control device according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
A cold station temperature control method, apparatus, electronic device, and readable storage medium according to embodiments of the present application will be described in detail with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a cold station temperature control method according to an embodiment of the present application. As shown in fig. 1, the method includes:
s101, acquiring operation parameters of cold station equipment and environment parameters corresponding to the operation of the cold station equipment;
s102, inputting environmental parameters and operation parameters into a trained cold energy demand prediction model, and predicting the cold energy demand of a cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the layers of prediction modules are obtained by cross verification training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction.
And S103, acquiring a cold energy demand predicted value output by the cold energy demand predicted model, and controlling the temperature of the cold station based on the cold energy demand predicted value.
Specifically, the operation parameters of the cold station device include parameters reflecting the operation state and performance of the cold station device, such as the cold machine power, the water pump frequency, the chilled water supply and return temperature, the chilled water supply and return pressure, the chilled water supply and return flow rate, the operation state of the cooling tower, and the like, the environment parameters corresponding to the operation of the cold station device include parameters affecting the indoor comfort and the demand of the cold load, such as indoor and outdoor temperature, humidity, human flow rate, wind speed, weather, and the like, and the acquisition methods of the parameters can be acquired by corresponding sensors, such as a temperature sensor, a humidity sensor, a pressure sensor, a flow sensor, and the like.
It can be understood that the cold demand prediction model is an artificial intelligence model, and includes a multi-layer prediction module that can extract and combine features of the acquired parameters layer by stacking a plurality of prediction layers, thereby capturing complex relationships among the parameters more accurately. At least one initial prediction model of each layer of prediction module can be further optimized and adjusted based on at least one prediction result output by the previous layer as input, so that the accuracy and reliability of cold demand prediction are further improved. In addition, at least one initial prediction model in each layer of prediction module is trained and tested on different data subsets in the cross-validation training process, so that the prediction performance of the initial prediction model is improved. Therefore, the cold energy demand prediction model can predict the cold energy demand of the cold station through the operation parameters and the environment parameters of the cold station equipment to generate a cold energy demand predicted value, and then the cold station adjusts the equipment parameters according to the cold energy demand predicted value so as to achieve an accurate temperature control effect.
It should be noted that the specific layer number of the multi-layer prediction module can be flexibly configured according to actual requirements and application situations. In addition, the number and type of initial prediction models for each layer of prediction modules may also be selected and adjusted. For example, different types of machine learning algorithms may be selected as the initial prediction model, such as linear regression, decision trees, neural networks, etc., and combined and optimized according to different parameter characteristics and prediction requirements, which is not particularly limited in this embodiment.
According to the technical scheme provided by the embodiment of the application, the operation parameters of the cold station equipment are obtained, and the environment parameters corresponding to the operation of the cold station equipment are obtained; the method comprises the steps of inputting environmental parameters and operation parameters into a trained cold energy demand prediction model, and predicting the cold energy demand of a cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-validation training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction. And acquiring a cold energy demand predicted value output by the cold energy demand predicted model, and controlling the temperature of the cold station based on the cold energy demand predicted value. The nonlinear relation between the operation parameters, the environment parameters and the cold energy demand can be fully excavated through the multi-layer prediction modules, so that the accuracy and the stability of cold energy demand prediction are obviously enhanced, meanwhile, the robustness, the generalization and the self-adaptive capacity of the cold energy demand prediction model can be further improved through the diversity and the cross verification training of at least one initial prediction model combination in each layer of prediction module, the accuracy of cold energy demand prediction is enhanced, a more accurate cold energy demand predicted value is obtained, and the cold energy demand predicted value can be used for accurately controlling the temperature of a cold station, so that the purposes of reducing the energy waste of the cold station and reducing the operation cost are achieved.
In some embodiments, before inputting the environmental parameters and the operational parameters into the trained cold demand prediction model, further comprising:
Acquiring a training sample set, and constructing an initial prediction model of each layer of prediction module in the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm; training an initial prediction model of each layer of prediction modules in the multi-layer prediction modules based on the training sample set; obtaining a prediction result output by a final layer of prediction module; and constructing a loss function based on the prediction result output by the last layer of prediction module and the corresponding real label, obtaining a multi-layer prediction module after training when the loss value of the loss function is smaller than a preset value, and obtaining a cold demand prediction model based on the multi-layer prediction module after training.
