Park energy management method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of energy management, and particularly relates to a park energy management method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining energy use information, inputting the energy use information into a trained LSTM model, obtaining an energy demand prediction result, and obtaining a park energy management result based on the energy demand prediction result. And generating equipment control information, wherein the equipment control information is used for controlling the work of the energy equipment. The method has the effects of improving the energy use efficiency and optimizing the energy management of the park.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to a campus energy management method, device, computer equipment and storage medium. Background Art

[0002] With the increasing energy consumption, effective energy management becomes particularly important. As an important place of energy consumption, the efficiency of energy management in the park directly affects the park's operating costs and environmental impact.

[0003] At present, traditional park energy management methods mostly rely on manual experience and simple information analysis, which makes it difficult to accurately predict energy demand and make corresponding adjustments. Therefore, how to achieve efficient management of park energy has become an urgent problem to be solved. Summary of the invention

[0004] In order to improve energy utilization efficiency and optimize the energy management of the park, the present application provides a park energy management method, device, computer equipment and storage medium.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A park energy management method, the park energy management method comprising: Obtain energy usage information; Inputting the energy usage information into the trained LSTM model to obtain energy demand prediction results; Based on the energy demand prediction result, device control information is generated, and the device control information is used to control the operation of energy devices.

[0006] By adopting the above technical solution, by obtaining energy usage information, it is possible to fully grasp the operating status and energy consumption of each energy equipment in the park, thereby providing a reliable data basis for subsequent energy demand forecasting, effectively improving the accuracy and comprehensiveness of energy monitoring, and thus improving the accuracy and efficiency of energy management. By inputting the energy usage information into the trained LSTM model, the long and short-term memory characteristics of the LSTM model can be used to deeply analyze and process the time series characteristics in the energy usage data, thereby effectively predicting the future energy demand change trend, greatly improving the accuracy and stability of energy demand forecasting, thereby reducing the waste of energy resources and improving energy utilization. By generating device control information based on the energy demand forecast results, it is possible to respond to changes in energy demand in a timely manner and adjust the operating status of energy equipment, thereby ensuring the balance of energy supply and demand, achieving efficient scheduling and intelligent management of energy, effectively reducing unnecessary energy consumption, and improving the economy of energy utilization. The device control information is used to control the work of energy equipment, and the working parameters of the equipment can be dynamically adjusted according to the real-time energy demand situation, thereby optimizing the operating efficiency of the equipment and reducing energy waste.

[0007] In a preferred example, the present application may be further configured as follows: the step of obtaining energy usage information further includes: Build the LSTM model.

[0008] By adopting the above technical solution, the long-term and short-term memory capabilities of the LSTM model can be fully utilized to effectively capture the time series characteristics in energy usage information, thereby more accurately predicting future energy demand changes. Through this prediction, the scheduling and allocation of energy resources can be optimized, thereby improving the intelligence level of the energy management system and reducing energy waste.

[0009] In a preferred example, the present application may be further configured as follows: the energy usage information is input into a trained LSTM model to obtain an energy demand prediction result, which includes: Acquire historical energy usage information, and divide the historical energy usage information into a training set and a test set in chronological order; Using the training set to train the LSTM model to obtain a trained LSTM model; The trained LSTM model is verified using the test set to obtain the trained LSTM model.

[0010] By adopting the above technical solutions, it is possible to ensure that the LSTM model obtains complete and accurate historical energy usage information before training. This chronological segmentation method can maintain the temporal nature of the data and avoid data confusion, thereby improving the stability of model training and the reliability of prediction results. The training method based on actual historical data enables the model to gradually learn and capture energy usage patterns, thereby improving the prediction accuracy of the model in practical applications. The trained LSTM model is fully verified through the test set. This verification method helps to evaluate the generalization ability and practical application effect of the model, thereby improving the adaptability and prediction accuracy of the model in different scenarios.

[0011] In a preferred example, the present application may be further configured as follows: the trained LSTM model is verified by using the test set to obtain the trained LSTM model, and then the following steps are included: The trained LSTM model is evaluated by a time series validation method to ensure the predictive ability of the trained LSTM model in practical applications.

