Energy optimization scheduling method and system, terminal and storage medium

Abstract

The invention belongs to the technical field of Internet, and particularly relates to an energy optimization scheduling method and system, a terminal and a storage medium, and the method comprises the steps: collecting real-time energy data, equipment state information and environment data of energy consumption equipment in a park; processing the real-time energy data, the equipment state information and the environment data by adopting a multi-source data fusion technology to obtain a park data set so as to generate a uniform data input format; obtaining actual demand data of the park, inputting the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtaining prediction results of the energy demand and the equipment health state of the park at the next moment; and adjusting the operation mode and parameter of the corresponding equipment based on the prediction result of the energy demand and the equipment health state of the park at the next moment. The method has the effect of improving the energy utilization rate of the park.

Description

Technical Field

[0001] The present application relates to the technical field of the Internet, and in particular to an energy optimization scheduling method, system, terminal and storage medium. Background Art

[0002] At present, with the development of intelligent energy management, more and more parks and enterprises have begun to pay attention to the optimization and scheduling of energy. At present, there are some energy management systems on the market that can analyze and schedule based on real-time monitored energy data. However, these systems mostly use traditional control algorithms, which makes it difficult to achieve accurate and efficient energy management.

[0003] The above-mentioned existing technical solutions have the following defects: the existing technology lacks intelligent scheduling strategies and control algorithms, and cannot be dynamically adjusted according to real-time energy demand and equipment status, thereby causing energy waste, so there is room for improvement. Summary of the invention

[0004] In order to improve the energy utilization rate of the park, the present application provides an energy optimization scheduling method, system, terminal and storage medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: An energy optimization scheduling method, the energy optimization scheduling method comprising: Collect real-time energy data, equipment status information, and environmental data of energy-consuming equipment in the park; Using multi-source data fusion technology, the real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format; Acquire the actual demand data of the park, input the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; Based on the predicted results of the energy demand and equipment health status of the park at the next moment, the operation mode and parameters of the corresponding equipment are adjusted.

[0006] By adopting the above technical solution, by collecting the real-time energy data, equipment status information and environmental data of the energy-consuming equipment in the park, the energy usage and environmental conditions of the equipment in the park can be fully understood, providing a reliable data basis for subsequent data processing and optimization; by adopting multi-source data fusion technology, the real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format, which can effectively eliminate the differences and redundant information of the data sources, improve the integration and consistency of the data, and thus provide more accurate basic data for energy demand prediction and equipment health status assessment; by obtaining the actual demand data of the park, the park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, which can effectively predict the changes in the energy demand of the park and the changes in the equipment operation status, ensuring the stability of equipment operation and the efficiency of energy utilization; by adjusting the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment, the equipment operation status can be adjusted in real time according to actual needs, thereby improving energy utilization efficiency and equipment service life.

[0007] In a preferred example, the present application may be further configured as follows: the collection of real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park includes: Using sensors deployed on each energy-consuming device in the park, monitoring and recording the power consumption data, device temperature, workload, and operating time of the device; Environmental data including temperature, humidity, light intensity, and wind speed are collected by installing environmental monitoring equipment at different locations in the park; The collected real-time energy data, equipment status information and environmental data are transmitted to the central management system via a wireless network to ensure the real-time and accuracy of data transmission.

[0008] By adopting the above technical solution, by utilizing sensors deployed on various energy-consuming devices in the park to monitor and record the equipment's power consumption data, equipment temperature, workload and operating time, it is possible to comprehensively and meticulously monitor the equipment's energy consumption and operating status, and provide detailed equipment performance data; by installing environmental monitoring equipment at different locations in the park, environmental data including temperature, humidity, light intensity, and wind speed are collected, which can comprehensively capture environmental changes inside and outside the park and provide more extensive background information for equipment operating status analysis; by transmitting the collected real-time energy data, equipment status information, and environmental data to the central management system via a wireless network to ensure the real-time and accuracy of data transmission, it is possible to ensure the integrity and timeliness of data during transmission, thereby improving the response speed and decision-making accuracy of the entire system.