Specifically, to obtain a high quality cold demand prediction model, multiple layers of prediction modules therein need to be trained and optimized. In training the predictive model, a training sample set containing rich data may first be obtained. The training sample set should include environmental parameters and operation parameters under various conditions and the real label of the cold demand corresponding to the environmental parameters and operation parameters, and on the basis, the training sample set should also cover data under different seasons and different climates so as to fully consider the influence of the environmental parameters on the cold demand. Further, an initial prediction model is constructed for each of the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm. It can be understood that the preset machine learning algorithm may include methods such as linear regression, decision tree, neural network, gradient elevator, etc., specifically, an algorithm suitable for the task characteristics and the data characteristics may be selected for model construction, which is not specifically limited in this implementation. And then training an initial prediction model of each layer of prediction module by using a training sample set, and enabling the initial prediction model to better fit training data and predict the cold energy demand by iterating parameters of an optimization model.
Further, after training is completed, a prediction result output by the last layer of prediction module is obtained and compared with a corresponding real label, a loss function is constructed and used for measuring the difference between the prediction result and the real label, and parameters of the model are further adjusted and optimized by minimizing the loss value of the loss function. When the loss value of the loss function is smaller than a preset value, the model can be considered to be trained, and the model has good prediction performance. And obtaining a multi-layer prediction module with the training completed, and constructing a cold energy demand prediction model based on the module.
Thus, a cold energy demand prediction model with good performance and training completion can be obtained. The model can comprehensively consider the influence of environmental parameters and operation parameters on the cold energy demand, and accurately predicts based on the multi-layer prediction module. In application, environmental parameters and operation parameters acquired in real time can be input into a trained cold demand prediction model to obtain an accurate cold demand prediction result.
In the construction and training of the cold demand prediction model, the diversity and representativeness of the training sample set need to be considered. The training sample set should contain environmental and operational parameters in each case to ensure that the model can accommodate different application scenarios and requirements. For example, when constructing a training sample set, data may be collected in different seasons and under different weather conditions, including environmental parameters such as temperature, humidity, wind speed, and operating parameters such as operating time, load condition, energy efficiency level, and the like of the device. Meanwhile, it is also necessary to ensure that the real label of the cold demand of each sample is accurate, and the generalization capability and accuracy of the cold demand prediction model are improved by constructing a training sample set with rich diversity and representativeness.
According to the technical scheme of the embodiment, a training sample set is obtained, an initial prediction model of each layer of prediction modules in the multi-layer prediction modules is constructed based on the training sample set and a preset machine learning algorithm, and the initial prediction model of each layer of prediction modules in the multi-layer prediction modules is trained based on the training sample set; obtaining a prediction result output by a final layer of prediction module; and constructing a loss function based on a prediction result output by the last layer of prediction module and a corresponding real label, obtaining a multi-layer prediction module after training when the loss value of the loss function is smaller than a preset value, obtaining a cold demand prediction model based on the multi-layer prediction module after training, constructing an initial prediction model based on a training sample set, and continuously optimizing parameters of the model in the training process, so that the model can be ensured to better fit training data and adapt to various complex environmental conditions and operating parameter changes. Meanwhile, the structure of the multi-layer prediction module is adopted, prediction results of different layers can be fully utilized, and accuracy and reliability of the prediction results are improved.
In some embodiments, constructing an initial prediction model for each of the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm includes:
dividing a training sample set into a training set and a verification set, and training a preset machine learning algorithm based on the training set and the verification set to obtain a plurality of intermediate prediction models; calculating a loss value between a predicted result and a true value of each sample in the verification set; calculating at least one of an average absolute loss, a mean square loss, and a root mean square loss for each intermediate prediction model based on the loss values; determining an evaluation result of the plurality of intermediate prediction models according to at least one of average absolute loss, mean square loss and root mean square loss; and selecting a preset number of intermediate prediction models from the plurality of intermediate prediction models as initial prediction models of each layer of prediction modules in the multi-layer prediction modules according to the evaluation results of the plurality of intermediate prediction models.