[0012] By adopting the above technical solutions and taking advantage of the continuity and trend of time series data, the performance of the model in actual use scenarios can be more realistically reflected. Through this evaluation, the prediction errors and potential deviations of the model in different time periods can be effectively identified, thereby improving the adaptability and accuracy of the model in a dynamically changing environment, and ultimately ensuring that the prediction effect in actual energy management applications is more reliable and accurate.

[0013] In a preferred example, the present application may be further configured as follows: generating device control information based on the energy demand prediction result, wherein the device control information is used to control the operation of the energy device, including: Obtaining energy equipment that needs to be adjusted from the energy demand forecast result; For the energy device that needs to be adjusted, the device control information is formulated, and the device control information is used to control the operation of the energy device.

[0014] By adopting the above technical solution, the energy equipment that needs to be adjusted is obtained from the energy demand forecast results, which can ensure that the adjustment decision of the energy equipment is more accurate. By analyzing the energy demand forecast results, the equipment that may have demand changes in a specific time period is identified, thereby improving the targeted energy management. By formulating the equipment control information for the energy equipment that needs to be adjusted, the equipment control information is used to control the operation of the energy equipment, which can ensure that the operating status of the energy equipment matches the actual demand, thereby optimizing energy distribution and utilization efficiency.

[0015] In a preferred example, the present application may be further configured as follows: for the energy device that needs to be adjusted, the device control information is formulated, and the device control information is used to control the operation of the energy device, including: Obtaining an energy device operation mode through the energy demand prediction result and the energy usage information; According to the energy device operation mode, adjusting the energy device load distribution to obtain adjusted load distribution information; Based on the adjusted load distribution information, the device control information is obtained, and the device control information is used to control the operation of the energy device.

[0016] By adopting the above technical solution, the operation mode of energy equipment is generated through energy demand forecast results and energy usage information, and the load distribution of energy equipment is dynamically adjusted based on the mode, so as to obtain optimized equipment control information. This process ensures that energy equipment can automatically adjust and optimize operation under different load conditions, improves the response speed, work efficiency and control accuracy of the equipment, reduces energy waste and errors caused by human intervention, and finally achieves high efficiency and sustainability of energy management.

[0017] In a preferred example, the present application may be further configured as follows: the park energy management method further includes: According to the energy usage information, real-time operation information of energy equipment is obtained; Based on the real-time operation information of the energy equipment and the energy demand forecast result, the equipment control information is dynamically adjusted to optimize the stable operation of the energy equipment.

[0018] By adopting the above technical solution, the real-time operation information of energy equipment can be obtained according to the energy usage information, and the equipment control information can be dynamically adjusted in combination with the energy demand forecast results, thereby optimizing the stable operation of energy equipment. This can not only respond to the changing needs in actual use in a timely manner and ensure the continuous and efficient operation of the equipment under different load conditions, but also reduce the energy waste and system failure risks caused by equipment operation fluctuations, thereby improving the overall stability and reliability of the energy management system.

[0019] The second object of the invention is achieved by the following technical solutions: A park energy management device, wherein the park energy management device comprises: Energy information collection module, used to obtain energy usage information; An energy demand prediction module, used to input the energy usage information into the trained LSTM model to obtain an energy demand prediction result; The device control information generating module is used to generate device control information based on the energy demand prediction result, and the device control information is used to control the operation of the energy device.

