Equipment management method integrated with power utilization dispatching

Abstract

The invention discloses an equipment management method fusing power utilization dispatching, which comprises the following steps of: distributing the overall power utilization demand of the power utilization dispatching according to areas and equipment types, and dispatching loads among the equipment. And collecting data related to the equipment, generating a health score corresponding to the data, and judging whether the equipment runs normally or not and needs to be protected or not. And according to the adjusted related data of the equipment load and the health score of the equipment, judging whether the equipment has a fault, and generating early warning information. By constructing a fused power consumption demand prediction model, accurate prediction of power consumption demands in a future time period is realized; based on the prediction result, estimating the load of the equipment, and evaluating the health condition of the equipment in combination with the real-time monitoring data of the equipment; finally, prediction, early warning and equipment maintenance suggestions are provided through an intelligent algorithm, and the intelligent level and operation efficiency of power system equipment management are improved.

Description

Technical Field

[0001] The present invention relates to the field of power electronics technology, and in particular to a method for equipment management integrating power dispatching. Background Art

[0002] At present, the equipment management technology of the power system mainly faces the following major challenges: First, the traditional equipment management method relies on regular maintenance and manual inspections, which cannot grasp the operating status of the equipment in real time, resulting in the inability to timely discover and handle equipment failures, affecting the stable operation of the power system. Secondly, the existing power consumption forecasting methods are mostly based on historical data and simple statistical models, which cannot accurately predict future power demand, resulting in a disconnect between dispatch instructions and actual demand. In addition, the assessment of equipment health status usually relies on a single monitoring indicator, which cannot fully and accurately reflect the comprehensive health status of the equipment and is difficult to provide effective maintenance recommendations. In recent years, with the development of big data technology, artificial intelligence and Internet of Things technology, data-driven equipment management methods have gradually become a research hotspot, realizing intelligent management of equipment by integrating multi-source data and building complex models. Summary of the invention

[0003] In view of the above-mentioned defects, the technical problem solved by the present invention is to provide a method for equipment management integrated with electricity scheduling, which realizes accurate prediction of electricity demand in future time periods by constructing a fusion electricity demand prediction model; based on the prediction results, the equipment load is estimated, and the health status of the equipment is evaluated in combination with the real-time monitoring data of the equipment; finally, predictive warnings and equipment maintenance suggestions are provided through intelligent algorithms, so as to improve the intelligence level and operation efficiency of power system equipment management.

[0004] A first aspect of the present invention provides a method for equipment management integrating power scheduling, the method comprising:

[0005] The overall electricity demand of the electricity scheduling is allocated by region and equipment type, and the load between the equipment is scheduled.

[0006] Collect data related to the device and generate a corresponding health score to determine whether the device is operating normally and whether maintenance is required.

[0007] Based on the adjusted relevant data of the equipment load and the health score of the equipment, it is determined whether the equipment has a fault and an early warning message is generated.

[0008] According to an embodiment of the present invention, allocating the overall power demand of the power scheduling by region and device type includes: assuming It's time The total electricity demand, It is The load ratio of the area is Electricity demand in the region , as shown in formula (1):

[0009] (1)

[0010] According to one embodiment of the present invention, the scheduling of the load between the devices includes: calculating the load rate of the device, and judging the load condition of the device according to the load rate; and dynamically adjusting the scheduling strategy according to the load condition to manage the load distribution of the device.

[0011] According to an embodiment of the present invention, calculating the load rate of the device and determining the load condition of the device according to the load rate includes:

[0012] Assumptions It is In the region The rated power of the device, No. The electricity demand of each region, is the historical load ratio of the equipment, then the equipment at time Load , as shown in formula (2):

[0013] (2)

[0014] Calculate the load factor of the equipment , the load rate Defined as the current load of the device With its rated power The ratio of is as follows:

[0015] (3)

[0016] Set the first threshold, the second threshold, and the equipment load rate Compare and judge the load-bearing condition of the equipment:

[0017] If the equipment load rate is greater than the first threshold, the equipment is overloaded; if the equipment load rate is less than the second threshold, the equipment is underloaded; if the equipment load rate is not greater than the first threshold and not less than the second threshold, the equipment is in a normal load state.

[0018] According to one embodiment of the present invention, dynamically adjusting the scheduling strategy based on the load conditions to manage the load distribution of the equipment includes: transferring the load of the overloaded equipment to the underloaded equipment, or adjusting the operating time of the overloaded equipment by dynamically adjusting the scheduling strategy.

