Power equipment control method and device and nonvolatile storage medium
By collecting data from power equipment within the industrial park and using edge computing and cloud-based predictive models to generate optimization instructions, the problem of overall control over power equipment within the park has been solved, achieving efficient energy management and optimized system operation.
Patent Information
- Application Number
- CN202511070953.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-31
- Publication Date
- 2025-11-04
AI Technical Summary
In medium and large industrial parks, it is difficult to manage multiple power devices as a whole, resulting in energy waste and poor management. Especially when a high proportion of new energy sources are connected, data processing efficiency is low, making it difficult to track load fluctuations in real time, which affects the economic benefits and operational efficiency of the power system.
By collecting target power data and environmental parameters of power equipment within the park, data aggregation is performed using edge computing terminals, and future power data is predicted in the cloud based on machine learning models to generate optimization instructions that guide the adjustment of power equipment, thereby achieving hierarchical control.
This enables hierarchical control of the park's power equipment, reduces energy waste, improves management efficiency, and ensures the economical, reliable, and environmentally friendly operation of the power system.
Smart Images

Figure CN120896333A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power equipment control, in particular to a power equipment control method and device and a nonvolatile storage medium. BACKGROUND
[0002] In a medium-large industrial park, flexible loads mainly include building refrigeration and heating equipment, electric production equipment such as electric forklift charging loads, and electrochemical energy storage equipment. Among them, the air conditioning load of the building is limited by environmental temperature control and has low flexibility; with the decrease of electrochemical energy storage cost, it is feasible to carry out economic scheduling as a flexible load, which helps to balance new energy power generation and load demand. In addition, most of the photovoltaic projects in the park operate in the mode of "self-use, surplus on-grid", when the photovoltaic output is greater than the internal load of the park during the photovoltaic power generation peak period, the excess power needs to be sent back to the power grid, which not only causes waste of resources, but also affects the economic benefit and operation efficiency of the power system.
[0003] At present, when dealing with large-scale and high-proportion new energy access, there are technical problems of low data processing efficiency, difficulty in real-time tracking of load fluctuations, reduced reliability, difficulty in meeting the requirements of the power system for flexibility, resulting in energy waste and poor management effect.
[0004] At present, there is no effective solution to the above problems. SUMMARY
[0005] The embodiments of the present application provide a power equipment control method, device and nonvolatile storage medium to at least solve the technical problems of energy waste and poor management effect caused by the difficulty in overall management and control of multiple power equipment in the park.
[0006] According to an aspect of an embodiment of the present application, a power equipment control method is provided, comprising: collecting target power data and target environmental parameters corresponding to power equipment in a target park; based on an edge computing terminal, aggregating the target power data and the target environmental parameters to obtain aggregated data; based on a cloud, predicting future target power data of the power equipment according to the aggregated data; based on the cloud, generating an optimization instruction according to the future target power data and a preset power optimization target; and issuing the optimization instruction to the power equipment.
[0007] Optionally, the target power data and the target environment parameter corresponding to the power equipment in the target park are collected, including: collecting initial power data and initial environment parameter corresponding to the power equipment based on a preset time window; mapping the initial power data and the initial environment parameter to a time sequence corresponding to the time window to determine a power data sequence and an environment parameter sequence; detecting whether there is a missing value in the power data sequence and the environment parameter sequence; in a case where there is a missing value in the power data sequence and / or the environment parameter sequence, estimating the missing value based on a linear difference method to determine the target power data and the target environment parameter.
[0008] Optionally, the target power data and the target environment parameter are aggregated based on the edge computing terminal to obtain aggregated data, including: determining a target power data statistic and a target environment parameter statistic by calculating respective statistics of the target power data and the target environment parameter; determining a correlation between the target power data and the target environment parameter based on the target power data statistic and the target environment parameter statistic; and determining the aggregated data based on the target power data, the target environment parameter and the correlation.
[0009] Optionally, the future target power data of the power equipment is predicted based on the cloud and the aggregated data, including: inputting the aggregated data into a preset machine learning model in the cloud to output the future target power data, wherein the machine learning model is trained by using historical target environment parameters and historical target power data.
[0010] Optionally, the optimization instruction is generated based on the cloud and the future target power data and a preset power optimization target, including: establishing an initial optimization model and an objective function based on the power optimization target in the cloud; adjusting parameters in the optimization model based on the future target power data to obtain a target optimization model; solving the target optimization model to obtain an optimization parameter corresponding to the power equipment; and generating the optimization instruction based on the optimization parameter corresponding to the power equipment.
[0011] Optionally, in a case where the power equipment receives the optimization instruction, the optimized power data of the power equipment is monitored; and an optimization result of the target park is determined based on the optimized power data.