[0020] By adopting the above technical solution, by obtaining energy usage information, it is possible to fully grasp the operating status and energy consumption of each energy equipment in the park, thereby providing a reliable data basis for subsequent energy demand forecasting, effectively improving the accuracy and comprehensiveness of energy monitoring, and thus improving the accuracy and efficiency of energy management. By inputting the energy usage information into the trained LSTM model, the long and short-term memory characteristics of the LSTM model can be used to deeply analyze and process the time series characteristics in the energy usage data, thereby effectively predicting the future energy demand change trend, greatly improving the accuracy and stability of energy demand forecasting, thereby reducing the waste of energy resources and improving energy utilization. By generating device control information based on the energy demand forecast results, it is possible to respond to changes in energy demand in a timely manner and adjust the operating status of energy equipment, thereby ensuring the balance of energy supply and demand, achieving efficient scheduling and intelligent management of energy, effectively reducing unnecessary energy consumption, and improving the economy of energy utilization. The device control information is used to control the work of energy equipment, and the working parameters of the equipment can be dynamically adjusted according to the real-time energy demand situation, thereby optimizing the operating efficiency of the equipment and reducing energy waste.

[0021] 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 campus energy management method when executing the computer program.

[0022] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned campus energy management method when executed by a processor.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. By acquiring energy usage information, the operating status and energy consumption of each energy device in the park can be fully understood, thereby providing a reliable data basis for subsequent energy demand forecasts, effectively improving the accuracy and comprehensiveness of energy monitoring, and thus improving the accuracy and efficiency of energy management. By inputting the energy usage information into the trained LSTM model, the long and short-term memory characteristics of the LSTM model can be used to deeply analyze and process the time series characteristics in the energy usage data, thereby effectively predicting future energy demand change trends, greatly improving the accuracy and stability of energy demand forecasts, thereby reducing the waste of energy resources and improving energy utilization. By generating equipment control information based on the energy demand forecast results, it is possible to respond to changes in energy demand in a timely manner and adjust the operating status of energy equipment, thereby ensuring the balance of energy supply and demand, achieving efficient energy scheduling and intelligent management, effectively reducing unnecessary energy consumption, and improving the economy of energy utilization. The equipment control information is used to control the operation of energy equipment, and the working parameters of the equipment can be dynamically adjusted according to the real-time energy demand situation, thereby optimizing the operating efficiency of the equipment and reducing energy waste; 2. By using the continuity and trend of time series data, the performance of the model in actual use scenarios can be more realistically reflected. Through this evaluation, the prediction errors and potential deviations of the model in different time periods can be effectively identified, thereby improving the adaptability and accuracy of the model in a dynamically changing environment, and ultimately ensuring that the prediction effect in actual energy management applications is more reliable and accurate; 3. Obtain real-time operation information of energy equipment based on energy usage information, and dynamically adjust equipment control information in combination with energy demand forecast results, thereby optimizing the stable operation of energy equipment. This not only enables timely response to changing needs in actual use and ensures that equipment continues to operate efficiently under different load conditions, but also reduces energy waste and system failure risks caused by equipment operation fluctuations, thereby improving the overall stability and reliability of the energy management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of a park energy management method in one embodiment of the present application; Figure 2 This is a flowchart of the implementation after step S10 in the park energy management method in one embodiment of the present application; Figure 3 This is a flowchart of the implementation before step S20 in the park energy management method in one embodiment of the present application; Figure 4 It is a flowchart of the implementation after step S23 in the park energy management method in one embodiment of the present application; Figure 5This is a flowchart for implementing step S30 in the park energy management method in one embodiment of the present application; Figure 6 It is a flowchart for implementing step S32 in the park energy management method in one embodiment of the present application; Figure 7 This is a flowchart of the implementation after step S30 in the park energy management method in one embodiment of the present application; Figure 8 This is a principle block diagram of a park energy management device in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described in detail below in conjunction with the accompanying drawings.

[0026] In one embodiment, if Figure 1 As shown, the present application discloses a campus energy management method, which specifically includes the following steps: S10: Obtain energy usage information.

[0027] In this embodiment, the energy usage information refers to information related to equipment performance and operating conditions collected from energy equipment in real time.

[0028] Specifically, energy usage information is obtained through the campus energy management database. Energy usage information includes: Energy consumption information: refers to the energy consumption of the equipment in a specific time period, such as electricity consumption (kilowatt-hours), heat (kilocalories) or other forms of energy usage. Equipment operating status refers to the current operating mode or status of the equipment, including the start, stop, standby or maintenance status of the equipment. Equipment load parameters refer to the load conditions of the equipment under different operating conditions, including the current load rate, maximum load capacity and operating pressure of the equipment. Operating time records refer to the cumulative operating time of the equipment, the number of starts and the duration of each operation.