[0009] In a preferred example, the present application can be further configured as follows: the multi-source data fusion technology is used to process the real-time energy data, equipment status information and environmental data to obtain a park data set to generate a unified data input format including: The real-time energy data, equipment status information and environmental data are cleaned and standardized by a data preprocessing method to eliminate noise and redundant information to obtain preprocessed data; The preprocessed data is processed by adopting a multi-source data fusion algorithm based on Bayesian reasoning, and the energy data, equipment status information and environmental data at different time points are synchronized using time series data processing technology, so as to finally obtain the park data set.

[0010] By adopting the above technical solution, the real-time energy data, equipment status information and environmental data are cleaned and standardized through data preprocessing methods, noise and redundant information are eliminated, and preprocessed data are obtained, which can eliminate errors and inconsistencies before data analysis, thereby improving the accuracy and effectiveness of data processing; by adopting the multi-source data fusion algorithm of Bayesian reasoning, the preprocessed data is processed, and the energy data, equipment status information and environmental data at different time points are synchronized using time series data processing technology, and finally a park data set is obtained, which can establish connections between multi-dimensional data from different sources and at different times, ensure the timeliness and consistency of the data, thereby improving the effectiveness of overall data processing and decision support capabilities.

[0011] In a preferred example, the present application may be further configured as follows: before obtaining the actual demand data of the park, inputting the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtaining the prediction results of the energy demand and equipment health status of the park at the next moment, the energy optimization scheduling method further includes: Collecting historical energy data and historical equipment status data, and preprocessing the historical energy data and historical equipment status data to obtain a training set; An energy model is constructed based on a convolutional neural network and a long short-term memory network, the energy model is trained using the training set, and the trained energy model is iteratively optimized using a genetic algorithm to finally obtain the pre-trained energy model.

[0012] By adopting the above technical solution, by collecting historical energy data and historical equipment status data, and pre-processing the historical energy data and historical equipment status data to obtain a training set, it is possible to effectively integrate and process past data accumulation, and provide rich samples for the training of the energy model; by constructing an energy model based on a convolutional neural network and a long short-term memory network, using the training set to train the energy model, and using a genetic algorithm to iteratively optimize the trained energy model, finally a pre-trained energy model is obtained, which can construct an efficient prediction model with self-learning and self-adaptive capabilities, thereby improving the accuracy of energy demand and equipment health status prediction, and further optimizing the energy use and equipment management of the park.

[0013] In a preferred example, the present application can be further configured as follows: the actual demand data of the park is obtained, the park data set and the actual demand data of the park are input into a pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, including: According to the production plan, historical production data and equipment usage records of the park, the actual energy demand data of the park is obtained, and the actual energy demand data of the park includes the start-up and shutdown plan of the production equipment, the production process requirements and the expected output; The park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, so as to obtain the prediction results of the energy demand and equipment health status of the park at the next moment.

[0014] By adopting the above technical solution, the actual energy demand data of the park is obtained according to the production plan, historical production data and equipment usage records of the park. By analyzing and integrating production data of different dimensions, the actual energy demand status of the park can be accurately grasped, and real demand information can be provided for the prediction model. By inputting the park data set and the actual demand data of the park into the pre-trained energy model for prediction, the prediction results of the energy demand and equipment health status of the park at the next moment can be obtained. Advanced prediction technology can be used to accurately predict future energy demand and equipment status, thereby providing strong support for equipment scheduling and energy optimization of the park.

[0015] In a preferred example, the present application may be further configured as follows: the energy optimization scheduling method further includes: When the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, the prediction results are recorded and verified using blockchain technology to ensure the security and transparency of the data; Real-time data of the park when performing energy adjustment is acquired in real time, the real-time data is fed back to the pre-trained energy model, and the pre-trained energy model is adjusted to ensure the adaptability of the pre-trained model.

[0016] By adopting the above technical solution, when obtaining the prediction results of the park's energy demand and equipment health status at the next moment, the prediction results are recorded and verified using blockchain technology, which can ensure the immutability and transparency of the prediction result data, thereby improving the security and credibility of the data; by obtaining real-time data of the park when making energy adjustments in real time, the real-time data is fed back to the pre-trained energy model, and the pre-trained energy model is adjusted to ensure the adaptability of the pre-trained model, the prediction model can be dynamically adjusted according to actual conditions, and the accuracy and adaptability of the model can be continuously improved, thereby ensuring the flexibility and reliability of the system in actual operation.