[0012] According to another aspect of the embodiment of the present application, a control device of a power equipment is also provided, including: a collection module configured to collect target power data and target environment parameter corresponding to the power equipment in a target park; an aggregation module configured to aggregate the target power data and the target environment parameter based on an edge computing terminal to obtain aggregated data; a prediction module configured to predict future target power data of the power equipment based on the cloud and the aggregated data; a generation module configured to generate an optimization instruction based on the cloud and the future target power data and a preset power optimization target; and a delivery module configured to deliver the optimization instruction to the power equipment.
[0013] According to a further aspect of the embodiments of the present application, a nonvolatile storage medium is also provided, which comprises a stored program, wherein the program, when executed, controls a device in which the nonvolatile storage medium is located to perform the power device control method in any one of the above.
[0014] According to a further aspect of the embodiments of the present application, a computer device is also provided, which comprises a processor configured to execute a program, wherein the program, when executed, performs the power device control method in any one of the above.
[0015] According to a further aspect of the embodiments of the present application, a computer program product is also provided, which comprises a computer program configured to, when executed by a processor, implement the power device control method in any one of the above.
[0016] In the embodiments of the present application, the power device control method is adopted, and the target power data and the target environment parameters corresponding to the power device in the target park are collected. The target power data and the target environment parameters are aggregated based on an edge computing terminal to obtain aggregated data. The future target power data of the power device is predicted based on the cloud and the aggregated data. The optimization instruction is generated based on the cloud and the future target power data and a preset power optimization target. The optimization instruction is sent to the power device, so as to achieve the purpose of hierarchical control of the power device in the park, thereby achieving the technical effects of reducing energy waste and improving management effect, and further solving the technical problems of energy waste and poor management effect caused by the difficulty in overall management of multiple power devices in the park. BRIEF DESCRIPTION OF DRAWINGS
[0017] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:
[0018] Figure 1 Fig. 1 shows a hardware structure block diagram of a computer terminal for implementing the power device control method;
[0019] Figure 2 Fig. 2 is a flow diagram of the power device control method according to an embodiment of the present application;
[0020] Figure 3 Fig. 3 is a structure block diagram of the power device control device according to an embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts should fall within the scope of the present application.
[0022] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0023] According to the embodiments of the present application, a method embodiment of a control method of a power device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.
[0024] The method embodiment provided by the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 A hardware structure block diagram of a computer terminal for implementing a control method of a power device is shown. As shown in Figure 1 , the computer terminal 10 can include one or more processors (the processor can include but is not limited to a microprocessor MCU or a programmable logic device FPGA processing device) (shown in 102a, 102b,..., 102n), a memory 104 for storing data. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 can include more or fewer components than those shown in Figure 1 , or have different structures from those shown inFigure 1 different configurations.
[0025] It should be noted that the one or more processors and / or other data processing circuitry described above can be referred to herein generally as "data processing circuitry". The data processing circuitry can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuitry can be a single standalone processing module, or incorporated in whole or in part within any one of the other elements of the computer terminal 10. As referred to in embodiments of the present application, the data processing circuitry acts as a processor to control, for example, the selection of the variable resistance terminal path in connection with the interface.
[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage means corresponding to the control method of the power equipment in embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, i.e. implements the control method of the power equipment of the application program described above. The memory 104 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory disposed remotely with respect to the processor, which can be connected to the computer terminal 10 through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0027] The display can be, for example, a touch screen type liquid crystal display (LCD) that can enable a user to interact with the user interface of the computer terminal 10.
[0028] Figure 2 is a flowchart of the control method of the power equipment according to embodiments of the present application, as shown in Figure 2 The method comprises the following steps:
[0029] In step S202, target power data and target environmental parameters corresponding to the target power equipment in the target park are collected.
[0030] In this step, data can be collected from the power equipment and stored in the local database, which can include real-time state data such as current power, voltage, current, frequency, etc. Environmental parameters closely related to the performance of the power equipment, such as temperature, humidity, light intensity, wind speed, etc., are determined, and an ideal operating range is set. Install sensors suitable for measuring target environmental parameters at key locations, collect environmental parameters through environmental sensors, and store them in the local database.
[0031] Step S204, based on the edge computing terminal, the target power data and the target environmental parameters are aggregated to obtain aggregated data.
[0032] In this step, the edge computing terminal receives real-time power data and environmental parameters, which typically include voltage, current, power, frequency, as well as temperature, humidity, and light intensity. The integrity and validity of the received data can be checked to exclude invalid or damaged data packets. Clear outliers such as voltage and current readings outside the normal range, and unreasonable jumps in environmental parameters can be removed. The timestamps of all data can be converted to a unified time reference to ensure the temporal consistency of the data. Then the time interval for aggregation can be determined, such as every 5 minutes, every hour, or every day. For power data, calculate the average, maximum, minimum, and total of each time window. For environmental parameters, analyze trends such as temperature and humidity changes, and periodic fluctuations in light intensity. Environmental parameters can also be correlated with power data, for example, the trend of increased power demand when temperature rises. In addition to considering time series, data can also be aggregated by device type, geographic location, or functional area to provide a more detailed analysis perspective.