[0029] Furthermore, the park energy management database refers to a centralized database used to store and manage various energy-related data within the park.

[0030] S20: Input the energy usage information into the trained LSTM model to obtain the energy demand prediction result.

[0031] In this embodiment, the trained LSTM model refers to a deep learning model trained by a long short-term memory network (LSTM) based on historical energy usage information. The energy demand forecast result refers to the energy demand or demand trend in the future time period obtained after analyzing the input energy usage information based on the trained LSTM model.

[0032] Specifically, standardize or normalize the energy usage information to meet the input requirements of the LSTM model. Organize the energy usage information into time series information to ensure the time order and consistency of the information. Divide the energy usage information into time windows of fixed length (for example, information from the past 24 hours), and each window is used as the input of the LSTM model. Extract prediction-related features from the energy usage information, such as energy consumption, load, operating status, etc., and use these features as input. Load the previously trained LSTM model and input the organized time series information into the LSTM model for prediction. The LSTM model generates a prediction result for future energy demand based on the input information.

[0033] S30: Generate device control information based on the energy demand prediction result, where the device control information is used to control the operation of the energy device.

[0034] In this embodiment, the device control information refers to instructions or parameters generated according to the energy demand prediction results, which are used to guide and control the operation of energy devices to ensure stable, efficient and energy-saving operation of the devices.

[0035] Specifically, according to the energy demand forecast results, decide whether to start or stop the operation of specific energy equipment. For example, when it is predicted that the energy demand will be low in the future, the system can generate instructions to stop certain equipment to save energy. According to the energy demand forecast results, switch the operation mode of the equipment, such as switching from high-load mode to energy-saving mode, to adapt to different demand levels. According to the predicted energy demand results, generate load distribution parameters to adjust the power output or operating load of energy equipment. For example, when future peak demand is predicted, the system can increase the operating load of the equipment in advance to ensure sufficient energy supply. Distribute the load among multiple devices and generate a device load distribution strategy to balance the operation of each device and avoid overloading or long-term inefficiency of some devices. According to the predicted energy demand, generate a specific equipment scheduling plan to determine the start and shutdown time of the equipment to ensure the balance of energy supply and demand. For example, shut down some equipment during off-peak hours to avoid energy waste.

[0036] Furthermore, the system refers to the park energy management system, which is used to comprehensively monitor, dispatch and optimize the operation of various energy equipment in the park. By collecting energy usage information in the park and combining it with the energy demand prediction model, the system can generate accurate equipment control information and achieve efficient allocation and use of energy.

[0037] In one embodiment, if Figure 2 As shown, after step S10, the energy usage information is obtained, and then the following steps are further included: S11: Build LSTM model.

[0038] In this embodiment, the LSTM model refers to a prediction model constructed by defining a model architecture, including an input layer, a hidden layer, and an output layer, setting parameters such as the number of neurons in each layer and the time step, and using a long short-term memory (LSTM) unit in a recurrent neural network (RNN).

[0039] Specifically, the input layer is defined to receive multidimensional time series information, such as device usage and power consumption. Next, a hidden layer containing 2-3 layers of LSTM units is set, each containing 64 to 256 units to capture the long-term and short-term dependencies of the information. The output layer is used to generate future energy demand forecasts. The weights and bias parameters of the model are randomly initialized, and then the Adam optimizer is used. An optimization algorithm based on adaptive learning rate combines the advantages of momentum and RMSprop. The learning rate can be dynamically adjusted during the model training process, thereby accelerating the convergence speed and improving the training stability of the model. Specifically, the hyperparameters of the Adam optimizer include the learning rate (such as 0.001), the exponential decay rate β1 of the first-order moment estimate (such as 0.9), and the exponential decay rate β2 of the second-order moment estimate (such as 0.999). And the mean square error loss function is optimized.