[0017] The second object of the invention is achieved by the following technical solutions: An energy optimization scheduling system, comprising: The data collection module is used to collect real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park; A data processing module is used to process the real-time energy data, equipment status information and environmental data using multi-source data fusion technology to obtain a park data set to generate a unified data input format; A model prediction module is used to obtain the actual demand data of the park, input the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; The adjustment module is used to adjust the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment.

[0018] By adopting the above technical solution, by collecting the real-time energy data, equipment status information and environmental data of the energy-consuming equipment in the park, the energy usage and environmental conditions of the equipment in the park can be fully understood, providing a reliable data basis for subsequent data processing and optimization; by adopting multi-source data fusion technology, the real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format, which can effectively eliminate the differences and redundant information of the data sources, improve the integration and consistency of the data, and thus provide more accurate basic data for energy demand prediction and equipment health status assessment; by obtaining the actual demand data of the park, the park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, which can effectively predict the changes in the energy demand of the park and the changes in the equipment operation status, ensuring the stability of equipment operation and the efficiency of energy utilization; by adjusting the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment, the equipment operation status can be adjusted in real time according to actual needs, thereby improving energy utilization efficiency and equipment service life.

[0019] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned energy optimization scheduling method when executing the computer program.

[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned energy optimization scheduling method are implemented.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. By collecting real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park, the energy usage and environmental conditions of equipment in the park can be fully understood, providing a reliable data basis for subsequent data processing and optimization; by adopting multi-source data fusion technology, real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format, which can effectively eliminate the differences and redundant information of data sources, improve the integration and consistency of data, and thus provide more accurate basic data for energy demand forecasting and equipment health status assessment; 2. By obtaining the actual demand data of the park, the park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained. This can effectively predict the changes in the energy demand of the park and the changes in the equipment operation status, ensure the stability of equipment operation and the efficiency of energy utilization; by adjusting the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment, the equipment operation status can be adjusted in real time according to actual needs, thereby improving energy utilization efficiency and equipment service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of an energy optimization scheduling method in one embodiment of the present application; Figure 2 It is a flowchart for implementing step S10 in an energy optimization scheduling method in one embodiment of the present application; Figure 3 is a flowchart for implementing step S20 in an energy optimization scheduling method in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S30 in an energy optimization scheduling method in an embodiment of the present application; Figure 5 It is a flowchart for implementing step S30 in an energy optimization scheduling method in one embodiment of the present application; Figure 6 This is a flowchart of an implementation of an energy optimization scheduling method in an embodiment of the present application; Figure 7 This is a principle block diagram of an energy optimization scheduling system in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses an energy optimization scheduling method, which specifically includes the following steps: S10: Collect real-time energy data, equipment status information, and environmental data of energy-consuming equipment in the park.

[0025] Specifically, the system collects real-time data of various energy-consuming devices in the park, including energy consumption, equipment status information such as switch status, operating efficiency, etc., and environmental data such as temperature and humidity.

[0026] S20: Use multi-source data fusion technology to process real-time energy data, equipment status information and environmental data to obtain a park data set to generate a unified data input format.

[0027] Specifically, in order to create a unified data set that can be provided as input to the analysis model to ensure data consistency and availability, data fusion technology is used to integrate and process real-time data from different sources, such as energy data, equipment status, and environmental data. The processed data set is converted into a standardized format that is suitable for input into the energy prediction model.

[0028] S30: Acquire the actual demand data of the park, input the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment.

[0029] Specifically, the current or expected energy demand data of the park is collected, which may include energy usage forecasts for different time periods, energy demand of specific equipment, etc. The processed data set and actual demand data are input into a pre-trained energy forecasting model. This model uses machine learning algorithms, such as time series analysis and deep learning, to learn patterns in the data and make predictions. The energy model will output the energy demand forecast of the park at the next moment and the prediction results of the equipment health status. The energy demand forecast helps to understand the energy usage of the park in the future, and the equipment health status forecast can predict potential problems and maintenance needs of the equipment.