[0033] To reduce network bandwidth occupancy, data compression techniques can be used to compress aggregated data. Before data transmission, encryption algorithms are used to encrypt data to ensure data security. According to the network environment, select appropriate communication protocols (such as MQTT, HTTP / HTTPS, COAP, etc.) to transmit aggregated data to the cloud data center. Through the network, upload the encrypted and compressed data packets to the cloud platform for further analysis and decision-making.
[0034] Through the above steps, the edge computing terminal can effectively aggregate target power data and target environmental parameters to generate aggregated data that helps system management and decision-making, while ensuring data quality and communication security. This data aggregation method fully utilizes the local processing power and low latency characteristics of edge computing, providing key support for the optimized operation of the power system and the achievement of environmental protection goals.
[0035] Step S206, based on the cloud, according to the aggregated data, predict the future target power data of the power equipment.
[0036] In this step, the aggregated power data and environmental parameter data received from the edge computing terminal are imported into the data warehouse or database of the cloud platform. The imported data can be cleaned again, including checking data integrity, consistency, and processing any noise or outliers that may exist. Features that help prediction are extracted from the aggregated data, including historical power data trends, environmental parameter changes, device status information, timestamps (date, time, season, holidays, etc.). Statistical methods or machine learning techniques are used to determine which features are most critical to predicting target power data, and irrelevant or redundant features are removed to improve the efficiency and accuracy of the prediction model.
[0037] According to the time series characteristics of the power data, suitable time series prediction models are selected, such as ARIMA, SARIMA, Prophet, LSTM (Long Short-Term Memory Network), etc. The selected prediction model is trained using the historical aggregated data set, and the model parameters are adjusted to achieve the best prediction performance. Using the trained prediction model, based on the current aggregated data and environmental parameters, the target power data in the future period is predicted. During the prediction process, external factors that may affect power demand, such as weather forecasts, holidays, special events, etc., are considered to improve prediction accuracy.
[0038] Through the above steps, the cloud platform can use the rich information of aggregated data and powerful computing resources to accurately predict the future target power data of power equipment, providing decision-making basis for intelligent scheduling and optimal operation of the power system.
[0039] Step S208, based on the cloud, generates optimization instructions based on the future target power data and the preset power optimization target.
[0040] In this step, the power optimization target can be defined first, such as economic targets, such as minimizing power costs, optimizing power purchase and sale strategies. Reliability targets to ensure stable operation of the power system and avoid power overload or underload. Environmental protection targets to maximize the use of renewable energy sources such as photovoltaic and wind power to reduce carbon emissions. Safety targets to monitor and maintain power equipment within the safe operating parameter range.
[0041] Analyze the trend of future target power data to identify demand peaks and troughs, as well as the expected amount of renewable energy generation. Based on the predicted data and existing load conditions, assess possible supply and demand imbalances. Predict the potential impact of environmental parameters (such as temperature, humidity) on the performance of power equipment.
[0042] An appropriate optimization model can be selected or constructed, such as linear programming, mixed integer programming, dynamic programming, genetic algorithm, particle swarm optimization, etc., depending on the complexity of the optimization objective and the characteristics of the data. Define the optimization objective function, convert economic, reliability, environmental and safety objectives into mathematical expressions. Set the constraints of the optimization model, including the operation limits of power equipment, grid capacity limits, environmental parameter limits, etc. Use cloud computing resources to run the optimization model and solve the optimal value of the objective function under the constraint conditions.
[0043] Convert the solution of the optimization model into specific device operation instructions, such as adjusting the output power of the generator set, controlling the charge and discharge plan of the energy storage device, adjusting the load distribution of the power distribution network, etc.
[0044] Through the above steps, the cloud can generate and issue optimization instructions based on the predicted future target power data and the preset optimization objectives, guiding the power equipment to make real-time adjustments to achieve economic, reliable, environmentally friendly and safe operation of the power system.
[0045] Step S210, issue the optimization instructions to the power equipment.
[0046] In this step, the cloud system can decode the general instructions generated based on the optimization model and convert them into specific instruction formats that the specific equipment can understand and execute. Pack the converted optimization instructions and use encryption algorithms for data protection to prevent tampering or interception during transmission. According to network conditions and data transmission requirements, choose the appropriate communication channel. This may include fiber broadband, 5G network, power line carrier communication, etc. to ensure that the instructions can quickly and reliably reach the edge computing terminal. The edge computing terminal receives the instruction data packet issued by the cloud and performs decryption processing to restore the original instruction content. Parse the instruction content into specific operations suitable for local execution. Based on the parsed instructions, generate control signals for specific devices, which should include device ID, control action, expected parameters, etc.
[0047] Through the "edge-end" communication network, send the control signals to the corresponding power equipment, for example, you can use wireless local area network (WLAN), Bluetooth, ZigBee, etc. Short-range communication technology.