[0040] Furthermore, the random initialization selects the Xavier initialization method, which generates initial weights through uniform distribution or normal distribution to maintain the variance consistency of the network layer output and avoid the gradient vanishing or exploding problem. Adam optimizer refers to. The mean square error loss function refers to the square average of the error between the model prediction value and the true value.

[0041] In one embodiment, if Figure 3 As shown, before step S20, the energy usage information is input into the trained LSTM model to obtain the energy demand prediction result, which includes: S21: Obtain historical energy usage information, and divide the historical energy usage information into a training set and a test set in chronological order.

[0042] In this embodiment, historical energy usage information refers to detailed information generated and recorded by energy equipment during operation in the past year. Time sequence refers to arranging and processing information in the order of time when the energy usage information is recorded. The training set refers to an information set for model training divided from the historical energy usage information in time sequence. The test set refers to an information set for verifying model performance divided from the historical energy usage information in time sequence.

[0043] Specifically, the historical energy usage information is first sorted in chronological order, and then the sorted information set is divided into a training set and a test set in turn according to a predetermined division ratio.

[0044] Furthermore, the predetermined division ratio is 70% for the training set and 30% for the test set.

[0045] S22: Train the LSTM model using the training set to obtain a trained LSTM model.

[0046] In this embodiment, the trained LSTM model refers to an LSTM model that is obtained by inputting historical energy usage information in a training set into an initial LSTM model and, after multiple iterations of optimization, can more accurately predict future energy demand.

[0047] Specifically, the training set information arranged in chronological order is input into the LSTM model, and a batch of information is input each time for processing. The LSTM model processes time series information through its internal gating mechanism (input gate, forget gate, output gate). After the model generates the initial prediction value, the mean square error (MSE) is used as the loss function to calculate the error between the predicted value and the true value. The Adam optimizer is used for gradient descent to adjust the model parameters to minimize the loss function. The gradient descent is repeated many times until the prediction error of the model converges to a minimum level. After multiple iterative optimizations, the model parameters gradually converge, and the final LSTM model can effectively predict energy demand.

[0048] S23: Use the test set to verify the trained LSTM model to obtain the trained LSTM model.

[0049] Specifically, the energy usage information in the test set is input into the trained LSTM model, and the model predicts the test set information based on the time series patterns and correlations it has learned. After the model generates prediction results, these results are compared with the corresponding actual energy usage information in the test set to calculate the prediction error. The mean square error (MSE) is usually used as a metric to evaluate the performance of the model on the test set. By analyzing the prediction error, the accuracy and generalization ability of the model are evaluated. If the model has a low error on the test set, it means that the model can not only perform well on the training information, but also effectively predict on unseen information. This step is to confirm that the model does not overfit the training information and has the ability to be applied in actual scenarios. If it is found during the verification process that the model has too large an error on the test set, it may be necessary to return to the model training stage, adjust the model's hyperparameters or optimization strategy, and retrain and verify until the model has a low error on the test set. An LSTM model that has been verified and has an acceptable error range is a trained LSTM model.

[0050] In one embodiment, if Figure 4As shown, after step S23, the trained LSTM model is verified using the test set to obtain a trained LSTM model, and then the following steps are included: S231: Evaluate the trained LSTM model through the time series validation method to ensure the predictive ability of the trained LSTM model in practical applications.

[0051] In this embodiment, the time series verification method refers to evaluating the time series information of the trained LSTM model to verify the prediction ability of the model in practical applications.

[0052] Specifically, the historical energy usage information is divided into multiple consecutive time periods in chronological order, and each time period can be used as an independent validation set. The time periods can cover different seasons, holidays or other important time nodes to ensure that the model can accurately predict in various situations. At the beginning of each time period, the trained LSTM model is used to predict the information within that period. The prediction error of the model is calculated by comparing it with the actual energy usage information. This is done by sliding the window, that is, gradually moving the time period to verify the prediction accuracy of the model in different time periods, obtain the prediction results, and evaluate the prediction results by the mean square error (MSE). If the prediction error of the model is large in certain time periods, it is necessary to adjust the model's hyperparameters or retrain the model to improve its overall prediction ability.