Specifically, when an initial prediction model of the multi-layer prediction module is constructed, in order to improve stability and generalization capability of the model, a training sample set may be used to train a preset machine learning algorithm to obtain a plurality of intermediate prediction models. For example, the training sample set is divided into a training set for training of the model and a validation set for evaluating the performance of the model. By training a preset machine learning algorithm based on the training set and the verification set, a plurality of intermediate predictive models may be obtained. These intermediate predictive models are derived based on the same training data and parameter settings, but have different predictive capabilities and performance performances due to the different structure of each intermediate predictive model.
It can be appreciated that to evaluate the performance of these intermediate predictive models, a loss value between the predicted and actual values for each sample in the validation set can be calculated. The loss value can reflect the degree of difference between the predicted result and the true value of the intermediate prediction model, and can be used for measuring the prediction precision and accuracy of the model. By calculating the evaluation indexes such as average absolute loss, mean square loss, root mean square loss and the like, the performance of a plurality of intermediate prediction models can be comprehensively evaluated. From these evaluation indexes, evaluation results of a plurality of intermediate prediction models can be determined. The evaluation result may include information on prediction accuracy, stability, robustness, and the like of each model. Based on the evaluation results, a preset number of models can be selected from the plurality of intermediate prediction models to serve as initial prediction models of each layer of prediction modules in the multi-layer prediction modules. In this way, the model with the best prediction performance is selected from a plurality of intermediate prediction models to serve as an initial prediction model, so that the stability and generalization capability of the multi-layer prediction module are improved. Meanwhile, the problems of over fitting, under fitting and the like can be effectively avoided, and the prediction precision and reliability of the cold energy demand prediction model are improved.
It should be noted that the diversity and complementarity between models may also be considered when selecting the initial prediction model. Since each layer of the multi-layer prediction module is composed of at least one initial prediction model, the models between different layers should have a certain difference and complementarity to improve the prediction performance of the whole prediction module. For example, different types of machine learning algorithms may be selected as the initial predictive models for different layers, or parameters and structures of different layer models may be adjusted to have different predictive features and advantages. In addition, in the process of constructing each layer of initial prediction model, the construction requirements of more bottom models and fewer top models can be met as much as possible, so that the stability and generalization capability of the model are improved.
According to the technical scheme of the embodiment, a training sample set is divided into a training set and a verification set, and a preset machine learning algorithm is trained based on the training set and the verification set to obtain a plurality of intermediate prediction models; calculating a loss value between a predicted result and a true value of each sample in the verification set; calculating at least one of an average absolute loss, a mean square loss, and a root mean square loss for each intermediate prediction model based on the loss values; determining an evaluation result of the plurality of intermediate prediction models according to at least one of average absolute loss, mean square loss and root mean square loss; according to the evaluation results of the plurality of intermediate prediction models, a preset number of intermediate prediction models are selected from the plurality of intermediate prediction models to serve as initial prediction models of each layer of prediction modules in the multi-layer prediction modules, and a model with excellent performance is selected to serve as the initial prediction model of each layer of prediction modules in the multi-layer prediction modules through a cross verification method based on a training set and a verification set, so that a cold energy demand prediction model with stable performance and high prediction precision can be constructed, and further a more accurate and reliable prediction result is provided.
In some embodiments, training each of the multi-layer prediction modules based on the training sample set includes:
dividing the preprocessed training sample set into K subsets, wherein each subset comprises operation parameters of cold station equipment in different time periods, and acquiring environment parameters corresponding to the operation of the cold station equipment; for each initial prediction model of the first layer prediction module, K-1 subsets are sequentially used as training data, the rest subset is used as verification data, and K times of training and verification are carried out to obtain an initial prediction result corresponding to each initial prediction model; and for the rest prediction modules except the first layer of prediction module, taking the initial prediction result obtained by the last layer of prediction module as the input of the next layer of prediction module, and repeatedly executing K times of cross validation training until the last layer of prediction module is trained.
Specifically, in the training process of the multi-layer prediction module, in order to fully utilize information of the training sample set and improve generalization capability of the model, the preprocessed training sample set may be divided into K subsets, where each subset includes operation parameters of the cold station device and corresponding environmental parameters in different time periods. For the first layer of the multi-layer prediction module, K-1 subsets are selected as training data, and the remaining subset is selected as verification data. The combination mode is carried out K times, and an initial prediction result corresponding to an initial prediction model can be obtained in each training. In this way, it is ensured that each subset has at least one chance to be used as verification data, thereby making full use of the information in the training sample set. And taking the initial prediction result obtained by the prediction module of the upper layer as the input of the prediction module of the lower layer for the rest prediction modules except the prediction module of the first layer. And then, repeatedly executing the process of the K times of cross validation training until the training of the prediction module of the last layer is completed. The output information of the upper layer of prediction module is fully utilized and is used as the input of the lower layer of prediction module to predict so as to correct the prediction defect of the upper layer of model, thereby constructing a more accurate and stable prediction model.