[0048] Through the above steps, the optimization instructions can be accurately and securely transmitted from the cloud to the power equipment, guiding the equipment to make adjustments to achieve optimized operation of the power system.
[0049] Through the above steps, the purpose of hierarchical control of power equipment in the park can be achieved, thereby achieving the technical effects of reducing energy waste and improving management effectiveness, and further solving the technical problems of energy waste and poor management effectiveness caused by the difficulty of overall control of multiple power equipment in the park.
[0050] As an optional embodiment, the target power data and the target environment parameter corresponding to the power equipment in the target park are collected, including: collecting initial power data and initial environment parameter corresponding to the power equipment based on a preset time window; mapping the initial power data and the initial environment parameter to a time sequence corresponding to the time window to determine a power data sequence and an environment parameter sequence; detecting whether there is a missing value in the power data sequence and the environment parameter sequence; in a case where there is a missing value in the power data sequence and / or the environment parameter sequence, estimating the missing value based on a linear difference method to determine the target power data and the target environment parameter.
[0051] Optionally, the time window can be set according to actual conditions, for example, it can be set to five minutes, that is, data collection is performed once every five minutes. Mapping the initial power data and the initial environment parameter to the time sequence corresponding to the time window can check whether there is data missing. If there is data missing, the data missing can be estimated based on the linear difference method to fill in the data missing, and finally the target power data and the target environment parameter are determined. In this way, the continuity and integrity of data collection can be ensured, and the use of the linear difference method ensures the accuracy and real-time performance of data processing. The combination of time series analysis and data interpolation technology can effectively process incomplete data and ensure the reliability of subsequent analysis.
[0052] In a cloud-managed edge architecture-based power system, a time window, such as 1 hour, 24 hours or longer, can be preset for continuous data collection according to predicted demand and data characteristics. In the set time window, power data and environmental parameters are continuously collected from power equipment and environmental monitoring equipment, which should include but not limited to power output, power demand, temperature, humidity, light intensity, etc. The collected initial power data and initial environmental parameters are recorded according to the corresponding time points to form time series data. The recorded initial data can be mapped to the time series to ensure that each data matches its corresponding time window position, forming power data sequences and environmental parameter sequences. Check if there are missing values in the sequences, which may be caused by equipment failure, network interruption or other unforeseen reasons. If no missing values are found in the power data sequence and environmental parameter sequence after checking, these sequences can be directly used as input for subsequent data analysis and prediction model construction. In the case of detecting missing values in the power data sequence and / or environmental parameter sequence, the missing values can be estimated by analyzing the time series data before and after the missing values using linear interpolation method. Linear interpolation assumes that the data changes linearly in the time period before and after the missing value, i.e. the missing value can be linearly interpolated from the two known values before and after it. Using the above linear difference method, the missing values in the power data sequence and environmental parameter sequence are completed to form complete time series. Check the completed data to ensure that it conforms to the logic and trend of the actual scenario, and avoid prediction bias caused by unreasonable interpolation.
[0053] After completing the missing value processing, the complete power data sequence and environmental parameter sequence obtained are the target power data and target environmental parameters. The processed data can be stored in a cloud database and transmitted to edge devices through an efficient and secure communication network (such as a cloud-edge communication network) for real-time control and analysis.
[0054] Through the above steps, even in the case of incomplete data, the missing values can be estimated by linear difference method to ensure the completeness of the data sequence and the accuracy of the prediction model, thereby effectively supporting the intelligent management and optimal scheduling of the power system.
[0055] As an optional embodiment, based on the edge computing terminal, the target power data and the target environmental parameters are aggregated to obtain aggregated data, including: calculating the statistical quantities corresponding to the target power data and the target environmental parameters respectively, determining the target power data statistical quantity and the target environmental parameter statistical quantity; determining the correlation between the target power data and the target environmental parameters based on the target power data statistical quantity and the target environmental parameter statistical quantity; based on the target power data, the target environmental parameters and the correlation, determining the aggregated data.
[0056] Optionally, statistical quantities of target power data can be calculated, such as:
[0057] Average power output: Calculate the average power output of all devices within a certain time window to understand the basic level of power demand.
[0058] Maximum / minimum power; Record the maximum and minimum power output values of the device within the same time window to evaluate the fluctuation range of power demand.
[0059] Power peak time: Identify the time point when the power demand reaches the peak, which helps to plan power scheduling and resource allocation.
[0060] Renewable energy contribution rate: Calculate the proportion of renewable energy (such as solar energy, wind energy) in the total power supply, evaluate its influence on the stability and cost of the power grid.
[0061] Calculate the statistical quantities of target environmental parameters, such as:
[0062] Average temperature / humidity: Calculate the average temperature and humidity of the environment to understand the basic conditions of the environment.
[0063] Temperature / humidity fluctuation range: Record the fluctuation range of environmental parameters to evaluate their impact on the performance of power equipment.
[0064] Light intensity / wind speed change trend: Analyze the change trend of light intensity and wind speed over time to predict the output change of renewable energy.