[0053] In one embodiment, if Figure 5 As shown, in step S30, based on the energy demand prediction result, device control information is generated, and the device control information is used to control the operation of the energy device, including: S31: Obtain energy equipment that needs to be adjusted from energy demand forecast results.

[0054] In this embodiment, the energy equipment that needs to be adjusted refers to the energy equipment whose actual operating state deviates from the predicted demand according to the energy demand prediction result.

[0055] Specifically, first, the trained LSTM model is used to predict the energy demand for a period of time in the future and generate energy demand forecast results. The energy demand forecast results are compared with the actual operation information of the current energy equipment. The deviation between the actual operating status of each energy device and the predicted demand is calculated. If the deviation between the actual operating status of a device and the predicted result exceeds a preset threshold (for example, the actual consumption is much lower or higher than the predicted value), the device is marked as an energy device that needs to be adjusted.

[0056] Furthermore, the preset threshold refers to a standard or limit value used to determine whether the equipment needs to be adjusted when comparing the actual operating status of the energy equipment with the predicted results.

[0057] S32: For energy equipment that needs to be adjusted, equipment control information is formulated, and the equipment control information is used to control the operation of the energy equipment.

[0058] Specifically, the current operating status of the energy equipment that needs to be adjusted is monitored and analyzed in real time, including but not limited to parameters such as energy consumption, output efficiency, and workload. This information is used to accurately evaluate the gap between the actual performance of the equipment and the energy demand forecast results. According to the energy demand forecast results, the target parameters for equipment operation are set, such as the target energy consumption level, the expected output power, etc. According to the evaluation results and the set adjustment goals, a specific control strategy is formulated. The control strategy includes adjusting the operating mode of the equipment, changing the load distribution of the equipment, modifying the working time period or frequency of the equipment, etc. The above control strategy is converted into equipment control information, that is, specific instructions or parameter configurations. The equipment control information may include adjusting power output, changing the operating mode, reconfiguring the equipment's working schedule, etc. The generated equipment control information is sent to the energy equipment for execution.

[0059] In one embodiment, if Figure 6 As shown, in step S32, the energy equipment operation mode is obtained through the energy demand prediction result and the energy usage information; S321: Adjust the load distribution of the energy equipment according to the operation mode of the energy equipment to obtain adjusted load distribution information.

[0060] In this embodiment, the adjusted load distribution information refers to specific control information obtained after the workload of the energy device is redistributed according to the operation mode of the energy device.

[0061] Specifically, the current working status and load level of each energy device are monitored and recorded, including its power output, operating time, and operating efficiency. This information can reflect the load situation of the device in actual operation and its gap with the expected load. Next, the actual operation information is compared with the energy demand forecast results to evaluate whether the current load distribution can meet future energy needs. It will analyze whether the equipment has problems such as overload, idleness or load imbalance, and formulate corresponding adjustment strategies based on these problems. The formulation of the adjustment strategy includes determining the optimal load distribution for each device to provide sufficient energy during peak energy demand periods or reduce unnecessary energy consumption during low demand periods. Finally, the adjusted load distribution information is generated, which includes the new load level of each device, the adjusted operating period, and the power output setting. The adjusted load distribution information is used to reconfigure the equipment operating parameters to optimize the overall energy efficiency and equipment operation stability.

[0062] S322: Based on the adjusted load distribution information, obtain device control information, where the device control information is used to control the operation of the energy device.

[0063] Specifically, a specific device control strategy is formulated based on the adjusted load distribution information. The load distribution information usually includes the amount of load that each energy device needs to bear in different time periods. Based on this information, the control strategy will specify the operating parameters of each device in detail, such as power settings, operating hours, and load distribution. The formulation of the control strategy needs to take into account the working characteristics, energy efficiency, and optimization goals of the equipment. For example, if the adjusted load distribution information indicates that the load demand of a certain device increases during a certain period of time, the power output of the device should be adjusted to a higher level accordingly, and the load of other devices may need to be reduced to maintain the overall balance of the system. The device control information is usually transmitted to the energy management system or directly to the energy device in the form of control instructions. These control instructions will include specific operating commands, such as start-stop signals, power adjustment instructions, etc. Finally, the device control information will be sent to each energy device through the control system to achieve precise control of the equipment and ensure the efficient operation of the energy system and the balanced management of the load.