It should be noted that, for the other prediction modules except the first layer prediction module, besides taking the multiple initial prediction results obtained by the previous layer prediction module as the input of the next layer prediction module, the training sample set may be taken as the input of each layer module, and the next layer prediction module is cross-validated and trained by combining the multiple initial prediction results obtained by the previous layer prediction module and the training sample set, so as to fully utilize the existing training sample set, further mine potential information in the data, and enable each layer prediction module to obtain more comprehensive and accurate training, and further improve the prediction precision and stability of the model.
According to the technical scheme of the embodiment of the application, the preprocessed training sample set is divided into K subsets, and each subset comprises the operation parameters of the cold station equipment in different time periods, and the environment parameters corresponding to the operation of the cold station equipment are obtained; for each initial prediction model of the first layer prediction module, K-1 subsets are sequentially used as training data, the rest subset is used as verification data, and K times of training and verification are carried out to obtain an initial prediction result corresponding to each initial prediction model; and for the rest prediction modules except the first layer of prediction module, taking the initial prediction result obtained by the last layer of prediction module as the input of the next layer of prediction module, and repeatedly executing the K times of cross validation training until the last layer of prediction module is trained. The multi-layer prediction module can be fully trained and verified by adopting a K-time cross verification training method, so that stable performance of the model can be ensured under different time periods and different data distribution. Meanwhile, the problems of over fitting and under fitting can be effectively avoided, and the prediction accuracy and reliability of the model are improved.
In some embodiments, obtaining a training sample set includes:
Determining the equipment operation time of each cold station from the historical operation parameters of the cold station equipment; when the equipment running time is larger than a preset time threshold, the running parameters of the cold station equipment with the equipment running time larger than the preset time threshold and the corresponding environment parameters are used as training sample sets.
Specifically, in the process of acquiring the training sample set, in order to ensure the quality and the effectiveness of the sample, data with longer equipment operation time can be screened from the historical operation parameters of the cold station equipment for use. That is, determining the equipment operation time of each cold station may be implemented by analyzing a history operation record or log, which is not particularly limited. Only when the device running time is greater than the preset time threshold value, the corresponding running parameters and the corresponding environment parameters are used as a part of the training sample set. In this way, data that is too short or unstable in run time can be excluded, thereby ensuring the quality of the training sample set. At the same time, this also helps to improve the stability and generalization ability of the model, as long-term operational data generally more reflects the actual operational situation and performance characteristics of the device.
According to the technical scheme provided by the embodiment of the application, the equipment operation time of each cold station is determined from the historical operation parameters of the cold station equipment; when the equipment running time is larger than a preset time threshold, the running parameters of the cold station equipment with the equipment running time larger than the preset time threshold and the corresponding environment parameters are used as training sample sets. The quality and the effectiveness of the sample are ensured by using the data with longer running time of the screening equipment as a training sample set.
In some embodiments, prior to obtaining the training sample set, further comprising:
And at least one of constructing period operation characteristics, cutting off cold energy negative values, calculating accumulated cold energy in preset time, analyzing and counting indoor temperature and humidity, calculating wet bulb temperature, constructing indoor and outdoor temperature difference characteristics and cold source system temperature difference characteristics, performing characteristic processing on inclination characteristic processing, and performing independent heat vector coding on a classification variable by utilizing the operation parameters of cold station equipment in the training sample set and environment parameters corresponding to the operation of the cold station equipment.