[0065] Then use statistical methods such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc. to analyze the correlation between target power data and target environmental parameters. For example, build a regression model to explore how environmental parameters affect power demand and equipment performance. Analyze how changes in target environmental parameters affect future power demand trends, such as whether temperature rise leads to increased load of refrigeration equipment.
[0066] Combine target power data statistics and target environmental parameter statistics to form a comprehensive operating state description, such as associating average power output with average temperature to reflect the direct impact of temperature changes on power demand. Add context information such as time stamp, geographic location, and device type to the aggregated data to enhance the analysis value and application range of the data. Based on statistical quantities and correlation relationships, perform anomaly detection on the data to mark abnormal data points for subsequent analysis and fault diagnosis.
[0067] Through statistical analysis and correlation analysis, effective data aggregation can be achieved, reducing the data processing pressure of the cloud. Among them, the calculation of statistical quantities and the determination of correlation relationships provide a solid data foundation for subsequent prediction and optimization.
[0068] The generation of aggregated data enables the system to more efficiently perform global optimization, improving the intelligent level of energy management and scheduling. In other optional embodiments, more complex data analysis models, such as deep neural networks, can also be introduced to further explore potential correlations between data and improve the depth and breadth of data aggregation.
[0069] As an optional embodiment, based on the cloud, the future target power data of the power equipment is predicted according to the aggregated data, including: inputting the aggregated data into a preset machine learning model in the cloud to output the future target power data, wherein the machine learning model is trained by using historical target environmental parameters and historical target power data.
[0070] Optionally, using the computing resources of the cloud for deep learning can process large-scale, high-dimensional data, improving the accuracy and efficiency of prediction. The machine learning model can capture the rules and trends of power equipment operation by learning historical data, providing an accurate model for prediction.
[0071] The prediction of future target power data provides a basis for the generation of optimization instructions, which helps to achieve economic operation of the power system and efficient consumption of new energy. In other embodiments, more advanced machine learning algorithms, such as reinforcement learning, can be used to solve the dynamic adaptability problem of the prediction model, improving the flexibility and accuracy of the prediction.
[0072] As an optional embodiment, based on the cloud, the optimization instruction is generated according to the future target power data and the preset power optimization target, including: in the cloud, establishing an initial optimization model and a target function based on the power optimization target; adjusting the parameters in the optimization model based on the future target power data to obtain a target optimization model; solving the target optimization model to obtain the optimization parameters corresponding to the power equipment; and generating the optimization instruction based on the optimization parameters corresponding to the power equipment.
[0073] Optionally, a machine learning model suitable for time series data prediction can be selected. The aggregated data is standardized to ensure that the data is on the same scale when input into the model, which helps the stability and prediction accuracy of the model. Based on the needs of the model and the characteristics of the aggregated data of the edge computing terminal, feature selection is performed to remove irrelevant or redundant features, and new features can also be constructed to enhance the prediction ability. The processed aggregated data, including historical target power data and historical target environmental parameters, is provided as input to the loaded machine learning model. The model is run to predict future target power data based on the relationships and patterns of historical data. The model outputs predicted values of power demand, power generation, or power system state. Analyze the predicted values output by the model to understand the impact of the prediction results on the operation of the power system, such as predicted power demand peaks and troughs, and guidance for power generation planning and energy storage strategies. Use a test data set to evaluate the prediction accuracy of the model to ensure that the model can work effectively in actual scenarios. Common evaluation metrics include but are not limited to mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Based on the prediction results, develop energy scheduling, energy storage charging and discharging strategies, or demand response plans to address fluctuations in predicted power demand. Convert the optimization strategies into specific operational instructions and issue them to the edge computing terminal through the cloud edge communication network, and control the power equipment or flexible load according to the instructions by the edge terminal to achieve the predicted future power data target.
[0074] Throughout the process, the cloud utilizes its powerful computing resources and storage capabilities to process large-scale aggregated data, execute complex prediction models, and store and analyze large amounts of historical data and prediction results. This not only improves the economy and efficiency of the power system operation, but also enhances the stability and resilience of the system to sudden events, especially when dealing with a high proportion of new energy access, effectively promoting the consumption and utilization of new energy.
[0075] By establishing an optimization model, intelligent optimization of power equipment operation strategies is achieved. By adjusting model parameters, the model can adapt to changes in future power data, enabling dynamic optimization. The generation of optimization instructions guides the efficient operation of power equipment, improving the economy and stability of the power system. In other embodiments, multi-objective optimization algorithms can be introduced to overcome the limitations of single-objective optimization, achieving more comprehensive and detailed power system optimization.
[0076] As an optional embodiment, in the case where the power equipment receives optimization instructions, the optimized power data of the power equipment is monitored; based on the optimized power data, the optimization result of the target park is determined.