[0064] In one embodiment, if Figure 7 As shown, after step S30, the campus energy management method further includes: S40: Obtaining real-time operation information of energy equipment according to the energy usage information.

[0065] In this embodiment, the real-time operation information of the energy device is various information about the current operation status of the energy device collected and recorded in real time.

[0066] Specifically, real-time operation information of energy equipment includes, but is not limited to: real-time equipment status information, such as the switch status of the equipment (on or off), operation mode (normal operation, standby or fault mode), etc. Real-time performance information, including the real-time power consumption, current, voltage, load and other performance indicators of the equipment. Real-time environmental information, such as the temperature, humidity and other environmental conditions around the equipment, which may affect the operating efficiency and stability of the equipment. Real-time equipment fault information, including fault codes, alarm status, abnormal logs, etc., is used to identify whether the equipment has abnormal operation or faults. Real-time operation records, equipment operation history records, such as start-up time, downtime, operation adjustment records, etc.

[0067] S50: Based on the real-time operation information of the energy equipment and the energy demand forecast results, dynamically adjust the equipment control information to optimize the stable operation of the energy equipment.

[0068] Specifically, the operating status of energy equipment is monitored in real time to obtain the current equipment performance information and operation information. Equipment performance information and operation information include equipment power consumption, current, voltage, operating mode and environmental conditions. Then, these real-time operating information are comprehensively analyzed with the energy demand forecast results. The energy demand forecast results provide the expected energy demand in the future time period, while the real-time operating information reflects the current equipment status. By comparing the predicted demand with the actual equipment operating status, deviations and potential problems in equipment operation are identified. Based on the identification of deviations and potential problems in equipment operation, dynamic adjustment strategies are formulated, including adjusting the equipment's operating load, optimizing energy consumption distribution or modifying the operating mode to ensure that the equipment maintains a stable and efficient operating state while meeting the expected energy demand.

[0069] 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.

[0070] In one embodiment, a park energy management device is provided, and the park energy management device corresponds one-to-one to the park energy management method in the above embodiment. Figure 8 As shown, the park energy management device includes an energy information acquisition module, an energy demand prediction module and an equipment control information generation module. The detailed description of each functional module is as follows: Energy information collection module, used to obtain energy usage information; The energy demand prediction module is used to input energy usage information into the trained LSTM model to obtain energy demand prediction results; The device control information generation module is used to generate device control information based on the energy demand prediction results, and the device control information is used to control the operation of energy equipment.

[0071] Optionally, the energy information collection module includes: Model building module, used to build LSTM model.

[0072] Optionally, the energy demand forecasting module then includes: An information sorting module is used to obtain historical energy usage information and divide the historical energy usage information into a training set and a test set in chronological order; The training module is used to train the LSTM model using the training set to obtain the trained LSTM model; The verification module is used to verify the trained LSTM model using the test set to obtain a trained LSTM model.

[0073] Optionally, the authentication module is followed by: The time series validation module is used to evaluate the trained LSTM model through the time series validation method to ensure the predictive ability of the trained LSTM model in practical applications.

[0074] Optionally, the device control information generation module includes: The energy equipment adjustment submodule is used to obtain the energy equipment that needs to be adjusted from the energy demand forecast results; The device control information submodule is used to formulate device control information for energy devices that need to be adjusted. The device control information is used to control the operation of the energy devices.

[0075] Optionally, the device control information submodule includes: An operation mode unit, used to obtain the operation mode of energy equipment through energy demand prediction results and energy usage information; A load distribution information unit, used to adjust the load distribution of energy equipment according to the operation mode of the energy equipment, and obtain the adjusted load distribution information; The control submodule is used to obtain device control information based on the adjusted load distribution information, and the device control information is used to control the operation of the energy device.