[0019] According to one embodiment of the present invention, the collecting of data related to the device and generating a corresponding health score includes: preprocessing and feature extraction of the collected data related to the device, using a long short-term memory network (LSTM) model to generate a corresponding health score, and training the model.

[0020] According to an embodiment of the present invention, judging whether the device has a fault according to the adjusted relevant data of the device load and the health score of the device includes:

[0021] An equipment load prediction model is established based on the adjusted equipment load data, and the model is trained. At the same time, based on the equipment health score, it is determined whether there is a fault.

[0022] According to an embodiment of the present invention, the warning information includes: the name of the faulty device, the fault risk level, the operating status of the faulty device and the maintenance information of the faulty device.

[0023] The second aspect of the present invention provides an intelligent device, including a transmitter, a receiver, a memory and a processor; the memory is used to store computer instructions; the processor is used to run the computer instructions stored in the memory to implement the method of device management of integrated electricity scheduling mentioned above.

[0024] The third aspect of the present invention provides a storage medium, comprising: a readable storage medium and computer instructions, wherein the computer instructions are stored in the readable storage medium; the computer instructions are used to implement the method for equipment management of integrated electricity scheduling described above.

[0025] The beneficial effects provided by the present invention are as follows: by constructing a fusion electricity demand forecasting model, accurate forecasting of electricity demand in future time periods can be achieved; based on the forecasting results, the equipment load is estimated, and the health status of the equipment is evaluated in combination with the real-time monitoring data of the equipment; finally, forecasting warnings and equipment maintenance suggestions are provided through intelligent algorithms, thereby improving the intelligence level and operating efficiency of power system equipment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] Figure 1 A flow chart of a method for equipment management integrated with power dispatching disclosed in an embodiment of the present invention;

[0028] Figure 2 A schematic flow chart of a method for predicting power demand by integrating equipment management with power dispatching disclosed in an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of a device load estimation process for device management integrated with power dispatching disclosed in an embodiment of the present invention;

[0030] Figure 4 A schematic flow chart of a method for generating prediction and warning for equipment management integrated with power dispatching disclosed in an embodiment of the present invention;

[0031] Figure 5 A schematic diagram of the equipment maintenance process for equipment management integrating power dispatching disclosed in an embodiment of the present invention.

[0032] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0034] A method for equipment management integrating power dispatching, such as Figure 1 S101: Allocate the overall power demand of the power scheduling according to regions and equipment types, and schedule the loads between the equipments.

[0035] Electricity demand forecasting: Based on big data technology and artificial intelligence algorithms, a fusion electricity demand forecasting model is constructed, and multi-source data such as historical electricity consumption data, meteorological data, and socio-economic data are input to achieve accurate forecasts of electricity demand in future time periods.

[0036] In order to accurately predict the electricity demand in the future, this solution builds a fusion electricity demand forecasting model based on big data technology and artificial intelligence algorithms. The model makes predictions by inputting multi-source data, including historical electricity data, meteorological data, and socio-economic data. The following are the detailed implementation methods and steps:

[0037] Data collection and preprocessing include extracting electricity consumption data from the power company database for the past few years, including daily and hourly electricity consumption.

[0038] Meteorological data: Obtain historical and forecasted temperature, humidity, precipitation, and other data from meteorological departments or public meteorological data sources.

[0039] Socioeconomic data: Collect socioeconomic data related to electricity demand, such as population growth, industrial production index, holiday information, etc.

[0040] In the data preprocessing stage, the data needs to be cleaned, denoised, and standardized. For example, missing values, outliers, and data at different time scales need to be aligned.

[0041] Feature engineering: Convert raw data into feature vectors that can be processed by the model. Specifically, the temperature and humidity in the meteorological data can be used as continuous features, and the holiday information can be used as categorical features.

[0042] The feature matrix is ​​constructed by using time series features, such as daily, weekly, and monthly periodic features.

[0043] Model selection and training: Choose a suitable machine learning model, such as Long Short-Term Memory (LSTM), Random Forest, or Gradient Boosted Decision Tree (GBDT). LSTM has advantages in processing time series data.

[0044] The data set is divided into training set and test set. The cross-validation method is used to optimize the model parameters to prevent overfitting.

[0045] Model evaluation and validation: The model is evaluated using metrics such as mean square error (MSE), mean absolute error (MAE), and R-squared (R²).

[0046] (1)

[0047] (3)

[0048] in, represents the true value, represents the predicted value, is the number of samples.