[0030] S40: Based on the predicted results of the energy demand and equipment health status of the park at the next moment, the operation mode and parameters of the corresponding equipment are adjusted.

[0031] Specifically, based on the prediction results, the system will automatically or provide suggestions to adjust the operating mode and parameters of the equipment to optimize energy efficiency and ensure that the equipment operates in the best condition. For example, if the prediction shows that a certain device is about to fail, the system may recommend reducing its load or arranging maintenance; if the energy demand is predicted to increase, the system may recommend increasing energy supply or adjusting the operation of other equipment.

[0032] By adopting the above technical solution, by collecting the real-time energy data, equipment status information and environmental data of the energy-consuming equipment in the park, the energy usage and environmental conditions of the equipment in the park can be fully understood, providing a reliable data basis for subsequent data processing and optimization; by adopting multi-source data fusion technology, the real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format, which can effectively eliminate the differences and redundant information of the data sources, improve the integration and consistency of the data, and thus provide more accurate basic data for energy demand prediction and equipment health status assessment; by obtaining the actual demand data of the park, the park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, which can effectively predict the changes in the energy demand of the park and the changes in the equipment operation status, ensuring the stability of equipment operation and the efficiency of energy utilization; by adjusting the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment, the equipment operation status can be adjusted in real time according to actual needs, thereby improving energy utilization efficiency and equipment service life.

[0033] In one embodiment, if Figure 2 As shown, in step S10, real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park are collected, specifically including: S11: Use sensors deployed on various energy-consuming devices in the campus to monitor and record the device's power consumption data, device temperature, workload, and operating time.

[0034] Specifically, sensors are installed on various energy-consuming devices within the park. These sensors can monitor and record key equipment parameters in real time, including: the amount of electricity consumed by the equipment, the temperature of the equipment during operation, the current workload or operating intensity of the equipment, and the total time the equipment is turned on and running.

[0035] S12: Environmental data including temperature, humidity, light intensity and wind speed are collected through environmental monitoring equipment installed at different locations in the park.

[0036] Specifically, environmental monitoring equipment is installed at different locations in the park to collect environmental data that may affect energy consumption, including: the thermal state of the environment, the energy demand that may affect air conditioning, heating and other systems, the moisture content in the air, the brightness of natural or artificial light, and the outdoor wind speed.

[0037] S13: The collected real-time energy data, equipment status information and environmental data are transmitted to the central management system via a wireless network to ensure the real-time and accuracy of data transmission.

[0038] Specifically, the collected real-time energy data, equipment status information and environmental data are transmitted to the central management system via the wireless network. Wireless transmission of data provides flexibility and convenience, ensuring that data can be sent from each monitoring point to the central management system in real time, which can be used for accurate analysis and decision-making.

[0039] In one embodiment, if Figure 3 As shown, in step S20, multi-source data fusion technology is used to process real-time energy data, equipment status information and environmental data to obtain a park data set to generate a unified data input format, specifically including: S21: The real-time energy data, equipment status information and environmental data are cleaned and standardized through data preprocessing methods to eliminate noise and redundant information and obtain preprocessed data.

[0040] Specifically, in order to improve the data quality and make it suitable for subsequent analysis and model training, real-time energy data, equipment status information and environmental data are preprocessed to remove erroneous, duplicate or incomplete records in the data set, convert data of different dimensions and magnitudes to the same standard, and reduce or remove random fluctuations and outliers in the data to improve the reliability of the data, ultimately obtaining preprocessed data.

[0041] S22: The multi-source data fusion algorithm based on Bayesian reasoning is used to process the preprocessed data, and the time series data processing technology is used to synchronize the energy data, equipment status information and environmental data at different time points, and finally the park data set is obtained.

[0042] Specifically, in multi-source data fusion, Bayesian reasoning can be used to combine information from different sensors or data sources to obtain more accurate and reliable results by considering prior knowledge and data uncertainty. Time series data processing technology can be used to synchronize, interpolate, smooth, and trend energy data, equipment status information, and environmental data at different time points to ultimately obtain a park data set.