[0077] Optionally, after receiving the optimization instructions from the cloud data center or edge computing terminal, the power equipment converts the instructions into executable control signals according to the control protocol and instruction parsing function of the equipment, such as adjusting the power generation power, changing the load distribution scheme, etc. The sensors and metering devices on the equipment continuously monitor and collect the optimized power data, including but not limited to power output, energy consumption, voltage, current, and other key parameters. The optimized power data is uploaded to the edge computing terminal and the cloud in real time through the communication network (edge-end communication or cloud-edge communication), forming a closed-loop feedback mechanism, so that the system can adjust the optimization strategy according to the actual effect. In the cloud, the optimized power data is compared and analyzed with the pre-optimization data or predicted data to evaluate the actual effect of the optimization strategy. Based on the optimized power data, a series of performance indicators are calculated, such as energy consumption reduction percentage, power generation efficiency improvement, system stability improvement, cost savings, etc. Comprehensive analysis of the above performance indicators evaluates whether the optimization strategy has achieved the expected target, such as improving the consumption rate of new energy, reducing power costs, and enhancing system stability, etc.
[0078] If the optimization result does not meet the expectation, analyze the reasons, which may be caused by errors in optimization instructions, response delays of equipment, changes in external environment, etc. Then adjust the strategy or repair system failure.
[0079] Through these steps, the intelligent power management system based on cloud management edge architecture can monitor the execution effect of optimization instructions in real time, continuously adjust the strategy to achieve the best operating state, effectively improve the power use efficiency and economy of the target park, and reduce the operation risk, ensuring the stability and sustainability of the power system.
[0080] By monitoring the optimized power data in real time, the effect of the optimization strategy can be evaluated in a timely manner, providing a basis for subsequent strategy adjustment. The determination of the optimization result is based on real-time data feedback, which can realize closed-loop control, improve the self-adaptability of the system, and help continuously improve the optimization strategy and improve the overall operating efficiency of the system. In other optional embodiments, real-time data analysis and feedback mechanisms such as real-time data stream processing technology can be introduced to further improve the response speed and optimization effect of the system.
[0081] By adopting the hierarchical control of cloud and edge, the response speed and real-time performance are improved, because the edge computing node can quickly process real-time data, reducing the delay of data transmission to the cloud, and the cloud-edge architecture can process large-scale equipment data, through the preliminary filtering and processing of the edge node, the cloud only processes key data, avoiding the "curse of dimensionality", supporting the efficient access and management of large-scale intelligent devices.
[0082] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited by the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.
[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that the control method of the power equipment according to the above embodiments can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the method described in each embodiment of the present application.
[0084] According to the embodiments of the present application, a control device of power equipment for implementing the control method of power equipment is also provided, Figure 3 is a structural block diagram of the control device of power equipment provided by the embodiments of the present application, as Figure 3 shown, the control device of power equipment includes an acquisition module 302, an aggregation module 304, a prediction module 306, a generation module 308, and a delivery module 310, and the control device of power equipment will be described below.
[0085] The acquisition module 302 is configured to acquire target power data and target environment parameters corresponding to the power equipment in a target park.
[0086] The aggregation module 304 is connected with the acquisition module 302 and is configured to aggregate the target power data and the target environment parameters based on an edge computing terminal to obtain aggregated data.
[0087] The prediction module 306 is connected with the aggregation module 304 and is configured to predict future target power data of the power equipment based on a cloud according to the aggregated data.
[0088] The generation module 308 is connected with the prediction module 306 and is configured to generate an optimization instruction based on a cloud according to the future target power data and a preset power optimization target.
[0089] The delivery module 310 is connected with the generation module 308 and is configured to deliver the optimization instruction to the power equipment.
[0090] It should be noted that the above collection module 302, aggregation module 304, prediction module 306, generation module 308 and delivery module 310 correspond to steps S202 to S210 in the embodiment, and the plurality of modules have the same instances and application scenarios as the corresponding steps, but are not limited to the above disclosed embodiments. It should be noted that the above modules as part of the device can run in the computer terminal 10 provided in the embodiment.
[0091] Embodiments of the present application can provide a computer device. Optionally, in the present embodiment, the above computer device can be located in at least one network device of a plurality of network devices of a computer network. The computer device comprises a memory and a processor.
[0092] The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the control method and device of the power equipment in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, i.e. implements the above-mentioned control method of the power equipment. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the computer terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0093] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: collecting target power data and target environment parameters corresponding to the target power equipment in the target park; based on the edge computing terminal, aggregating the target power data and the target environment parameters to obtain aggregated data; based on the cloud, predicting future target power data of the power equipment according to the aggregated data; based on the cloud, generating optimization instructions according to the future target power data and the preset power optimization target; and delivering the optimization instructions to the power equipment.