[0049] Model deployment and application: Deploy the trained model in the power dispatching system, input the latest meteorological data and socio-economic data in real time, and generate power demand forecasts for future periods, such as Figure 2 shown.

[0050] Suppose we have electricity consumption data, meteorological data, and socioeconomic data for the past three years. We first clean the data, such as filling missing values ​​and removing outliers. Then, we standardize the data, taking meteorological data such as temperature and humidity as continuous features and holidays as categorical features.

[0051] Then, we select the LSTM model and train it. The dataset is divided into 80% training set and 20% test set. During the training process, we use cross-validation to determine the best model parameters. After training, we evaluate the model using MSE, MAE, and R² to ensure that its prediction accuracy meets expectations.

[0052] Finally, the trained model is deployed to the power dispatching system. By inputting the latest weather forecast data and socio-economic data, the model can generate a forecast of power demand in the future. In this way, power companies can make power dispatching plans in advance to ensure the stability and reliability of power supply.

[0053] Equipment load estimation: Based on the power demand forecast results and the power system dispatch strategy, estimate the load of each device and identify possible overloaded or underloaded equipment.

[0054] Based on the power demand forecast results and combined with the power system dispatch strategy, we can estimate the load of each device and identify possible overloaded or underloaded devices. The following are detailed implementation methods and steps:

[0055] Power demand allocation: Allocate the predicted overall power demand by region or device type. This step needs to consider the historical power consumption ratio of each region or device and the current scheduling strategy.

[0056] Assumptions It's time The total electricity demand, It is The load ratio of the area is The electricity demand of each region can be expressed as formula (4):

[0057] (4)

[0058] Equipment load calculation: For specific equipment in each area, the power demand in the area is broken down into individual devices based on their rated power and historical load ratio.

[0059] Assumptions It is In the region The rated power of the device, is the historical load ratio of the device, then the device The load can be expressed as formula (5):

[0060] (5)

[0061] Equipment overload / underload identification: Calculate the load factor of each device. The load factor is defined as the ratio of the current load of the device to its rated power, as shown in formula (6):

[0062] (6)

[0063] Set overload and underload thresholds, for example, if , then the device is judged to be overloaded; if The device is judged to be underloaded.

[0064] Scheduling strategy adjustment: Dynamically adjust the scheduling strategy based on the equipment load, for example, transfer part of the load from overloaded equipment to underloaded equipment, or adjust the operating time and sequence of equipment.

[0065] Adjustments to the dispatch strategy can be made through optimization algorithms, such as linear programming or genetic algorithms, to minimize overload risks and improve equipment utilization efficiency. Figure 3 shown.

[0066] Assuming that the total electricity demand we predict in a certain period is 1000MW, and the electricity demand in a certain area is 20%, then the electricity demand in this area is as shown in formula (7).

[0067] (7)

[0068] In this area, there are two devices, device A and device B, with rated powers of 50MW and 100MW respectively, and historical load ratios of 60% and 40% respectively. During this period, the loads of device A and device B are respectively expressed as equation (8) and equation (9):

[0069] (8)

[0070] (9)

[0071] Then, we calculate the load rates of equipment A and equipment B, as shown in equations (10) and (11):

[0072] (10)

[0073] (11)

[0074] Obviously, device A is in an overload state, while device B is in a normal load state. Based on this result, we can adjust the scheduling strategy to transfer part of the load from device A to device B, or reduce the operating time of device A in the scheduling plan.

[0075] In this way, we can achieve accurate estimation of equipment load and adjust the dispatching strategy in time to ensure the safe and stable operation of the power system.

[0076] S102: Collect data related to the device and generate a corresponding health score to determine whether the device is operating normally and whether maintenance is required.

[0077] Equipment health status assessment: Collect real-time monitoring data of the equipment, including current, voltage, temperature and other indicators, use multi-indicator fusion method to assess the health status of the equipment and generate equipment health score.

[0078] In order to ensure the stable operation and timely maintenance management of the equipment, we need to evaluate the health status of the equipment. The evaluation process includes data collection, data processing, multi-index fusion and health score generation. The following are detailed implementation methods and steps:

[0079] Data collection: First, install sensors and monitoring equipment to collect multiple operating indicators of the equipment in real time, including current, voltage, temperature, vibration frequency, etc.

[0080] Through the Internet of Things (IoT) technology, these sensors are connected to a centralized data acquisition system to ensure real-time data transmission and storage.

[0081] Data preprocessing: Clean and preprocess the collected raw data, including removing noise, filling missing values ​​and data standardization.