Specifically, to further improve the prediction accuracy and performance of the model, a series of feature processing operations may be performed on the training sample set. These operations include, but are not limited to, construction period run characteristics, cold quantity negative value cut-off, calculation of accumulated cold quantity within a preset time, analysis and statistics of indoor temperature and humidity, construction of indoor and outdoor temperature difference characteristics and cold source system temperature difference characteristics, processing of inclination characteristics, independent heat vector coding of classification variables, and the like. By constructing the operation characteristics of the period, the operation characteristics and modes of the cold station equipment in different seasons and times can be reflected; by means of negative value cutoff of the cooling quantity, interference of negative values to model training can be avoided; by calculating the accumulated cold for a preset time (e.g., 1 hour), the accumulated effect of cold can be captured; the condition of the indoor environment can be known and the data of the abnormal sensor can be filtered through indoor temperature and humidity analysis and statistics; the influence of the environmental temperature change on the cold energy demand can be reflected by constructing the indoor and outdoor temperature difference characteristic and the cold source system temperature difference characteristic; the wet bulb temperature can be calculated according to the collected indoor temperature and humidity data to serve as an additional characteristic so as to reflect the state of the indoor environment more comprehensively; processing the oblique features can eliminate the correlation or redundancy among the features, and specifically can comprise operations such as conversion processing, normalization truncation and the like; the classification variables are subjected to independent hot vector coding so that classification data can be converted into a numerical form which can be processed by the model. The feature processing operations can be selected and combined according to actual conditions and requirements so as to achieve the purpose of improving the model performance.
According to the technical scheme provided by the embodiment of the application, before the training sample set is acquired, a series of characteristic processing operations are carried out through the operation parameters and the environment parameters, so that the prediction precision and the stability of the model can be effectively improved. The feature processing operation can extract key features which have important influence on the prediction result, eliminate noise and redundant information in the data, and enable the model to understand and learn the internal rules of the data more easily. By constructing the time period operating characteristics, the operating characteristics of the cold station equipment in different time periods can be captured, so that the future operating state of the cold station equipment can be accurately predicted. And the negative value of the cold quantity is cut off, so that the interference of the negative value to model training can be avoided, and the stability and reliability of the model are improved. The accumulated cold in the preset time is calculated, so that the accumulated effect of the cold can be reflected, and the accuracy of prediction is further improved. The indoor temperature and humidity analysis and statistics can be used for knowing the condition of the indoor environment and helping the model to adapt to different environmental conditions better. The influence of the environmental temperature change on the cold energy demand can be reflected by constructing the indoor and outdoor temperature difference characteristic and the temperature difference characteristic of the cold source system, and the sensitivity of the model to the environmental change is improved. And the inclined characteristics are processed, so that the correlation or redundancy among the characteristics can be eliminated, and the generalization capability of the model is improved. And (3) performing independent thermal vector coding on the classification variable, so that the classification data can be converted into a numerical form which can be processed by the model, and the model can fully utilize all input information.
In some embodiments, after controlling the cold station temperature based on the cold demand forecast, further comprising:
Storing the predicted value of the cold energy demand and the corresponding environmental parameters and operation parameters in a time sequence mode; and acquiring data of the latest preset days from the stored cold demand predicted values and the corresponding operation parameters as a new training sample set to train the cold demand predicted model, obtaining an updated cold demand predicted model, and predicting the cold demand based on the updated cold demand predicted model.
Specifically, after the cold station temperature is controlled based on the cold energy demand predicted value, the model may be periodically updated and optimized in order to further improve the prediction performance of the model. In particular, the predicted value of the cooling demand and the corresponding environmental and operating parameters may be stored in a time series for later use. Then, the latest data of preset days are selected from the stored data to serve as a new training sample set, and the preset days can be set according to actual requirements, for example, the latest data of one week or two weeks can be selected. And then training the cold energy demand prediction model by using a new training sample set to obtain an updated cold energy demand prediction model. By continuously updating and optimizing the model, the model can be better adapted to the change of environment and equipment, and the accuracy and reliability of prediction are improved. And finally, carrying out cold energy demand prediction based on the updated cold energy demand prediction model so as to realize more accurate and efficient cold station temperature control. This periodic model update and optimization process can be cycled to ensure continued effectiveness and performance improvement of the model.
It should be understood that the sequence number of each step in the above embodiment does not mean the sequence of execution sequence, and the execution sequence of each process should be determined by the function and the internal logic of each process, and should not be construed as limiting the process in the embodiment of the present application.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein.
The following are examples of the apparatus of the present application that may be used to perform the method embodiments of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method of the present application.