[0094] Optionally, the processor can further execute the program code of the following steps: collecting target power data and target environment parameters corresponding to the target power equipment in the target park, comprising: collecting initial power data and initial environment parameters corresponding to the power equipment based on a preset time window; mapping the initial power data and the initial environment parameters to a time sequence corresponding to the time window to determine a power data sequence and an environment parameter sequence; detecting whether there is a missing value in the power data sequence and the environment parameter sequence; in the case that there is a missing value in the power data sequence and / or the environment parameter sequence, estimating the missing value based on a linear difference method to determine the target power data and the target environment parameters.
[0095] Optionally, the processor can further execute program codes of the following steps: based on the edge computing terminal, aggregating the target power data and the target environment parameter to obtain aggregated data, including: calculating respective statistics of the target power data and the target environment parameter, and determining the target power data statistics and the target environment parameter statistics; determining the correlation between the target power data and the target environment parameter based on the target power data statistics and the target environment parameter statistics; and determining the aggregated data based on the target power data, the target environment parameter, and the correlation.
[0096] Optionally, the processor can further execute program codes of the following steps: based on the cloud, predicting future target power data of the power equipment according to the aggregated data, including: inputting the aggregated data into a preset machine learning model on the cloud to output the future target power data, wherein the machine learning model is trained by using historical target environment parameters and historical target power data.
[0097] Optionally, the processor can further execute program codes of the following steps: based on the cloud, generating an optimization instruction according to the future target power data and a preset power optimization target, including: establishing an initial optimization model and a target function based on the power optimization target on the cloud; adjusting parameters in the optimization model based on the future target power data to obtain a target optimization model; solving the target optimization model to obtain optimization parameters corresponding to the power equipment; and generating the optimization instruction based on the optimization parameters corresponding to the power equipment.
[0098] Optionally, the processor can further execute program codes of the following steps: in the case that the power equipment receives the optimization instruction, monitoring optimized power data of the power equipment; and determining an optimization result of the target park based on the optimized power data.
[0099] By adopting the embodiment of the present application, a control method of a power equipment is provided, which collects target power data and target environment parameters corresponding to power equipment in a target park; based on an edge computing terminal, the target power data and the target environment parameter are aggregated to obtain aggregated data; based on the cloud, future target power data of the power equipment is predicted according to the aggregated data; based on the cloud, an optimization instruction is generated according to the future target power data and a preset power optimization target; and the optimization instruction is sent to the power equipment, which achieves the purpose of hierarchical control of the power equipment in the park, thereby realizing the technical effects of reducing energy waste and improving management effect, and further solving the technical problems of energy waste and poor management effect caused by the difficulty in overall management of multiple power equipment in the park.
[0100] Those skilled in the art can understand that all or part of the steps in the above-mentioned various methods of the embodiments can be completed by instructing the terminal device related hardware through a program, and the program can be stored in a non-volatile storage medium, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0101] The embodiments of the present application also provide a non-volatile storage medium. Optionally, in the present embodiment, the non-volatile storage medium can be used to save the program code executed by the control method of the power equipment provided by the above-mentioned embodiments.
[0102] Optionally, in the present embodiment, the non-volatile storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.
[0103] Optionally, in the present embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: collecting target power data and target environment parameters corresponding to the power equipment in the target park; based on the edge computing terminal, aggregating the target power data and the target environment parameters to obtain aggregated data; based on the cloud, predicting future target power data of the power equipment according to the aggregated data; based on the cloud, generating an optimization instruction according to the future target power data and a preset power optimization target; and issuing the optimization instruction to the power equipment.
[0104] Optionally, in the present embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: collecting target power data and target environment parameters corresponding to the power equipment in the target park, including: collecting initial power data and initial environment parameters corresponding to the power equipment based on a preset time window; mapping the initial power data and the initial environment parameters to a time sequence corresponding to the time window to determine a power data sequence and an environment parameter sequence; detecting whether there is a missing value in the power data sequence and the environment parameter sequence; and in the case that there is a missing value in the power data sequence and / or the environment parameter sequence, estimating the missing value based on a linear difference method to determine the target power data and the target environment parameters.
[0105] Optionally, in the embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: based on the edge computing terminal, aggregating the target power data and the target environment parameter to obtain aggregated data, including: calculating respective statistics of the target power data and the target environment parameter, and determining the target power data statistics and the target environment parameter statistics; based on the target power data statistics and the target environment parameter statistics, determining the correlation between the target power data and the target environment parameter; and based on the target power data, the target environment parameter and the correlation, determining the aggregated data.
[0106] Optionally, in the embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: based on the cloud, predicting future target power data of the power equipment according to the aggregated data, including: inputting the aggregated data into a preset machine learning model on the cloud, and outputting the future target power data, wherein the machine learning model is trained using historical target environment parameters and historical target power data.
[0107] Optionally, in the embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: based on the cloud, generating an optimization instruction according to the future target power data and a preset power optimization target, including: based on the power optimization target, establishing an initial optimization model and a target function on the cloud; adjusting parameters in the optimization model based on the future target power data to obtain a target optimization model; solving the target optimization model to obtain optimization parameters corresponding to the power equipment; and generating the optimization instruction based on the optimization parameters corresponding to the power equipment.