[0043] In one embodiment, if Figure 4 As shown, before step S30, that is, obtaining the actual demand data of the park, inputting the park data set and the actual demand data of the park into the pre-trained energy model for prediction, and obtaining the prediction results of the energy demand and equipment health status of the park at the next moment, the energy optimization scheduling method also includes: S301: Collect historical energy data and historical equipment status data, and pre-process the historical energy data and historical equipment status data to obtain a training set.

[0044] Specifically, first, it is necessary to collect energy consumption data and equipment operating status data over a period of time. These data may include the usage of electricity, water, gas and other energy, as well as the switching status, operating efficiency, fault records and other information of the equipment, and preprocess the collected data, including cleaning data, standardizing or normalizing data, feature selection, etc. The preprocessed data is organized into a training set, which will be used to train the machine learning model.

[0045] S302: construct an energy model based on a convolutional neural network and a long short-term memory network, train the energy model using a training set, and iteratively optimize the trained energy model using a genetic algorithm, and finally obtain a pre-trained energy model.

[0046] Specifically, an energy model is constructed based on convolutional neural networks and long short-term memory networks. Convolutional neural networks are used to process data with obvious spatial structures, such as local pattern recognition in images or time series data. Long short-term memory networks can learn long-term dependencies and are suitable for processing and predicting time series data. The energy model is trained using a training set. During the training process, the model learns how to extract features from the input data and make predictions based on these features. Finally, a genetic algorithm is used to iteratively optimize the trained energy model and adjust the model's hyperparameters, such as the number of network layers, the number of neurons in the layer, the learning rate, etc., to improve the performance of the model and ultimately obtain a pre-trained energy model.

[0047] In one embodiment, if Figure 5 As shown, in step S30, the actual demand data of the park is obtained, and the park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, and the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, which specifically include: S31: According to the production plan, historical production data and equipment usage records of the park, the actual energy demand data of the park is obtained. The actual energy demand data of the park includes the start and stop plan of the production equipment, the production process requirements and the expected output.

[0048] Specifically, actual energy demand data is collected based on the park's production plan, historical production data, and equipment usage records. The actual energy demand data includes: when the equipment is started or shut down, the time that affects energy use, the specific requirements for energy type and amount at different process stages, and the expected production volume.

[0049] S32: Input the park data set and the park's actual demand data into a pre-trained energy model for prediction, and obtain the prediction results of the park's energy demand and equipment health status at the next moment.

[0050] Specifically, the actual energy demand data collected is integrated with the park data set previously collected and preprocessed through sensors, and the integrated data is provided as input to a pre-trained energy prediction model. The energy model analyzes and calculates the input data to predict the energy demand of the park at the next moment, including predicting energy consumption under specific production plans and process requirements. In addition to energy demand, the model also predicts the health status of the equipment, such as possible failures and maintenance needs. The prediction of equipment health status helps to arrange maintenance work in advance and reduce the risk of unexpected downtime. In one embodiment, if Figure 6 As shown, the energy optimization scheduling method also includes: S51: When obtaining the forecast results of the energy demand and equipment health status of the park at the next moment, blockchain technology is used to record and verify the forecast results to ensure the security and transparency of the data.

[0051] Specifically, when the forecast results of energy demand and equipment health status are generated, these results can be recorded on the blockchain. This can ensure the integrity and transparency of the forecast results. Once the data is recorded on the blockchain, it cannot be easily changed or deleted, ensuring the security and transparency of the data.

[0052] S52: Real-time data of the park when adjusting energy is obtained in real time, and the real-time data is fed back to a pre-trained energy model, and the pre-trained energy model is adjusted to ensure the adaptability of the pre-trained model.

[0053] Specifically, real-time data of the park is obtained when making energy adjustments. The collected real-time data is used as feedback and input into a pre-trained energy model. This feedback mechanism allows the model to learn the latest energy usage patterns and equipment responses, thereby improving the accuracy of the model. The pre-trained energy model is adjusted to ensure the adaptability of the pre-trained model.