Fig. 2 is a schematic structural diagram of a cold station temperature control device according to an embodiment of the present application. As shown in fig. 2, the apparatus includes:
an obtaining module 201, configured to obtain an operation parameter of the cold station device, and obtain an environment parameter corresponding to the operation of the cold station device;
The input module 202 is configured to input the environmental parameter and the operation parameter into a trained cold energy demand prediction model, and predict the cold energy demand of the cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-checking and training at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of the next layer of prediction module for further prediction.
The control module 203 is configured to obtain a predicted value of the cooling demand output by the cooling demand prediction model, and control the temperature of the cooling station based on the predicted value of the cooling demand.
In some embodiments, the cold station temperature control apparatus further comprises a training module 204, the training module 204 configured to obtain a training sample set and construct an initial prediction model for each of the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm; training an initial prediction model of each layer of prediction modules in the multi-layer prediction modules based on the training sample set; obtaining a prediction result output by a final layer of prediction module; and constructing a loss function based on the prediction result output by the last layer of prediction module and the corresponding real label, obtaining a trained multi-layer prediction module when the loss value of the loss function is smaller than a preset value, and obtaining a cold demand prediction model based on the trained multi-layer prediction module.
In some embodiments, the training module 204 is further configured to divide the training sample set into a training set and a validation set, and train a preset machine learning algorithm based on the training set and the validation set to obtain a plurality of intermediate prediction models; calculating a loss value between a predicted result and a true value of each sample in the verification set; calculating at least one of an average absolute loss, a mean square loss, and a root mean square loss for each intermediate prediction model based on the loss values; determining an evaluation result of the plurality of intermediate prediction models according to at least one of average absolute loss, mean square loss and root mean square loss; and selecting a preset number of intermediate prediction models from the plurality of intermediate prediction models as initial prediction models of each layer of prediction modules in the multi-layer prediction modules according to the evaluation results of the plurality of intermediate prediction models.
In some embodiments, the training module 204 is further configured to divide the training sample set into K subsets, wherein each subset contains operating parameters of the cold station device for different time periods and environmental parameters corresponding to when the cold station device is operating; for each initial prediction model of the first layer prediction module, K-1 subsets are sequentially used as training data, the rest subset is used as verification data, and K times of training and verification are carried out to obtain an initial prediction result corresponding to each initial prediction model; and for the rest prediction modules except the first layer of prediction module, taking the initial prediction result obtained by the last layer of prediction module as the input of the next layer of prediction module, and repeatedly executing the K times of cross validation training until the last layer of prediction module is trained.
In some embodiments, the training module 204 is further configured to determine a device runtime for each cold station from historical operating parameters of the cold station device; when the equipment running time is larger than a preset time threshold, the running parameters of the cold station equipment with the equipment running time larger than the preset time threshold and the corresponding environment parameters are used as training sample sets.
In some embodiments, the training module 204 is further configured to perform at least one of constructing a time period operation feature, performing a truncation of a negative value of the cold amount, calculating an accumulated cold amount for a preset time, performing indoor temperature humidity analysis and statistics, calculating a wet bulb temperature, constructing an indoor and outdoor temperature difference feature and a cold source system temperature difference feature, performing a feature processing on an inclination feature processing, and performing a single heat vector encoding on a classification variable using an operation parameter of the cold station apparatus in the training sample set and an environment parameter corresponding to the operation of the cold station apparatus.
In some embodiments, the control module 204 is further configured to store the refrigeration demand predictions as well as the corresponding environmental parameters and operating parameters in a time series; and selecting the latest data of preset days from the stored cold demand predicted values, the corresponding environment parameters and the corresponding operation parameters as a new training sample set to train the cold demand predicted model, obtaining an updated cold demand predicted model, and predicting the cold demand based on the updated cold demand predicted model.
Fig. 3 is a schematic diagram of an electronic device 3 according to an embodiment of the present application. As shown in fig. 3, the electronic apparatus 3 of this embodiment includes: a processor 301, a memory 302 and a computer program 303 stored in the memory 302 and executable on the processor 301. The steps of the various method embodiments described above are implemented when the processor 301 executes the computer program 303. Or the processor 301 when executing the computer program 303 performs the functions of the modules/units in the above-described device embodiments.
The electronic device 3 may be an electronic device such as a desktop computer, a notebook computer, a palm computer, or a cloud server. The electronic device 3 may include, but is not limited to, a processor 301 and a memory 302. It will be appreciated by those skilled in the art that fig. 3 is merely an example of the electronic device 3 and is not limiting of the electronic device 3 and may include more or fewer components than shown, or different components.