[0076] Optionally, the device control information generation module then includes: The equipment operation module is used to obtain the real-time operation information of energy equipment according to the energy usage information; The dynamic adjustment module is used to dynamically adjust the equipment control information based on the real-time operation information of the energy equipment and the energy demand forecast results to optimize the stable operation of the energy equipment.

[0077] For the specific definition of the park energy management device, please refer to the definition of the park energy management method above, which will not be repeated here. Each module in the above-mentioned park energy management device 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.

[0078] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and an information library 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 an information library. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The information library of the computer device is used for the campus energy management database. 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, a campus energy management method is implemented.

[0079] 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: Obtain energy usage information; Input the energy usage information into the trained LSTM model to obtain the energy demand forecast result; Based on the energy demand forecast results, device control information is generated, and the device control information is used to control the operation of energy devices.

[0080] 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: Obtain energy usage information; Input the energy usage information into the trained LSTM model to obtain the energy demand forecast result; Based on the energy demand forecast results, device control information is generated, and the device control information is used to control the operation of energy devices.

[0081] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented 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, information library 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. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double information 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), etc.

[0082] Those skilled in the art can clearly understand that for the convenience and simplicity 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 device can be divided into different functional units or modules to complete all or part of the functions described above.

[0083] 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. A park energy management method, characterized in that: The park energy management method comprises: Obtain energy usage information; Inputting the energy usage information into the trained LSTM model to obtain energy demand prediction results; Based on the energy demand prediction result, device control information is generated, and the device control information is used to control the operation of energy devices.

2. The park energy management method according to claim 1, characterized in that: The obtaining of energy usage information further includes: Build the LSTM model.

3. The park energy management method according to claim 1, characterized in that: The energy usage information is input into the trained LSTM model to obtain the energy demand prediction result, which includes: Acquire historical energy usage information, and divide the historical energy usage information into a training set and a test set in chronological order; Using the training set to train the LSTM model to obtain a trained LSTM model; The trained LSTM model is verified using the test set to obtain the trained LSTM model.

4. The park energy management method according to claim 2, characterized in that: The trained LSTM model is verified by using the test set to obtain the trained LSTM model, and then the following steps are included: The trained LSTM model is evaluated by a time series validation method to ensure the predictive ability of the trained LSTM model in practical applications.

5. The park energy management method according to claim 1, characterized in that: The generating of device control information based on the energy demand prediction result, wherein the device control information is used to control the operation of the energy device, includes: Obtaining energy equipment that needs to be adjusted from the energy demand forecast result; For the energy device that needs to be adjusted, the device control information is formulated, and the device control information is used to control the operation of the energy device.

6. The park energy management method according to claim 5, characterized in that: The step of formulating the device control information for the energy device that needs to be adjusted, wherein the device control information is used to control the operation of the energy device, includes: Obtaining an energy device operation mode through the energy demand prediction result and the energy usage information; According to the energy device operation mode, adjusting the energy device load distribution to obtain adjusted load distribution information; Based on the adjusted load distribution information, the device control information is obtained, and the device control information is used to control the operation of the energy device.

7. The park energy management method according to claim 1, characterized in that: The park energy management method further includes: According to the energy usage information, real-time operation information of energy equipment is obtained; Based on the real-time operation information of the energy equipment and the energy demand forecast result, the equipment control information is dynamically adjusted to optimize the stable operation of the energy equipment.

8. A park energy management device, characterized in that: The park energy management device comprises: Energy information collection module, used to obtain energy equipment usage information; An energy demand prediction module, used to input the energy usage information into the trained LSTM model to obtain an energy demand prediction result; The device control information generating module is used to generate device control information based on the energy demand prediction result, and the device control information is used to control the operation of the energy device.

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 campus energy management method as described in any one of claims 1 to 7 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 the campus energy management method as described in any one of claims 1 to 7 are implemented.

Images