[0054] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] In one embodiment, an energy optimization scheduling system is provided, and the energy optimization scheduling system corresponds one-to-one to an energy optimization scheduling method in the above embodiment. Figure 7 As shown, the energy optimization scheduling system includes a data collection module, a data processing module, a model prediction module and an adjustment module. The detailed description of each functional module is as follows: The data collection module is used to collect real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park.

[0056] The data processing module is used to process real-time energy data, equipment status information and environmental data using multi-source data fusion technology to obtain a park data set in order to generate a unified data input format.

[0057] The model prediction module is used to obtain the actual demand data of the park, input the park data set and the actual demand data of the park into the pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment.

[0058] The adjustment module is used to adjust the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment.

[0059] Optionally, the energy optimization scheduling system further includes: The verification module is used to record and verify the prediction results of the park's energy demand and equipment health status at the next moment using blockchain technology to ensure data security and transparency.

[0060] The model adjustment module is used to obtain real-time data when the park is making energy adjustments, feed the real-time data back to the pre-trained energy model, and adjust the pre-trained energy model to ensure the adaptability of the pre-trained model.

[0061] The historical data collection module is used to collect historical energy data and historical equipment status data, and pre-process the historical energy data and historical equipment status data to obtain a training set.

[0062] The model training module is used to build an energy model based on a convolutional neural network and a long short-term memory network, train the energy model using a training set, and iteratively optimize the trained energy model using a genetic algorithm to finally obtain a pre-trained energy model.

[0063] Optionally, the data collection module includes: The sensor detection submodule is used to monitor and record the power consumption data, device temperature, workload and operating time of the equipment using sensors deployed on various energy-consuming equipment in the park.

[0064] The environmental monitoring submodule is used to collect environmental data including temperature, humidity, light intensity, and wind speed through environmental monitoring equipment installed in different locations in the park.

[0065] The transmission submodule is used to transmit the collected real-time energy data, equipment status information and environmental data to the central management system through the wireless network to ensure the real-time and accuracy of data transmission.

[0066] Optionally, the data processing module includes: The preprocessing submodule is used to clean and standardize real-time energy data, equipment status information and environmental data through data preprocessing methods, eliminate noise and redundant information, and obtain preprocessed data.

[0067] The synchronization submodule is used to process the preprocessed data using a multi-source data fusion algorithm based on Bayesian reasoning, and synchronize the energy data, equipment status information, and environmental data at different time points using time series data processing technology, ultimately obtaining a park data set.

[0068] Optionally, the model prediction module includes: The actual data acquisition submodule is used to acquire the actual energy demand data of the park based on the production plan, historical production data and equipment usage records of the park. The actual energy demand data of the park includes the start and stop plan of production equipment, production process requirements and expected output.

[0069] The prediction submodule is used to input the park data set and the park's actual demand data into a pre-trained energy model for prediction, and obtain the prediction results of the park's energy demand and equipment health status at the next moment.

[0070] For the specific definition of an energy optimization scheduling system, please refer to the definition of an energy optimization scheduling method above, which will not be repeated here. Each module in the above-mentioned energy optimization scheduling system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0071] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to obtain historical data of the park. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an energy optimization scheduling method is implemented.

[0072] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Collect real-time energy data, equipment status information, and environmental data of energy-consuming equipment in the park; Adopt multi-source data fusion technology to process real-time energy data, equipment status information and environmental data to obtain park data collection and generate a unified data input format; Obtain the actual demand data of the park, input the park data set and the actual demand data of the park into the pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; Based on the predicted results of the park’s energy demand and equipment health status at the next moment, adjust the operating mode and parameters of the corresponding equipment.

[0073] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Collect real-time energy data, equipment status information, and environmental data of energy-consuming equipment in the park; Adopt multi-source data fusion technology to process real-time energy data, equipment status information and environmental data to obtain park data collection and generate a unified data input format; Obtain the actual demand data of the park, input the park data set and the actual demand data of the park into the pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; Based on the predicted results of the park’s energy demand and equipment health status at the next moment, adjust the operating mode and parameters of the corresponding equipment.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0075] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0076] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An energy optimization scheduling method, characterized in that: The energy optimization scheduling method comprises: Collect real-time energy data, equipment status information, and environmental data of energy-consuming equipment in the park; Using multi-source data fusion technology, the real-time energy data, equipment status information and environmental data are processed to obtain a park data set to generate a unified data input format; Acquire the actual demand data of the park, input the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; Based on the predicted results of the energy demand and equipment health status of the park at the next moment, the operation mode and parameters of the corresponding equipment are adjusted.