The Processor 301 may be a central processing unit (Central Processing Unit, CPU) or other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.
The memory 302 may be an internal storage unit of the electronic device 3, for example, a hard disk or a memory of the electronic device 3. The memory 302 may also be an external storage device of the electronic device 3, for example, a plug-in hard disk provided on the electronic device 3, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. The memory 302 may also include both internal storage units and external storage devices of the electronic device 3. The memory 302 is used to store computer programs and other programs and data required by the electronic device.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit.
The integrated modules/units may be stored in a readable storage medium if implemented in the form of software functional units and sold or used as stand-alone products. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a readable storage medium, where the computer program may implement the steps of the method embodiments described above when executed by a processor. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The readable storage medium may include: any entity or device, recording medium, USB flash disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), electrical carrier signals, telecommunications signals, and software distribution media that can carry computer program code.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A cold station temperature control method, comprising:
acquiring operation parameters of cold station equipment and environment parameters corresponding to the operation of the cold station equipment;
Inputting the environmental parameters and the operation parameters into a trained cold energy demand prediction model, and predicting the cold energy demand of a cold station by using the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-checking and training at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction;
And acquiring a cold energy demand predicted value output by the cold energy demand predicted model, and controlling the temperature of the cold station based on the cold energy demand predicted value.
2. The method of claim 1, wherein before inputting the environmental parameter and the operating parameter into the trained cold demand prediction model, further comprising:
Acquiring a training sample set, and constructing an initial prediction model of each layer of prediction modules in the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm;
Training an initial prediction model of each layer of prediction modules in the multi-layer prediction modules based on the training sample set;
obtaining a prediction result output by a final layer of prediction module;
And constructing a loss function based on a prediction result output by the last layer of prediction module and a corresponding real label, obtaining a multi-layer prediction module after training when the loss value of the loss function is smaller than a preset value, and obtaining the cold demand prediction model based on the multi-layer prediction module after training.
3. The method of claim 2, wherein constructing an initial prediction model for each of the multi-layer prediction modules based on the training sample set and a preset machine learning algorithm comprises:
Dividing the training sample set into a training set and a verification set, and training a preset machine learning algorithm based on the training set and the verification set to obtain a plurality of intermediate prediction models;
Calculating a loss value between a predicted result and a true value of each sample in the verification set;
Calculating at least one of an average absolute loss, a mean square loss, and a root mean square loss for each intermediate prediction model based on the loss values;
Determining an evaluation result of the plurality of intermediate prediction models according to at least one of the average absolute loss, the mean square loss and the root mean square loss;
And selecting a preset number of intermediate prediction models from the plurality of intermediate prediction models as initial prediction models of each layer of prediction modules in the multi-layer prediction module according to the evaluation results of the plurality of intermediate prediction models.
4. The method of claim 2, wherein training each of the multi-layer prediction modules based on the training sample set comprises:
dividing the training sample set into K subsets, wherein each subset comprises operation parameters of the cold station equipment in different time periods and environment parameters corresponding to the operation of the cold station equipment;
For each initial prediction model of the first layer prediction module, K-1 subsets are sequentially used as training data, the rest subset is used as verification data, and K times of training and verification are carried out to obtain an initial prediction result corresponding to each initial prediction model;
and for the rest prediction modules except the first layer of prediction module, taking the initial prediction result obtained by the last layer of prediction module as the input of the next layer of prediction module, and repeatedly executing K times of cross validation training until the last layer of prediction module is trained.
5. The method of claim 2, wherein the acquiring a training sample set comprises:
Determining a device run time for each of the cold stations from historical operating parameters of the cold station device;
And when the equipment operation time is greater than a preset time threshold, taking the operation parameters of the cold station equipment with the equipment operation time greater than the preset time threshold and the corresponding environment parameters as the training sample set.
6. The method of claim 2, wherein prior to the acquiring the training sample set, further comprising:
And performing at least one of construction period operation characteristics, cutting off cold energy negative values, calculating accumulated cold energy in preset time, performing indoor temperature and humidity analysis and statistics, calculating wet bulb temperature, constructing indoor and outdoor temperature difference characteristics and cold source system temperature difference characteristics, performing characteristic processing on inclination characteristic processing and performing independent heat vector coding on classification variables by utilizing the operation parameters of the cold station equipment in the training sample set and the environment parameters corresponding to the operation of the cold station equipment.