[0082] For time series data, sliding window technology is used for smoothing to eliminate short-term fluctuations.

[0083] Feature extraction: Extract key features from the preprocessed data, such as the mean and variance of current, the peak value of temperature, etc.

[0084] The principal component analysis (PCA) method can be used to reduce the dimensionality of high-dimensional features to reduce the computational complexity.

[0085] Multi-index fusion: Use the multi-index fusion method based on deep learning to combine different operating indicators to evaluate the overall health status of the equipment.

[0086] An improved long short-term memory network (LSTM) model is adopted, which can process time series data and capture the long-term dependencies of equipment operation indicators.

[0087] The input of the LSTM model is Multiple indicator data at all times, output as the health score of the device The model training can be achieved by minimizing the following loss function, as shown in formula (12):

[0088] (12)

[0089] in, For actual health score, Give the model predicted health score.

[0090] Health score generation: Generate a health score for the device based on the output of the LSTM model. The score range is usually set between 0 and 100, with higher values ​​indicating better device health.

[0091] Set thresholds for the health score, for example, a score below 60 indicates that the device needs maintenance, and a score above 80 indicates that the device is operating well.

[0092] Suppose we install current, voltage and temperature sensors on a certain device, and the real-time data collected is as follows:

[0093] - Current data (unit: A): [ 10 , 12 , 11 , 13 , 12 ] ;

[0094] - Voltage data (unit: V): [ 220 , 221 , 219 , 222 , 220 ] ;

[0095] - Temperature data (unit: °C): [ 40 , 42 , 41 , 43 , 42 ] .

[0096] Data preprocessing: Smooth the current data to obtain smoothed data: [ 10 . 8 , 11 . 6 , 12 . 0 , 12 . 8 , 12 . 4 ] ; Standardize the voltage data to obtain the standardized data: [ 0 . 1 , 0 . 2 , − 0 . 1 , 0 . 3 , 0 . 1 ] ; Perform denoising on the temperature data to obtain the denoised data: [ 41 , 42 , 41 . 5 , 42 . 5 , 42 ] .

[0097] Feature extraction: Calculate the mean and variance of the current data: the mean is 11.92 and the variance is 0.68.

[0098] Calculate the mean and variance of the voltage data: the mean is 0.12 and the variance is 0.04.

[0099] Calculate the peak and mean of the temperature data: the peak is 42.5 and the mean is 41.8.

[0100] Multi-index fusion: The extracted features are input into the LSTM model for training and prediction. Assume that after training, the health score obtained by the model is 75.

[0101] Health score generation: Based on the health score of 75 output by the model, it is judged that the equipment is in good operating condition and does not require immediate maintenance.

[0102] Through the above steps, we can achieve real-time assessment of equipment health status and generate accurate health scores to help managers identify potential problems in a timely manner and take corresponding measures.

[0103] Prediction and warning: Based on the equipment health status assessment results and combined with the equipment load estimation, possible failure risks are identified, and prediction and warning information is generated to prompt operation and maintenance personnel to take preventive measures.

[0104] S103: judging whether the device has a fault according to the adjusted relevant data of the device load and the health score of the device, and generating early warning information.

[0105] Based on the equipment health status assessment results, combined with the equipment load estimation, possible failure risks are identified, and prediction and warning information is generated to prompt operation and maintenance personnel to take preventive measures. The following are detailed implementation methods and steps, such as Figure 3 shown.

[0106] Equipment load prediction: By analyzing historical electricity consumption data, an equipment load prediction model is established. Time series analysis methods such as autoregressive integrated moving average model (ARIMA) or long short-term memory network (LSTM) can be used to predict equipment load in future periods.

[0107] For example, when using the LSTM model for load forecasting, the input is The historical load data at the time is output as The predicted load at the moment. The model training can be achieved by minimizing the following loss function, as shown in formula (13):

[0108] (13)

[0109] in, is the actual load, The load predicted by the model.

[0110] Fault risk identification: Combine the equipment health status assessment results with the load forecast results to assess the equipment failure risk in the future period.

[0111] Set thresholds for fault risk assessment. For example, when the health score is lower than 60 and the load forecast value is higher than 80% of the maximum load, the fault risk is considered high.

[0112] Generate forecast warning information: Generate forecast warning information based on the fault risk assessment results. The warning information includes equipment name, fault risk level, recommended preventive measures, etc.

[0113] Early warning information can be sent to operation and maintenance personnel in real time via SMS, email or intelligent operation and maintenance platform.