2. The energy optimization scheduling method according to claim 1, characterized in that: The real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park are collected, including: Using sensors deployed on each energy-consuming device in the park, monitoring and recording the power consumption data, device temperature, workload, and operating time of the device; Environmental data including temperature, humidity, light intensity, and wind speed are collected by installing environmental monitoring equipment at different locations in the park; The collected real-time energy data, equipment status information and environmental data are transmitted to the central management system via a wireless network to ensure the real-time and accuracy of data transmission.

3. The energy optimization scheduling method according to claim 2, characterized in that: The multi-source data fusion technology is used to process the real-time energy data, equipment status information and environmental data to obtain a park data set to generate a unified data input format including: The real-time energy data, equipment status information and environmental data are cleaned and standardized by a data preprocessing method to eliminate noise and redundant information to obtain preprocessed data; The preprocessed data is processed by adopting a multi-source data fusion algorithm based on Bayesian reasoning, and the energy data, equipment status information and environmental data at different time points are synchronized using time series data processing technology, so as to finally obtain the park data set.

4. The energy optimization scheduling method according to claim 1, characterized in that: Before obtaining the actual demand data of the park, inputting the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtaining the prediction result of the energy demand and equipment health status of the park at the next moment, the energy optimization scheduling method further includes: Collecting historical energy data and historical equipment status data, and preprocessing the historical energy data and historical equipment status data to obtain a training set; An energy model is constructed based on a convolutional neural network and a long short-term memory network, the energy model is trained using the training set, and the trained energy model is iteratively optimized using a genetic algorithm to finally obtain the pre-trained energy model.

5. The energy optimization scheduling method according to claim 4, characterized in that: The obtaining of the actual demand data of the park, inputting the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtaining the prediction results of the energy demand and equipment health status of the park at the next moment include: According to the production plan, historical production data and equipment usage records of the park, the actual energy demand data of the park is obtained, and the actual energy demand data of the park includes the start-up and shutdown plan of the production equipment, the production process requirements and the expected output; The park data set and the actual demand data of the park are input into the pre-trained energy model for prediction, so as to obtain the prediction results of the energy demand and equipment health status of the park at the next moment.

6. The energy optimization scheduling method according to claim 5, characterized in that: The energy optimization scheduling method further includes: When the prediction results of the energy demand and equipment health status of the park at the next moment are obtained, the prediction results are recorded and verified using blockchain technology to ensure the security and transparency of the data; Real-time data of the park when performing energy adjustment is acquired in real time, the real-time data is fed back to the pre-trained energy model, and the pre-trained energy model is adjusted to ensure the adaptability of the pre-trained model.

7. An energy optimization scheduling system, characterized in that: The energy optimization scheduling system comprises: The data collection module is used to collect real-time energy data, equipment status information and environmental data of energy-consuming equipment in the park; A data processing module is used to process the real-time energy data, equipment status information and environmental data using multi-source data fusion technology to obtain a park data set to generate a unified data input format; A model prediction module is used to obtain the actual demand data of the park, input the park data set and the actual demand data of the park into a pre-trained energy model for prediction, and obtain the prediction results of the energy demand and equipment health status of the park at the next moment; The adjustment module is used to adjust the operation mode and parameters of the corresponding equipment based on the prediction results of the energy demand and equipment health status of the park at the next moment.

8. The energy optimization scheduling system according to claim 7, characterized in that: The energy optimization scheduling system further includes: A verification module is used to record and verify the prediction results of the energy demand and equipment health status of the park at the next moment by using blockchain technology to ensure the security and transparency of the data; The model adjustment module is used to obtain real-time data of the park when performing energy adjustment, feed the real-time data back to the pre-trained energy model, and adjust the pre-trained energy model to ensure the adaptability of the pre-trained model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the energy optimization scheduling method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of an energy optimization scheduling method as described in any one of claims 1 to 6 are implemented.

Images