[0108] Optionally, in the embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: in the case that the power equipment receives the optimization instruction, monitoring optimized power data of the power equipment; and based on the optimized power data, determining an optimization result of the target park.
[0109] The embodiment of the application also provides a computer program product, including a computer program, and optionally, in the embodiment, the computer program can be implemented by the processor when executed to: collect target power data and target environment parameters corresponding to power equipment in a target park; based on an edge computing terminal, aggregate the target power data and the target environment parameter to obtain aggregated data; based on the cloud, predict future target power data of the power equipment according to the aggregated data; based on the cloud, generate an optimization instruction according to the future target power data and a preset power optimization target; and issue the optimization instruction to the power equipment.
[0110] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.
[0111] In the above-mentioned embodiments of the present application, the description of each embodiment is focused on, and the part not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.
[0112] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and in actual implementation, there can be another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, and can be electrical or other forms.
[0113] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed to a plurality of units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
[0114] In addition, each functional unit in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.
[0115] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a non-volatile storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and various program code storage media.
[0116] The above-mentioned is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.
Claims
1. A control method of a power device, characterized by, The method comprises the following steps: Collecting target power data and target environment parameters corresponding to power equipment in a target park; Based on the edge computing terminal, the target power data and the target environment parameters are aggregated to obtain aggregated data; Based on the cloud, the future target power data of the power equipment is predicted according to the aggregated data; Based on the cloud, the optimization instruction is generated according to the future target power data and the preset power optimization target; The optimization instruction is sent to the power equipment.
2. The method of claim 1, wherein, The method comprises the following steps: Based on a preset time window, initial power data and initial environment parameters corresponding to the power equipment are collected; The initial power data and the initial environment parameters are mapped to the time sequence corresponding to the time window to determine the power data sequence and the environment parameter sequence; Detect whether there is a missing value in the power data sequence and the environment parameter sequence; In the case that there is a missing value in the power data sequence and / or the environment parameter sequence, the missing value is estimated based on the linear difference method to determine the target power data and the target environment parameters.
3. The method of claim 1, wherein, The method comprises the following steps: The statistical quantities corresponding to the target power data and the target environment parameters are calculated to determine the target power data statistical quantity and the target environment parameter statistical quantity; Based on the target power data statistical quantity and the target environment parameter statistical quantity, the correlation between the target power data and the target environment parameters is determined; Based on the target power data, the target environment parameters and the correlation, the aggregated data is determined.
4. The method of claim 1, wherein, The method comprises the following steps:
5. The method of claim 1, wherein, In the cloud, the aggregated data is input into a preset machine learning model to output the future target power data, wherein the machine learning model is trained by using historical target environment parameters and historical target power data. The method comprises the following steps: In the cloud, based on the power optimization target, an initial optimization model and a target function are established; Based on the future target power data, the parameters in the optimization model are adjusted to obtain a target optimization model; The target optimization model is solved to obtain the optimization parameters corresponding to the power equipment; 6. The method according to any one of claims 1 to 5, characterized in that, Based on the optimization parameters corresponding to the power equipment, the optimization instruction is generated. The method further comprises the following steps: In the case that the power equipment receives the optimization instruction, the optimized power data of the power equipment is monitored; 7. A control device of a power device, characterized by comprising: Based on the optimized power data, the optimization result of the target park is determined. The method comprises the following steps: A collection module is configured to collect target power data and target environment parameters corresponding to power equipment in a target park; An aggregation module is configured to aggregate the target power data and the target environment parameters based on an edge computing terminal to obtain aggregated data; A prediction module configured to predict, based on a cloud, future target power data of the power device according to the aggregated data; A generation module configured to generate, based on the cloud, an optimization instruction according to the future target power data and a preset power optimization target; A delivery module configured to deliver the optimization instruction to the power device.
8. A non-volatile storage medium, comprising: The non-volatile storage medium includes a stored program, wherein the program controls the device where the non-volatile storage medium is located to perform the control method of the power device in any one of claims 1 to 6 when the program is running.
9. A computer device, comprising: Comprise: A memory and a processor, The memory stores a computer program; The processor is configured to execute the computer program stored in the memory, and the computer program makes the processor execute the control method of the power device in any one of claims 1 to 6 when the computer program runs.
10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the control method of the power device in any one of claims 1 to 6.
Citation Information
Patent Citations
Intelligent fishing photovoltaic power station operation and maintenance method and system
CN117911000A
Power analysis method, device and equipment for hybrid energy industrial park, and medium
CN118886683A
Photovoltaic energy storage system, control method and electric equipment
CN120073721A
Park load prediction method and device based on multi-modal data, and medium
CN120389389A
Method and system for automatic machine learning-based prediction of new energy power with cloud-edge collaboration
US20240394443A1
Cited By
Power data service system and power data service method
JP7900885B1