[0114] Suppose we analyze the historical power consumption data of a certain device and obtain the following data: Load data for the past 5 hours (unit: kW): [ 50 , 55 , 53 , 58 , 56 ] .

[0115] Equipment load estimation: Use the LSTM model to predict load. Input the above historical load data and the model outputs a predicted load of 60kW for the next hour.

[0116] Fault risk identification: The known equipment health score is 55 and the maximum load is 70kW. Set the fault risk assessment threshold: the health score is less than 60 and the load forecast value is greater than 80% of the maximum load. Calculate the percentage of the load forecast value: , which is 85.7%. Since the health score of 55 is lower than 60 and the load forecast value of 85.7% is higher than 80%, it is identified that the equipment has a high risk of failure.

[0117] Generate forecast warning information: The generated warning information includes: equipment name, failure risk level (high), recommended preventive measures (such as checking equipment operating status, arranging maintenance, etc.). The warning information is sent to relevant operation and maintenance personnel in real time through the intelligent operation and maintenance platform, prompting them to take preventive measures to avoid equipment failure.

[0118] Through the above steps, we can timely identify possible failure risks based on equipment health assessment and load forecast results, generate predictive warning information, and help operation and maintenance personnel take preventive measures in advance to ensure the stable operation of the equipment.

[0119] Equipment maintenance recommendations: Based on the equipment health score and prediction and warning information, intelligent algorithms are used to generate equipment maintenance recommendations, including maintenance time, maintenance measures, etc., to guide operation and maintenance personnel to perform equipment maintenance.

[0120] Based on the equipment health score and forecast warning information, intelligent algorithms are used to generate equipment maintenance suggestions, including maintenance time, maintenance measures, etc., to guide operation and maintenance personnel to perform equipment maintenance. The following are detailed implementation methods and steps, such as Figure 4 shown.

[0121] Integration of equipment health score and early warning information: Collect equipment health score and forecast early warning information, and integrate these data into a comprehensive assessment model. The health score can be calculated based on factors such as the equipment's historical fault records and operating data, while the early warning information is based on the aforementioned load forecast and fault risk identification results.

[0122] Intelligent algorithms generate maintenance recommendations: Use rule-based expert systems or machine learning algorithms, such as decision trees and random forests, to analyze equipment health scores and warning information to generate specific maintenance recommendations. The inputs to the algorithm include equipment health scores, load forecast results, historical maintenance records, etc., and the output is specific maintenance measures and schedules.

[0123] For example, using the decision tree algorithm, maintenance recommendations can be generated based on the following rules:

[0124] If the health score is lower than 50 and the load forecast is higher than 80%, it is recommended to shut down and inspect immediately.

[0125] If the health score is between 50 and 70 and the load forecast is above 70%, maintenance is recommended during the next maintenance cycle.

[0126] If the health score is above 70 and the load forecast is below 70%, regular inspection is recommended.

[0127] Generate maintenance plan: Generate a detailed maintenance plan based on the output of the intelligent algorithm. The maintenance plan includes equipment name, maintenance time, specific maintenance measures, required tools and spare parts, etc.

[0128] The maintenance plan can be sent to relevant operation and maintenance personnel in the form of a task list through the intelligent operation and maintenance platform, and the progress can be tracked on the platform.

[0129] Suppose we have the following data: Equipment health score: 45 Load forecast result: 85% maximum load, Historical maintenance record: The last maintenance time was 3 months ago.

[0130] Integration of equipment health score and early warning information: The equipment health score is 45, the load forecast result is 85%, and the result is

[0131] Historical maintenance records.

[0132] Intelligent algorithm generates maintenance recommendations: According to the rules of the decision tree algorithm: Health score 45 is lower than 50, load forecast

[0133] 85% is higher than 80%, so it is recommended to shut down the machine immediately for inspection. Therefore, the generated maintenance recommendation is: shut down the machine immediately and conduct a detailed inspection.

[0134] Generate maintenance plan: The generated maintenance plan includes: Equipment name: Equipment A Maintenance time: Immediate, Specific maintenance measures: Shut down to check the electrical system, lubrication system, cooling system, etc., check for overheating, wear or other abnormal conditions. Required tools and spare parts: multimeter, lubricating oil, coolant, spare cables, etc.

[0135] Operation and maintenance personnel perform maintenance: The maintenance plan is sent to relevant operation and maintenance personnel through the intelligent operation and maintenance platform. The operation and maintenance personnel conduct equipment shutdown inspections according to the plan to ensure stable operation of the equipment.

[0136] Through the above steps, based on the equipment health score and predictive warning information, intelligent algorithms are used to generate detailed maintenance recommendations and plans to guide operation and maintenance personnel to perform effective equipment maintenance, thereby improving equipment reliability and operating efficiency.

[0137] The second aspect of the present invention provides an intelligent device, including a transmitter, a receiver, a memory and a processor; the memory is used to store computer instructions; the processor is used to run the computer instructions stored in the memory to implement the method of device management of integrated electricity scheduling mentioned above.

[0138] The third aspect of the present invention provides a storage medium, comprising: a readable storage medium and computer instructions, wherein the computer instructions are stored in the readable storage medium; the computer instructions are used to implement the method for equipment management of integrated electricity scheduling described above.

[0139] The beneficial effects provided by the present invention are as follows: by constructing a fusion electricity demand forecasting model, accurate forecasting of electricity demand in future time periods can be achieved; based on the forecasting results, the equipment load is estimated, and the health status of the equipment is evaluated in combination with the real-time monitoring data of the equipment; finally, forecasting warnings and equipment maintenance suggestions are provided through intelligent algorithms, thereby improving the intelligence level and operating efficiency of power system equipment management.

[0140] Obviously, the above specific implementation cases are only examples for illustrating the application of the present method, rather than limiting the implementation methods. For those skilled in the art, other different forms of changes and modifications can be made on the basis of the above description to study other related issues. Therefore, the protection scope of the present invention should be the protection scope of the claims.

[0141] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0142] The electronic device and other embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the embodiments of the present invention have been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0145] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0146] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for equipment management integrating power dispatching, characterized in that: The method comprises: S101: Allocate the overall power demand of the power scheduling according to regions and equipment types, and schedule the loads between the equipment; S102: Collect data related to the device and generate a health score corresponding to the device to determine whether the device is operating normally and whether maintenance is required; S103: judging whether the device has a fault according to the adjusted relevant data of the device load and the health score of the device, and generating early warning information.

2. The method according to claim 1, characterized in that The overall electricity demand of the electricity dispatch is allocated by region and equipment type, including: assuming It's time The total electricity demand, It is The load ratio of the area is Electricity demand in the region , as shown in formula (1): （1）。 3. The method according to claim 2, characterized in that The scheduling of the load between the devices includes: calculating the load rate of the device, and judging the load condition of the device according to the load rate; and dynamically adjusting the scheduling strategy according to the load condition to manage the load distribution of the device.

4. The method according to claim 3, characterized in that Calculating the load rate of the equipment and determining the load condition of the equipment according to the load rate include: Assumptions It is In the region The rated power of the device, No. The electricity demand of each region, is the historical load ratio of the equipment, then the equipment at time Load , as shown in formula (2): （2） Calculate the load factor of the equipment , the load rate Defined as the current load of the device With its rated power The ratio of is as follows: （3） Set the first threshold, the second threshold, and the equipment load rate Compare and judge the load-bearing condition of the equipment: If the equipment load rate is greater than the first threshold, the equipment is overloaded; if the equipment load rate is less than the second threshold, the equipment is underloaded; if the equipment load rate is not greater than the first threshold and not less than the second threshold, the equipment is in a normal load state.

5. The method according to claim 3, characterized in that: The dynamically adjusting the dispatching strategy according to the load condition to manage the load distribution of the equipment includes: transferring the load of the overloaded equipment to the underloaded equipment, or adjusting the operating time of the overloaded equipment by dynamically adjusting the dispatching strategy.

6. The method according to claim 1, characterized in that The collecting of data related to the device and generating a health score corresponding thereto includes: The collected device-related data is preprocessed and feature extracted, and the long short-term memory network (LSTM) model is used to generate the corresponding health score, and the model is trained.

7. The method according to claim 1, characterized in that The determining whether the device has a fault according to the adjusted data related to the device load and the health score of the device includes: An equipment load prediction model is established based on the adjusted equipment load data, and the model is trained. At the same time, based on the equipment health score, it is determined whether there is a fault.

8. The method according to claim 1, characterized in that The warning information includes: the name of the faulty device, the fault risk level, the operating status of the faulty device and the maintenance information of the faulty device.

9. A smart device, characterized in that: include: transmitter, receiver, memory and processor; The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement the method for equipment management of integrated electricity dispatching as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: include: A readable storage medium and computer instructions, wherein the computer instructions are stored in the readable storage medium; The computer instructions are used to implement the method for equipment management of integrated electricity dispatching as described in any one of claims 1 to 7.

Images