7. The method of claim 1, wherein after controlling the cold station temperature based on the cold demand forecast, further comprising:
Storing the predicted value of the cold demand and the corresponding environmental parameter and the running parameter in a time sequence mode;
And selecting the latest data of preset days from the stored cold demand predicted values, the corresponding environment parameters and the corresponding operation parameters as a new training sample set to train the cold demand predicted model, obtaining an updated cold demand predicted model, and predicting the cold demand based on the updated cold demand predicted model.
8. A cold station temperature control apparatus, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is configured to acquire operation parameters of cold station equipment and acquire environment parameters corresponding to the operation of the cold station equipment;
The input module is configured to input the environmental parameters and the operation parameters into a trained cold energy demand prediction model, and the cold energy demand of the cold station is predicted by utilizing the cold energy demand prediction model, wherein the cold energy demand prediction model comprises a plurality of layers of prediction modules, the plurality of layers of prediction modules are obtained by cross-validation training of at least one initial prediction model of each layer of prediction module, the at least one initial prediction model of each layer of prediction module is used for generating at least one prediction result, and the at least one prediction result of each layer is used as the input of a next layer of prediction module for further prediction;
And the control module is configured to acquire the predicted value of the cold energy demand output by the cold energy demand prediction model and control the temperature of the cold station based on the predicted value of the cold energy demand.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410650038.7A CN118442676A (en) | 2024-05-23 | 2024-05-23 | Cold station temperature control method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410650038.7A CN118442676A (en) | 2024-05-23 | 2024-05-23 | Cold station temperature control method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118442676A true CN118442676A (en) | 2024-08-06 |
Family
ID=92314185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410650038.7A Pending CN118442676A (en) | 2024-05-23 | 2024-05-23 | Cold station temperature control method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118442676A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118729483A (en) * | 2024-09-02 | 2024-10-01 | 浩鲸云计算科技股份有限公司 | Energy-saving optimization control method for MIMO water-cooled air-conditioning system based on MPC |
-
2024
- 2024-05-23 CN CN202410650038.7A patent/CN118442676A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118729483A (en) * | 2024-09-02 | 2024-10-01 | 浩鲸云计算科技股份有限公司 | Energy-saving optimization control method for MIMO water-cooled air-conditioning system based on MPC |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117096504B (en) | Temperature control method and device, equipment and storage medium | |
| CN113255973A (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| US20200111174A1 (en) | Probabilistic Load Forecasting via Point Forecast Feature Integration | |
| KR102478684B1 (en) | Method for predicting energy consumption for using ensemble learning, and computing apparatus for performing the method | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN117891681A (en) | Storage device dynamic configuration method and system based on energy consumption prediction | |
| CN117540938B (en) | Integrated building energy consumption prediction method and system based on TD3 reinforcement learning optimization | |
| CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
| CN118442676A (en) | Cold station temperature control method and device, electronic equipment and readable storage medium | |
| CN118042786A (en) | Data center machine room environment regulation and control method and device and electronic equipment | |
| CN116757337B (en) | House construction progress prediction system based on artificial intelligence | |
| CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
| CN118195098A (en) | Heat load prediction method and system based on substation load and heat supply network hysteresis model | |
| CN118174294A (en) | Short-term power load prediction method | |
| CN115879190B (en) | Model construction method and device and building load prediction method and device | |
| CN118114916A (en) | New energy station power prediction technology assessment and scheduling method, system and device | |
| CN113723670A (en) | Photovoltaic power generation power short-term prediction method with variable time window | |
| CN114650190B (en) | Energy-saving method, system, terminal equipment and storage medium for data center network | |
| CN113780689B (en) | Energy router service life prediction method and device based on artificial intelligence | |
| CN118378761B (en) | Power grid data purification method, system, equipment and medium | |
| CN118822145B (en) | Power system energy supply prediction method and system based on transfer learning | |
| CN119310844A (en) | Control method and device of target equipment, electronic equipment and storage medium | |
| CN118412862B (en) | A regional wind power prediction method, device and server taking into account extreme weather | |
| CN119294828A (en) | Power grid look-ahead risk assessment method, device and medium | |
| CN117870008A (en) | Intelligent big data driven heat supply energy-saving optimization management method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |