Shelter equipment remote power supply monitoring method and system based on Internet of Things

Abstract

The invention provides a shelter equipment remote power supply monitoring method and system based on the Internet of Things. The method comprises the following steps: monitoring each electric device in real time, and sending monitoring data to a cloud server to obtain real-time monitoring data; generating an accurate power demand prediction report according to the real-time monitoring data; based on the power demand prediction report, when power supply and demand imbalance is predicted, starting an optimization scheduling strategy based on a particle swarm optimization algorithm, dynamically adjusting the output power of a generator set or the working schedule of electric equipment, and evaluating potential risk points by using a fault tree analysis technology; generating an emergency response plan and an optimal scheduling result; and carrying out automatic management on a power resource shortage condition based on the optimal scheduling result, ensuring normal operation of high-priority equipment, and generating a power management decision suggestion. According to the technical scheme provided by the invention, the flexibility of power supply monitoring can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of remote power supply monitoring technology, and in particular to a remote power supply monitoring method and system for cabin equipment based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things (IoOT) technology, the ability to remotely monitor and manage various types of equipment has been significantly improved. Especially in emergency shelters, such as medical shelters and emergency communication shelters, ensuring the stable operation of these facilities is crucial to ensuring public safety and service continuity.

[0003] There are some power management systems based on traditional algorithms on the market, which mainly adjust power distribution by manually setting rules or simply rely on fixed schedules to operate. In addition, there are also some products that have initially applied machine learning technology, trying to optimize power usage by analyzing historical data.

[0004] Although these solutions can improve energy efficiency and reduce waste to a certain extent, they perform poorly when faced with complex and changing real-world scenarios, especially when it comes to quickly responding to fluctuations in electricity demand caused by emergencies. Summary of the invention

[0005] The embodiments of the present application provide a remote power supply monitoring method and system for cabin equipment based on the Internet of Things, so as to solve the problem of lack of flexibility in power supply monitoring in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a remote power supply monitoring method for shelter equipment based on the Internet of Things, comprising the following steps:

[0007] Monitor each electrical device in real time and send the monitoring data to the cloud server to obtain real-time monitoring data;

[0008] Based on the real-time monitoring data, the support vector machine model is used to predict the future trend of electricity demand changes, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report;

[0009] Based on the power demand forecast report, when an imbalance in power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and a fault tree analysis technique is used to evaluate potential risk points, generate an emergency response plan and an optimization scheduling result;

[0010] Based on the optimization scheduling results, the power resource shortage situation is automatically managed to ensure the normal operation of high-priority equipment and generate power management decision suggestions.

[0011] Optionally, the real-time monitoring data is used to predict the future trend of electricity demand changes using a support vector machine model, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report, including:

[0012] Perform real-time monitoring on each electrical device and send the monitoring data to a cloud server to obtain the real-time monitoring data;

[0013] Using the real-time monitoring data, combined with historical electricity consumption data, preprocessing the data based on seasonal factors and historical electricity consumption patterns to obtain the preprocessed data;

[0014] The support vector machine model is trained according to the preprocessed data, and the prediction accuracy is improved by optimizing the model parameters, and the trained model is used to predict the future trend of power demand changes to obtain a power demand prediction value;

[0015] Based on the electricity demand forecast value, combined with seasonal factors, historical electricity consumption patterns and external influencing factors, a comprehensive analysis is performed to generate an accurate electricity demand forecast report.

[0016] Optionally, the using the real-time monitoring data, combined with historical electricity consumption data, preprocessing the data based on seasonal factors and historical electricity consumption patterns to obtain the preprocessed data includes:

[0017] Utilize the real-time monitoring data from each power-consuming device and combine it with the historical power consumption records to collect and integrate these data to obtain a comprehensive database;

[0018] Based on the comprehensive database, the data therein are cleaned to remove abnormal values ​​and missing values ​​to obtain cleaned data;

[0019] Utilizing the cleaned data, analyzing seasonal and periodic electricity consumption patterns, identifying electricity consumption characteristics in different time periods and electricity consumption patterns in different seasons, and obtaining electricity consumption pattern analysis results;

[0020] Based on the power consumption pattern analysis results, statistical methods and data mining techniques are used to deeply process the cleaned data, extract key features, and obtain feature extraction results;

[0021] Calculate the impact of external factors on the electricity consumption pattern, quantify the external factors and add them to the feature extraction results, perform further processing, improve the accuracy and reliability of the prediction model, and obtain feature data after considering the external factors;

[0022] The characteristic data after considering the external factors are integrated to form pre-processed data.

[0023] Optionally, the cleaned data is used to analyze seasonal and periodic electricity consumption patterns, identify electricity consumption characteristics in different time periods and electricity consumption patterns in different seasons, and obtain electricity consumption pattern analysis results, including:

[0024] Before calculating the electricity consumption E(t) at time t, a comprehensive electricity consumption pattern model is constructed by performing time series analysis, statistical feature extraction, and seasonal electricity consumption pattern analysis on the cleaned data to provide basic data for the calculation of E(t);

[0025]

[0026] Among them, E(t) is the electricity consumption at time t, reflecting the characteristics of electricity consumption in different time periods; α, β, γ, δ, ∈ are model parameters, obtained by fitting historical data, used to adjust the sensitivity and accuracy of the model; t is a time variable, indicating a specific moment or time period; T is the cycle length; D is the cycle length; φ, ψ are phase shifts, used to adjust the time starting point of the periodic function; S(t) is the seasonal electricity consumption pattern at time t, reflecting the difference in electricity consumption in different seasons; t0 is a specific time point, used to adjust the center position of the Gaussian function; σ is the standard deviation, used to control the width of the Gaussian function;

[0027] After calculating E(t), the power consumption data is smoothed, and the power demand forecast value P(t) is generated by combining historical power demand data and external influencing factors using the time series prediction model and optimization algorithm;

[0028]

[0029] Among them, P(t) is the predicted value of electricity demand at time t, which is used to evaluate the changing trend of future electricity demand; η, ζ, θ, κ, ρ, v are model parameters, which are obtained by fitting historical data and are used to adjust the sensitivity and accuracy of the model; E(t) is the electricity consumption at time t, which reflects the characteristics of electricity consumption in different time periods; μ is the average value of electricity consumption, which is used to standardize electricity consumption data and improve the stability of the model; t is a time variable, which represents a specific moment or time period; Y is the annual cycle length, which is used to capture the annual electricity consumption pattern; Q is the quarterly cycle length, which is used to capture the quarterly electricity consumption pattern; ω, λ are phase offsets, which are used to adjust the time starting point of the periodic function; F(t) is the function affected by external factors at time t;

[0030] After calculating P(t), a detailed power consumption pattern analysis report is generated through verification and calibration, visualization, and sensitivity analysis, providing a scientific basis for the management and dispatch of the power system.

[0031] Optionally, the support vector machine model is trained according to the preprocessed data, and the prediction accuracy is improved by optimizing the model parameters, and the trained model is used to predict the future trend of power demand changes to obtain a power demand prediction value, including:

[0032] Using the preprocessed data as input of a support vector machine model to perform model training to obtain a preliminarily trained support vector machine model;

[0033] Based on the initially trained support vector machine model, a cross-validation method is used to optimize the model parameters to improve the generalization ability and prediction accuracy of the model, thereby obtaining an optimized support vector machine model;

[0034] Using the optimized support vector machine model, combined with the latest real-time monitoring data and preprocessing process, the trend of power demand changes in a certain period of time in the future is predicted to obtain a preliminary power demand forecast value;

[0035] Based on the preliminary power demand forecast value, a comprehensive correction is performed in combination with seasonal factors, historical power consumption patterns and external influencing factors to generate a final power demand forecast report to obtain the power demand forecast value.

[0036] Optionally, based on the power demand forecast report, when an imbalance in power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and a fault tree analysis technique is used to evaluate potential risk points, generate an emergency response plan and an optimization scheduling result, including:

[0037] Using the power demand forecast report, the future power supply and demand balance is evaluated and processed, and when a power supply and demand imbalance is predicted, a power supply and demand imbalance warning signal is generated;

[0038] Based on the power supply and demand imbalance warning signal, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan;

[0039] Using fault tree analysis technology, risk assessment is performed on the preliminary optimization scheduling plan to generate a risk assessment report;

[0040] Based on the risk assessment report, conduct an in-depth analysis of various potential risk points and the chain reactions they may cause, and obtain an emergency response plan;

[0041] Combined with the preliminary optimization scheduling plan and the emergency response plan, the management and scheduling of power resources are comprehensively processed to generate an optimization scheduling result.

[0042] Optionally, based on the power supply and demand imbalance warning signal, an optimization scheduling strategy based on a particle swarm optimization algorithm is started to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan, including:

[0043] Before calculating the power supply and demand gap G(t) at time t, the power supply and demand model is constructed by analyzing and preprocessing the power demand forecast and historical operation data to prepare basic data for the calculation of G(t);

[0044]

[0045] Where G(t) is the gap between electricity supply and demand at time t, reflecting the degree of imbalance between electricity supply and demand; N is the number of generating units; M is the number of power-consuming devices; w i is the weight of the i-th generator set, reflecting its importance in the power system; P gen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; v j is the weight of the jth electrical equipment, reflecting its importance in the power system; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j (t) is the power consumption adjustment of the jth electrical equipment at time t;

[0046] After calculating G(t), normalization is performed, the power adjustment ratio is calculated, and the particle swarm optimization algorithm is used to adjust power generation and power consumption, and finally the optimized scheduling target value O(t) is generated;

[0047]

[0048] Among them, O(t) is the optimized dispatch target value at time t, reflecting the effect of the optimized dispatch scheme; η, ζ, θ, κ are model parameters, obtained by fitting historical data, and used to adjust the sensitivity and accuracy of the model; G(t) is the gap between power supply and demand at time t, reflecting the degree of imbalance between power supply and demand; N is the number of generators; M is the number of power-consuming equipment; P gen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; P max,i is the maximum output power of the i-th generator set; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j(t) is the power consumption adjustment of the jth electrical equipment at time t; P max,j is the maximum power consumption of the jth electrical equipment;

[0049] After calculating O(t), a detailed optimization scheduling plan is formed through the steps of verification and calibration, visualization, and sensitivity analysis to guide power system management and scheduling.

[0050] Optionally, the use of fault tree analysis technology to perform risk assessment processing on the preliminary optimization scheduling plan to generate a risk assessment report includes:

[0051] Using fault tree analysis technology, systematically analyze the key links and potential risk points in the preliminary optimization scheduling plan, identify various factors that may cause power system failures, and obtain a list of risk factors;

[0052] Based on the risk factor list, a fault tree model is constructed to clarify the logical relationship between various risk factors and their influence on the overall system stability, and a fault tree structure diagram is obtained;

[0053] Using the fault tree structure diagram, qualitative and quantitative risk assessment is performed to calculate the probability of occurrence of each risk event and the severity of its consequences, thereby obtaining risk assessment data;

[0054] Based on the risk assessment data, analyze the impact of different risk events on the balance of power supply and demand, evaluate the risks that may arise during the implementation of the optimized scheduling plan, and obtain risk assessment conclusions;

[0055] Based on the risk assessment conclusions, risk prevention and control recommendations are put forward and a risk assessment report is formed.

[0056] Optionally, automatically managing the power resource shortage situation based on the optimization scheduling result to ensure the normal operation of high-priority equipment and generate power management decision suggestions includes:

[0057] Using the optimization scheduling result, the allocation of power resources is automatically adjusted to obtain a power resource allocation plan;

[0058] Based on the power resource allocation scheme, a power resource management mechanism is established to monitor the usage status of power resources in real time and dynamically adjust power allocation to obtain a power resource management mechanism;

[0059] According to the power resource management mechanism, an emergency response level is set in the case of power resource shortage, and response measures of different levels are defined to obtain an emergency response level setting;

[0060] In combination with the optimization dispatch result and the emergency response level setting, a comprehensive assessment is made on the operating status of the power system, and specific power management decision suggestions are put forward to obtain power management decision suggestions.

[0061] In a second aspect, an embodiment of the present application provides a remote power supply monitoring system for cabin equipment based on the Internet of Things, including:

[0062] The monitoring module is used to monitor each electrical device in real time and send the monitoring data to the cloud server to obtain real-time monitoring data;

[0063] A prediction module is used to predict the future trend of electricity demand changes based on the real-time monitoring data using a support vector machine model, and to generate an accurate electricity demand forecast report by performing a multi-dimensional comprehensive analysis based on seasonal factors and historical electricity consumption patterns;

[0064] An adjustment module is used to start an optimization scheduling strategy based on a particle swarm optimization algorithm based on the power demand forecast report, dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, use the fault tree analysis technology to evaluate potential risk points, and generate an emergency response plan and optimization scheduling results when an imbalance between power supply and demand is predicted;

[0065] The management module is used to automatically manage the power resource shortage situation based on the optimization scheduling results, ensure the normal operation of high-priority equipment, and generate power management decision suggestions.

[0066] In an embodiment of the present application, each power-consuming device is monitored in real time, and the monitoring data is sent to a cloud server to obtain real-time monitoring data; based on the real-time monitoring data, a support vector machine model is used to predict future trends in electricity demand changes, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report; based on the electricity demand forecast report, when an imbalance in electricity supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and fault tree analysis technology is used to evaluate potential risk points, and emergency response plans and optimization scheduling results are generated; based on the optimization scheduling results, the power resource shortage situation is automatically managed to ensure the normal operation of high-priority equipment and generate power management decision recommendations.

[0067] The technical solution of this application has the following beneficial effects:

[0068] By monitoring each power-consuming device in real time and sending the monitoring data to the cloud server, the real-time and accuracy of the data is ensured, providing a reliable basis for subsequent analysis and decision-making; the monitoring data is stored in the cloud server to facilitate unified management and analysis of the data, improving the efficiency and security of data processing; the support vector machine model is used to combine seasonal factors and historical power consumption patterns for multi-dimensional comprehensive analysis, improving the accuracy and reliability of power demand forecasting; through accurate power demand forecasting, the imbalance between power supply and demand can be discovered in advance, providing early warning information for the management and dispatch of the power system, and avoiding sudden power shortages or surpluses; the optimized dispatching strategy based on the particle swarm optimization algorithm can dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to ensure the efficient use of power resources; Fault tree analysis technology evaluates potential risk points and generates emergency response plans, which improves the risk resistance of the power system and ensures that measures can be taken quickly in emergency situations to reduce losses; it automatically manages power resource shortages based on optimized scheduling results to ensure the normal operation of high-priority equipment and improve the stability and reliability of the power system; it generates power management decision-making recommendations to provide a scientific basis for power system managers to help them make more reasonable decisions and optimize power resource allocation; through real-time monitoring, accurate prediction, optimized scheduling and automatic management, it improves the operating efficiency of the entire power system and reduces operating costs; it ensures the normal operation of high-priority equipment, improves users' electricity experience and enhances user satisfaction; it optimizes the use of power resources, reduces unnecessary energy waste, and contributes to environmental protection and sustainable development.

[0069] Furthermore, by real-time monitoring of each power-consuming device and sending the data to the cloud server, preprocessing is performed in combination with historical power consumption data, and training and optimization are performed using the support vector machine model to generate power demand forecast values. A comprehensive analysis is performed in combination with seasonal factors, historical power consumption patterns, and external influencing factors to ultimately generate an accurate power demand forecast report; the accuracy of power demand forecasts is improved by combining real-time monitoring with historical data, as well as training and parameter optimization of the support vector machine model; a comprehensive analysis is performed in combination with seasonal factors, historical power consumption patterns, and external influencing factors to ensure that the forecast results are more comprehensive and reliable; accurate power demand forecasts can detect power supply and demand imbalances in advance, provide early warning information for power system management and dispatch, and avoid sudden power shortages or surpluses; the monitoring data is stored in a cloud server to facilitate unified data management and analysis, and improve the efficiency and security of data processing; accurate power demand forecast reports are generated to provide a scientific basis for power system managers, helping them make more reasonable decisions and optimize power resource allocation.

[0070] Furthermore, by evaluating the future balance of power supply and demand, it is possible to timely discover the imbalance of power supply and demand, generate early warning signals, and provide a basis for subsequent optimized scheduling; the optimized scheduling strategy based on the particle swarm optimization algorithm can dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to ensure the effective use of power resources; use the fault tree analysis technology to conduct risk assessment on the preliminary optimized scheduling plan, identify potential risk points, and improve the system's risk resistance; formulate an emergency response plan based on the risk assessment report to ensure that measures can be taken quickly in an emergency to reduce losses and ensure the stable operation of the power system; combine the preliminary optimized scheduling plan and the emergency response plan to comprehensively manage and schedule power resources, generate the final optimized scheduling results, and ensure the efficient and safe operation of the power system; the generated optimized scheduling results provide a scientific basis for power system managers to help them make more reasonable decisions, optimize power resource allocation, and improve overall operational efficiency.

[0071] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 A flowchart of a remote power supply monitoring method for shelter equipment based on the Internet of Things provided in an embodiment of the present application;

[0074] Figure 2 A schematic diagram of the structure of a remote power supply monitoring system for shelter equipment based on the Internet of Things provided in an embodiment of the present application;

[0075] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0077] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0079] Figure 1 A flowchart of a remote power supply monitoring method for shelter equipment based on the Internet of Things is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0080] 101. Monitor each electrical device in real time and send the monitoring data to the cloud server to obtain real-time monitoring data;

[0081] Real-time monitoring refers to the continuous data collection of power usage of electrical equipment through sensors, smart meters and other equipment. These data include but are not limited to current, voltage, power, energy consumption and other information. The collected data is sent to the cloud server through network transmission technology (such as 4G / 5G, Wi-Fi, etc.) to form real-time monitoring data.

[0082] In the embodiment of the present application, monitoring devices are installed on each power-consuming device, which collect power consumption data of the device regularly or continuously and upload the data to a cloud server via the network. The cloud server receives and stores the data to form a real-time updated database, which provides a basis for subsequent analysis.

[0083] Assume that there is a smart factory with a variety of electrical equipment, including motors on the production line, lighting systems, air conditioning systems, etc. In order to achieve real-time monitoring and optimal management of these devices, a monitoring system based on the Internet of Things (IoT) is deployed.

[0084] First, install and configure the equipment: install smart meters and sensors on each key power-consuming device. For example, install current sensors and voltage sensors on motors, and energy consumption monitors on lighting systems. Ensure that each sensor is connected to the factory's internal network via wired or wireless means (such as Wi-Fi, 4G / 5G). For wireless connections, ensure network coverage and stability.

[0085] Secondly, perform data collection: set the frequency of data collection, such as collecting current, voltage, power and other data once every minute. According to actual needs, the collection frequency can be adjusted to balance data accuracy and network load. Define a unified data format for subsequent processing and analysis. For example, the data format can be defined as structured data containing fields such as device ID, timestamp, current, voltage, power, etc.

[0086] Further, data transmission is performed: the data collected by the sensor is transmitted to the local gateway of the factory through the internal network. The local gateway is responsible for preliminary data processing and packaging. The local gateway securely transmits the packaged data to the cloud server via the Internet. The HTTPS protocol can be used to ensure the security of data transmission.

[0087] Furthermore, cloud data storage and processing are performed: the cloud server receives and stores data from various sensors. The data is stored in a database, which can be a relational database or a NoSQL database. The cloud server pre-processes the data, including data cleaning (removing outliers and missing values), data conversion (unit conversion, timestamp synchronization, etc.) and data aggregation (aggregating data by time interval).

[0088] Finally, real-time monitoring and alarm: The cloud platform provides a real-time monitoring interface to display the current status and historical data of each power-consuming device. Managers can access this information through the web interface or mobile application. Set threshold alarms. When the power consumption of a device exceeds the preset threshold, the system automatically sends an alarm notification to relevant personnel, such as through SMS, email, or APP push.

[0089] Here is a specific example:

[0090] Sensor data collection:

[0091] Motor A: Current = 10A, Voltage = 220V, Power = 2.2kW, Timestamp = 2024-11-26 23:05:00 Lighting System B: Energy consumption = 500Wh, Timestamp = 2024-11-26 23:05:00

[0092] Data upload:

[0093] The sensor data is transmitted to the local gateway via Wi-Fi. The local gateway packages the data into a structured data format and transmits it securely to the cloud server via the HTTPS protocol.

[0094] Cloud data processing:

[0095] After receiving the data, the cloud server cleans and preprocesses the data and then stores it in the database.

[0096] Data cleaning example: If the current value of a data point is detected to be abnormally high (e.g., outside the normal range), it is marked as an outlier and removed.

[0097] Data conversion example: Convert timestamps to UTC time to ensure that the time base of all data is consistent.

[0098] Data aggregation example: Summarize the average power and total energy consumption of each device on an hourly basis.

[0099] Real-time monitoring and alarm:

[0100] The real-time current, voltage and power graphs of motor A are displayed via the web interface.

[0101] If the power of motor A exceeds 2.5kW, the system automatically sends an alarm notification to the maintenance personnel.

[0102] Through the above embodiments, real-time monitoring of various power-consuming equipment is achieved, and the monitoring data is safely and efficiently transmitted to the cloud server, providing a solid foundation for subsequent power demand forecasting and optimized scheduling.

[0103] 102. Based on the real-time monitoring data, use the support vector machine model to predict the future trend of electricity demand changes, conduct a multi-dimensional comprehensive analysis based on seasonal factors and historical electricity consumption patterns, and generate an accurate electricity demand forecast report;

[0104] Support vector machine (SVM) is a supervised learning method used for classification and regression analysis. In this step, the SVM model is used to predict the future trend of electricity demand. Seasonal factors refer to the electricity consumption patterns in different seasons, and historical electricity consumption patterns refer to electricity consumption data over a period of time in the past. Multi-dimensional comprehensive analysis refers to comprehensive analysis combining multiple factors (such as time, weather, holidays, etc.) to improve the accuracy of the forecast.

[0105] In the embodiment of the present application, first, real-time monitoring data is obtained from the cloud server and combined with historical electricity consumption data. Then, the SVM model is used to train the data and improve the prediction accuracy by optimizing the model parameters. The model will take into account seasonal factors, historical electricity consumption patterns, and other external factors (such as weather, social activities, etc.), and finally generate an accurate electricity demand forecast report.

[0106] Optionally, in step 102, based on the real-time monitoring data, a support vector machine model is used to predict the future trend of electricity demand changes, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report, including:

[0107] Perform real-time monitoring on each power-consuming device, and send the monitoring data to a cloud server to obtain the real-time monitoring data; utilize the real-time monitoring data, in combination with historical power consumption data, pre-process the data based on seasonal factors and historical power consumption patterns, and obtain the pre-processed data; train a support vector machine model based on the pre-processed data, and improve the prediction accuracy by optimizing model parameters; use the trained model to predict future trends in power demand changes to obtain power demand prediction values; based on the power demand prediction values, conduct a comprehensive analysis in combination with seasonal factors, historical power consumption patterns, and external influencing factors to generate an accurate power demand prediction report.

[0108] The method includes training the support vector machine model based on the preprocessed data, improving the prediction accuracy by optimizing the model parameters, and using the trained model to predict the future trend of power demand changes to obtain a power demand prediction value, including:

[0109] The preprocessed data is used as the input of the support vector machine model to perform model training to obtain a preliminarily trained support vector machine model; based on the preliminarily trained support vector machine model, the model parameters are optimized using a cross-validation method to improve the generalization ability and prediction accuracy of the model to obtain an optimized support vector machine model; the optimized support vector machine model is used in combination with the latest real-time monitoring data and the preprocessing process to predict the trend of electricity demand changes in a certain period of time in the future to obtain a preliminary electricity demand forecast value; based on the preliminary electricity demand forecast value, a comprehensive correction is performed in combination with seasonal factors, historical electricity consumption patterns and external influencing factors to generate a final electricity demand forecast report to obtain the electricity demand forecast value.

[0110] The method of using the real-time monitoring data, combining the historical electricity consumption data, and preprocessing the data based on seasonal factors and historical electricity consumption patterns to obtain the preprocessed data includes:

[0111] Using the real-time monitoring data from each power-consuming device and combining it with historical power consumption records, these data are collected and integrated to obtain a comprehensive database; based on the comprehensive database, the data therein is cleaned to remove abnormal values ​​and missing values ​​to obtain cleaned data; using the cleaned data, seasonal and periodic power consumption patterns are analyzed to identify the power consumption characteristics of different time periods and the power consumption patterns of different seasons to obtain power consumption pattern analysis results; based on the power consumption pattern analysis results, statistical methods and data mining techniques are used to deeply process the cleaned data, extract key features, and obtain feature extraction results; calculate the impact of external influencing factors on the power consumption pattern, quantify the external influencing factors and add them to the feature extraction results for further processing to improve the accuracy and reliability of the prediction model and obtain feature data after considering external factors; integrate the feature data after considering external factors to form preprocessed data.

[0112] In the embodiment of the present application, it is assumed that there is a smart industrial park with a variety of electrical equipment, including motors on production lines, lighting systems, air conditioning systems, etc. In order to achieve real-time monitoring and optimal management of these devices, a monitoring system based on the Internet of Things (IoT) is deployed, and a support vector machine (SVM) model is used to predict power demand.

[0113] First, install smart meters and sensors on each key power-consuming device to collect current, voltage, power and other data every minute, and send the data to the cloud server via Wi-Fi or 4G / 5G network. Obtain the power consumption records of the past year from the cloud server, including the power consumption of each device, timestamp and other information. Integrate the real-time monitoring data and historical power consumption data into a comprehensive database to form a data set containing timestamps, device identification, power consumption and other information.

[0114] Secondly, remove outliers and missing values. For example, if the current value of a data point is abnormally high (for example, exceeding the normal range), mark it as an outlier and remove it. At the same time, fill in missing values, which can be filled using interpolation or the previous valid value. Analyze the electricity consumption characteristics of different time periods (such as weekdays, weekends, and holidays), as well as the electricity consumption patterns of different seasons (spring, summer, autumn, and winter). For example, the electricity consumption of air conditioning systems is usually higher in summer.

[0115] Furthermore, statistical methods and data mining techniques, such as cluster analysis and association rule analysis, are used to deeply process the cleaned data and extract key features. For example, the daily average power consumption and peak power consumption of each device are calculated. External influencing factors, such as weather conditions (temperature, humidity), social activities (holidays, large-scale events), etc., are considered, and these factors are quantified and added to the feature extraction results. For example, hot weather will lead to an increase in the power consumption of the air conditioning system.

[0116] Furthermore, the preprocessed data is used as the input of the support vector machine model for preliminary training to obtain a preliminarily trained support vector machine model. The model parameters are optimized using the cross-validation method to improve the generalization ability and prediction accuracy of the model. For example, K-fold cross-validation is used to select the best kernel function parameters and regularization parameters. The optimized support vector machine model is used in combination with the latest real-time monitoring data and preprocessing process to predict the trend of electricity demand changes in a certain period of time in the future and obtain a preliminary electricity demand forecast value.

[0117] Finally, based on the preliminary power demand forecast, a comprehensive correction is made in combination with seasonal factors, historical power consumption patterns, and external factors. For example, if the temperature is predicted to rise in the next week, the forecast value is adjusted to reflect the increase in power consumption of the air conditioning system. Based on the corrected forecast value, the final power demand forecast report is generated. The report includes information such as the total power consumption forecast for the next period of time, the power consumption forecast for each device, and the potential power supply and demand imbalance warning.

[0118] Here is a specific example:

[0119] Data collection and integration:

[0120] Motor A: Current = 10A, Voltage = 220V, Power = 2.2kW, Timestamp = 2024-11-26 23:05:00 Lighting System B: Energy consumption = 500Wh, Timestamp = 2024-11-26 23:05:00

[0121] Historical data: Electricity usage records for the past year, including daily electricity usage, timestamps, and other information.

[0122] Data preprocessing:

[0123] Cleaned data: The dataset after removing outliers and missing values.

[0124] Seasonal and cyclical analysis: Identify patterns of higher electricity usage in air conditioning systems during the summer.

[0125] Feature extraction: Calculate the daily average power consumption, peak power consumption, etc. of each device.

[0126] Quantification of external influencing factors: Quantify weather conditions (such as temperature and humidity) and social activities (such as holidays) and add them to the feature extraction results.

[0127] Model training and optimization:

[0128] Initial training: Use the preprocessed data to train the support vector machine model.

[0129] Parameter optimization: K-fold cross validation was used to optimize model parameters.

[0130] Optimized model: Use the optimized model to predict electricity demand for the next week.

[0131] Comprehensive analysis and report generation:

[0132] Comprehensive correction: Comprehensive correction is performed based on the predicted value and external influencing factors.

[0133] Generate report: Generate a power demand forecast report for the next week, including total power consumption forecast, power consumption forecast for each device, potential power supply and demand imbalance warning and other information.

[0134] Through the above-mentioned embodiments, real-time monitoring of various power-consuming equipment is achieved, and an accurate power demand forecast report is generated by combining historical power consumption data and external influencing factors, providing a scientific basis for subsequent power resource management and scheduling.

[0135] The present application takes into account that in the power system, accurate prediction of future power demand is essential to ensure power supply and demand balance, optimize scheduling and resource management. By analyzing historical power consumption data, seasonal factors and external influencing factors, a mathematical model can be constructed to predict future power consumption and power demand. The two formulas E(t) and P(t) used in this embodiment are designed based on time series analysis, statistical feature extraction and seasonal power consumption pattern analysis.

[0136] Optionally, the cleaned data is used to analyze seasonal and periodic electricity consumption patterns, identify electricity consumption characteristics in different time periods and electricity consumption patterns in different seasons, and obtain electricity consumption pattern analysis results, including:

[0137] Before calculating the electricity consumption E(t) at time t, a comprehensive electricity consumption pattern model is constructed by performing time series analysis, statistical feature extraction, and seasonal electricity consumption pattern analysis on the cleaned data to provide basic data for the calculation of E(t);

[0138]

[0139] Among them, E(t) is the electricity consumption at time t, reflecting the characteristics of electricity consumption in different time periods; α, β, γ, δ, ∈ are model parameters, obtained by fitting historical data, used to adjust the sensitivity and accuracy of the model; t is a time variable, indicating a specific moment or time period; T is the cycle length; D is the cycle length; φ, ψ are phase shifts, used to adjust the time starting point of the periodic function; S(t) is the seasonal electricity consumption pattern at time t, reflecting the difference in electricity consumption in different seasons; t0 is a specific time point, used to adjust the center position of the Gaussian function; σ is the standard deviation, used to control the width of the Gaussian function;

[0140] After calculating E(t), the power consumption data is smoothed, and the power demand forecast value P(t) is generated by combining historical power demand data and external influencing factors using the time series prediction model and optimization algorithm;

[0141]

[0142] Among them, P(t) is the predicted value of electricity demand at time t, which is used to evaluate the changing trend of future electricity demand; η, ζ, θ, κ, ρ, v are model parameters, which are obtained by fitting historical data and are used to adjust the sensitivity and accuracy of the model; E(t) is the electricity consumption at time t, which reflects the characteristics of electricity consumption in different time periods; μ is the average value of electricity consumption, which is used to standardize electricity consumption data and improve the stability of the model; t is a time variable, which represents a specific moment or time period; Y is the annual cycle length, which is used to capture the annual electricity consumption pattern; Q is the quarterly cycle length, which is used to capture the quarterly electricity consumption pattern; ω, λ are phase offsets, which are used to adjust the time starting point of the periodic function; F(t) is the function affected by external factors at time t;

[0143] After calculating P(t), a detailed power consumption pattern analysis report is generated through verification and calibration, visualization, and sensitivity analysis, providing a scientific basis for the management and dispatch of the power system.

[0144] The purpose of this formula is to comprehensively consider multiple factors such as periodicity, seasonality, and external influences in formulas E(t) and P(t) to improve the accuracy of the prediction; use nonlinear functions (such as sinusoidal functions, logarithmic functions, Gaussian functions, etc.) to capture the complex changes in power consumption patterns and improve the fitting ability of the model; obtain model parameters by fitting historical data so that the model can adapt to different power consumption patterns and environmental conditions.

[0145] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0146]

[0147] Periodic factors: Using the sine function and To capture changes in daily and weekly cycles.

[0148] Seasonality: Use the logarithmic function log(1+S(t)) to capture seasonal electricity usage patterns.

[0149] Gaussian function: Use Gaussian function To capture peak or trough electricity consumption at specific points in time.

[0150] Constant term: Use the constant term ∈ to adjust the overall power consumption level.

[0151] The following is a brief introduction to how to obtain the parameters of the formula:

[0152] α, β, γ, δ, ∈: These parameters are obtained by fitting historical electricity consumption data. These parameters can be determined using methods such as least squares and maximum likelihood estimation so that the model can best fit the historical data. T and D: represent the length of the daily cycle and weekly cycle, respectively. Usually, T = 24 hours (a day) and D = 7 days (a week). These values ​​can be adjusted according to the periodic characteristics of the actual electricity consumption data. φ and ψ: Phase offset, used to adjust the time starting point of the periodic function. These parameters are also obtained by fitting historical data. S(t): Seasonal electricity consumption pattern, reflecting the difference in electricity consumption in different seasons. It can be extracted from historical data through methods such as cluster analysis and regression analysis.

[0153] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0154]

[0155] Electricity consumption standardization: using the exponential function exp(-ζ(E(t)-μ) 2 ) to standardize electricity consumption data and improve model stability.

[0156] Annual Cyclic Factor: Using the Cosine Function To capture annual cyclical changes.

[0157] Quarterly Cyclic Factor: Using the Sine Function To capture quarterly cyclical changes.

[0158] External Influencing Factors: Using the Square Root Function To capture the impact of external factors.

[0159] Constant term: A constant term ν is used to adjust the overall electricity demand level.

[0160] The following is a brief introduction to how to obtain the parameters of the formula:

[0161] η,ζ,θ,κ,ρ,v: These parameters are obtained by fitting historical electricity demand data. These parameters can be determined by methods such as least squares method and maximum likelihood estimation so that the model can best fit the historical data;μ: The average value of electricity consumption, used to standardize electricity consumption data and improve the stability of the model;Y and Q: represent the length of the annual cycle and the quarterly cycle, respectively. Usually, Y = 365 days (a year) and Q = 90 days (a quarter). These values ​​can be adjusted according to the periodic characteristics of actual electricity demand data;ω and λ: Phase shift, used to adjust the time starting point of the periodic function. These parameters are also obtained by fitting historical data;F(t): A function affected by external factors, such as weather temperature, social activities, etc. The specific form of F(t) can be determined by relevant data analysis.

[0162] Assume data:

[0163] Historical electricity usage data: electricity usage per hour over the past year.

[0164] Economical electricity consumption pattern S(t): higher electricity consumption in summer and lower electricity consumption in winter.

[0165] External influencing factors F(t): weather temperature T weather .

[0166] Parameter settings:

[0167] E(t) parameters: α=1.5; β=0.8; γ=0.3; δ=0.2; ∈=50; T=24 hours; D=7 days; φ=0.5; ψ=0.3; t0=14 hours; σ=2; : η=1.2; ζ=0.1; θ=0.5; κ=0.3; ρ=0.2; ν=10; Y=365 days; Q=90 days; ε=0.4; λ=0.2; μ=100kW; F(t)=0.1×T weather

[0168] Calculation process:

[0169] Calculate E(t):

[0170] A specific time point t = 14 hours (2 pm) was selected.

[0171] Assume S(t) = 1.2 (electricity consumption is higher in summer).

[0172] Assume T weather =30 degrees (hot weather).

[0173] E(14)=1.5·sin(1.17+0.5)+0.8·sin(1.26+0.3)+0.3·log(2.2)+0.2

[0174] exp(0)+50

[0175] E(14)≈52.7347kW

[0176] Calculate P(t)

[0177] Use E(14)≈52.7347kW.

[0178] Assume F(14)=0.1×30=3.

[0179]

[0180] Conclusion Explanation:

[0181] E(14)≈52.7347kW: At 2 p.m., the predicted power consumption is about 52.7347 kW. This reflects the power consumption characteristics during this time period, including daily cycles, weekly cycles, seasonal factors, and peak power consumption at specific time points.

[0182] P(14)≈10.8924kW: At 2pm, the predicted power demand is about 10.8924kW. This reflects the changing trend of future power demand, combining the influence of power consumption, annual periodicity, quarterly periodicity and external factors (such as hot weather).

[0183] Assume that at 2 pm on a certain day, the calculated power consumption E(14)≈52.7347 kW and the power demand P(14)≈10.8924 kW.

[0184] Electricity consumption E(14)≈52.7347kW:

[0185] Assuming that the normal power consumption range is between 40KW and 60KW, since 40kW<52.7347kW<60kW, the power consumption is within the normal range and no special response measures are required.

[0186] Power demand P(14)≈10.8924kW:

[0187] Assuming that the normal range of power demand is between 5KW and 15KW, since 5kW<10.8924kW<15kW, the power demand is also within the normal range and no special response measures are required.

[0188] Through the above calculations, we get the specific power consumption and power demand forecast values. These results can be used to generate detailed power consumption pattern analysis reports, providing a scientific basis for the management and dispatch of power systems. For example, we can adjust the output power of the generator set in advance according to the forecast results, optimize the working schedule of the power equipment, and ensure the balance of power supply and demand.

[0189] 103. Based on the power demand forecast report, when an imbalance between power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and a fault tree analysis technique is used to evaluate potential risk points, generate an emergency response plan and optimize the scheduling results;

[0190] Particle swarm optimization (PSO) algorithm is a heuristic optimization algorithm used to solve complex optimization problems. In this step, the PSO algorithm is used to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to balance the supply and demand of electricity. Fault tree analysis (FTA) is a system safety analysis method used to identify and evaluate potential risk points. Emergency response plans are response measures formulated for possible emergencies.

[0191] In the embodiment of the present application, according to the power demand forecast report, if it is found that there is an imbalance in power supply and demand in a certain period of time in the future, the optimization scheduling strategy based on the PSO algorithm is started. This strategy ensures the effective use of power resources by dynamically adjusting the output power of the generator set or the working schedule of the power-consuming equipment. At the same time, the FTA technology is used to conduct a risk assessment on the preliminary optimization scheduling plan, identify potential risk points, and generate corresponding emergency response plans. Finally, the optimization scheduling strategy and the emergency response plan are combined to generate the optimization scheduling result.

[0192] Optionally, in step 103, based on the power demand forecast report, when an imbalance in power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and a fault tree analysis technique is used to evaluate potential risk points, generate an emergency response plan and an optimization scheduling result, including:

[0193] Using the power demand forecast report, the future power supply and demand balance is evaluated and processed, and when a power supply and demand imbalance is predicted, a power supply and demand imbalance warning signal is generated;

[0194] Based on the power supply and demand imbalance warning signal, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan;

[0195] Using fault tree analysis technology, risk assessment is performed on the preliminary optimization scheduling plan to generate a risk assessment report;

[0196] Based on the risk assessment report, conduct an in-depth analysis of various potential risk points and the chain reactions they may cause, and obtain an emergency response plan;

[0197] Combined with the preliminary optimization scheduling plan and the emergency response plan, the management and scheduling of power resources are comprehensively processed to generate an optimization scheduling result.

[0198] Optionally, the use of fault tree analysis technology to perform risk assessment processing on the preliminary optimization scheduling plan to generate a risk assessment report includes:

[0199] Using fault tree analysis technology, systematically analyze the key links and potential risk points in the preliminary optimization scheduling plan, identify various factors that may cause power system failures, and obtain a list of risk factors;

[0200] Based on the risk factor list, a fault tree model is constructed to clarify the logical relationship between various risk factors and their influence on the overall system stability, and a fault tree structure diagram is obtained;

[0201] Using the fault tree structure diagram, qualitative and quantitative risk assessment is performed to calculate the probability of occurrence of each risk event and the severity of its consequences, thereby obtaining risk assessment data;

[0202] Based on the risk assessment data, analyze the impact of different risk events on the balance of power supply and demand, evaluate the risks that may arise during the implementation of the optimized scheduling plan, and obtain risk assessment conclusions;

[0203] Based on the risk assessment conclusions, risk prevention and control recommendations are put forward and a risk assessment report is formed.

[0204] Suppose there is a smart grid system that manages the power supply and demand of a city. Through real-time monitoring and historical data analysis, the system generates a power demand forecast report for the next week. According to the forecast report, it is found that there will be an imbalance in power supply and demand on a certain day. In order to deal with this situation, the system starts an optimization scheduling strategy based on the particle swarm optimization algorithm (PSO), and uses the fault tree analysis technology (FTA) to evaluate potential risk points, generate emergency response plans and optimize scheduling results.

[0205] First, based on the generated power demand forecast report, the future power supply and demand balance is evaluated. When the power supply and demand imbalance is predicted for a certain day, a power supply and demand imbalance warning signal is generated. For example, the forecast shows that on November 30, 2024, power demand will exceed supply capacity by 5%.

[0206] Secondly, based on the early warning signal of imbalance between power supply and demand, the optimization scheduling strategy based on the particle swarm optimization algorithm (PSO) is started. The output power of the generator set and the working schedule of the power equipment are dynamically adjusted to balance the power supply and demand. For example, the output power of generator set A is increased, and the production schedule of factory B is adjusted to operate during the off-peak period. A preliminary optimization scheduling plan is obtained, including the output power adjustment plan of each generator set and the working schedule adjustment plan of each power equipment.

[0207] Furthermore, the fault tree analysis technology is used to systematically analyze the key links and potential risk points in the preliminary optimization scheduling plan to identify various factors that may cause power system failures. For example, the overload of generator set A, the production line failure of factory B, etc. Based on the risk factor list, a fault tree model is constructed to clarify the logical relationship between each risk factor and its impact on the overall system stability. For example, the overload of generator set A may cause power outages, thereby affecting the stability of the entire power grid. Using the fault tree structure diagram, qualitative and quantitative risk assessments are performed to calculate the probability of each risk event and the severity of its consequences. For example, the probability of overload of generator set A is 1%, and the severity of the consequences is high. Based on the risk assessment data, the impact of different risk events on the balance of power supply and demand is analyzed, and the risks that may arise during the implementation of the optimization scheduling plan are evaluated. For example, the overload of generator set A may cause power outages, affecting 50% of users. Combined with the risk assessment data, risk prevention and control suggestions are put forward to form a risk assessment report. For example, it is recommended to add a standby generator set and formulate an emergency plan to deal with the overload of generator set A.

[0208] Finally, based on the risk assessment report, we deeply analyze various potential risk points and the chain reactions they may cause, and formulate emergency response plans. For example, if generator set A fails, we immediately start the backup generator set C and notify the maintenance team to repair it. Combined with the preliminary optimization scheduling plan and the emergency response plan, we conduct a comprehensive process on the management and scheduling of power resources to generate the final optimization scheduling results. For example, the final optimization scheduling plan includes the output power adjustment plan of generator set A, the production schedule adjustment plan of factory B, and the specific measures of the emergency response plan.

[0209] Here is a specific example:

[0210] Assessment of electricity supply and demand balance:

[0211] Electricity Demand Forecast Report: By November 30, 2024, electricity demand is expected to be 1,200MW, while supply capacity is 1,140MW.

[0212] Early warning signal: Generates early warning signals for imbalance in electricity supply and demand, indicating that measures need to be taken to balance supply and demand.

[0213] Start the optimized scheduling strategy:

[0214] Dynamic adjustment processing: Increase the output power of generator set A to 110%; adjust the production schedule of factory B to run from 1 am to 5 am.

[0215] Preliminary optimization scheduling plan: the output power of generator set A is adjusted to 110%, and the production schedule of factory B is adjusted to 1:00 to 5:00 in the morning.

[0216] Risk Assessment Process:

[0217] List of risk factors: overload of generator set A, failure of production line of factory B.

[0218] Fault tree model: Overload of generator set A may cause power outage, affecting 50% of users; failure of the production line of factory B may cause production delays.

[0219] Qualitative and quantitative risk assessment: The probability of overloading of generator set A is 1%, and the severity of the consequences is high; the probability of production line failure in factory B is 2%, and the severity of the consequences is medium.

[0220] Risk assessment data: Overload of generator set A may cause power outage, affecting 50% of users; failure of the production line of factory B may cause production delays, affecting 10% of output.

[0221] Risk assessment conclusion: It is recommended to add backup generator sets and formulate emergency plans to deal with the overload of generator set A; it is recommended to strengthen the maintenance of the production line of factory B to reduce the occurrence rate of failures.

[0222] Emergency response plan and optimized dispatch results:

[0223] Emergency response plan: If generator set A fails, immediately start the backup generator set C and notify the maintenance team to carry out emergency repairs; if the production line B of the factory fails, immediately switch to the backup production line.

[0224] Comprehensive processing: The final optimized scheduling plan includes the output power adjustment plan of generator set A, the production schedule adjustment plan of factory B, and the specific measures of the emergency response plan.

[0225] Through the above embodiments, optimized scheduling and risk assessment based on power demand forecast reports are achieved, the stable operation of the power system is ensured, and a scientific basis and emergency measures are provided for dealing with potential risks.

[0226] The present application takes into account that in the power system, it is crucial to ensure the balance of power supply and demand. When an imbalance in power supply and demand is predicted at a certain point in the future, it is necessary to start an optimization scheduling strategy to adjust the output power of the generator set or the working schedule of the power-consuming equipment to achieve a balance between supply and demand. The two formulas G(t) and O(t) used in this embodiment are designed based on the particle swarm optimization algorithm (PSO) to calculate the gap between power supply and demand and generate the optimization scheduling target value.

[0227] Optionally, based on the power supply and demand imbalance warning signal, an optimization scheduling strategy based on a particle swarm optimization algorithm is started to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan, including:

[0228] Before calculating the power supply and demand gap G(t) at time t, the power supply and demand model is constructed by analyzing and preprocessing the power demand forecast and historical operation data to prepare basic data for the calculation of G(t);

[0229]

[0230] Where G(t) is the gap between electricity supply and demand at time t, reflecting the degree of imbalance between electricity supply and demand; N is the number of generating units; M is the number of power-consuming devices; w i is the weight of the i-th generator set, reflecting its importance in the power system; P gen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; v j is the weight of the jth electrical equipment, reflecting its importance in the power system; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j (t) is the power consumption adjustment of the jth electrical equipment at time t;

[0231] After calculating G(t), normalization is performed, the power adjustment ratio is calculated, and the particle swarm optimization algorithm is used to adjust power generation and power consumption, and finally the optimized scheduling target value O(t) is generated;

[0232]

[0233] Among them, O(t) is the optimized dispatch target value at time t, reflecting the effect of the optimized dispatch scheme; η, ζ, θ, k are model parameters, obtained by fitting historical data, and used to adjust the sensitivity and accuracy of the model; G(t) is the gap between power supply and demand at time t, reflecting the degree of imbalance between power supply and demand; N is the number of generators; M is the number of power-consuming equipment; Pgen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; P max,i is the maximum output power of the i-th generator set; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j (t) is the power consumption adjustment of the jth electrical equipment at time t; P max,j is the maximum power consumption of the jth electrical equipment;

[0234] After calculating O(t), a detailed optimization scheduling plan is formed through the steps of verification and calibration, visualization, and sensitivity analysis to guide power system management and scheduling.

[0235] The purpose of this formula is that formulas G(t) and O(t) comprehensively consider the current status, weight and maximum capacity of generators and power-consuming equipment to improve the accuracy and practicality of optimized scheduling; use nonlinear functions (such as exponential functions) to capture the impact of the gap between electricity supply and demand on the optimization scheduling target and improve the fitting ability of the model; obtain model parameters by fitting historical data so that the model can adapt to different electricity supply and demand situations and environmental conditions.

[0236] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0237]

[0238] The following is a brief introduction to how to obtain the parameters of the formula:

[0239] This section calculates the weighted total output power of all generators at time t. Each generator's current output power is added to its power adjustment, then multiplied by its weight, and finally the results of all generators are added together. This reflects the total generating capacity of the entire power system at time t.

[0240] This section calculates the weighted total power consumption of all power consumers at time t. The current power consumption of each power consumer is added to its power consumption adjustment, then multiplied by its weight, and finally the results of all power consumers are added together. This reflects the total power demand of the entire power system at time t.

[0241] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0242]

[0243] The following is a brief introduction to how to obtain the parameters of the formula:

[0244] η·exp(-ζ·G(t) 2 ) is designed to ensure that when the gap between electricity supply and demand is large, the optimal dispatch target value O(t) will be significantly reduced, thereby prompting the system to take more proactive measures to reduce the gap between supply and demand. This helps to improve the stability and reliability of the system.

[0245] This item is designed to ensure that the power utilization of the generator set is properly considered. Higher power utilization means that the generator set is closer to its maximum output capacity, which may lead to higher operating costs and maintenance requirements. By introducing this item, the optimized scheduling plan can avoid over-use of generator sets while ensuring the balance between supply and demand, thereby extending equipment life and reducing costs.

[0246] This item is designed to ensure that the power utilization of electrical equipment is properly considered. Higher power utilization means that the electrical equipment is closer to its maximum power capacity, which may lead to higher energy consumption and operating costs. By introducing this item, the optimized scheduling plan can avoid overuse of electrical equipment while ensuring the balance between supply and demand, thereby saving energy and reducing costs.

[0247] Assume data:

[0248] Number of generator sets N = 3

[0249] Number of electrical equipment M = 4

[0250] Current time t = 14 hours (2pm)

[0251] Generator weights w1 = 0.4, w2 = 0.3, w3 = 0.3

[0252] Weights of electrical equipment v1=0.3,v2=0.25,v3=0.25,v4=0.2

[0253] Current output power P gen,1 (14) = 100kW, P gen,2 (14)=80kW,P gen,3 (14) = 70kW

[0254] Current power consumption P load,1 (14) = 60kW, P load,2 (14)=50kW,P load,3 (14) = 40kW, P load,4 (14) = 30kW

[0255] Power adjustment ΔP gen,1 (14)=10kW,ΔP gen,2(14)=5kW,ΔP gen,3 (14) = 0kW

[0256] Power consumption adjustment ΔP load,1 (14)=0kW,ΔP load,2 (14)=5kW,ΔP load,3 (14)=10kW,ΔP load,4 (14) = 15kW

[0257] Maximum output power P max,1 =120kW,P max,2 =100kW,P max,3 =90kW

[0258] Maximum power consumption P max,1 =70kW,P max,2 =60kW,P max,3 =50kW,P max,4 =40kW

[0259] Model parameters η=1.2, ζ=0.1, θ=0.5, k=0.3

[0260] Calculation process:

[0261] Calculate G(t)

[0262]

[0263] Compute O(t)

[0264]

[0265] Setting a high electricity supply-demand gap threshold G high =50kW and low power supply and demand gap threshold G low =10kW. At 2 pm, the power supply and demand gap G(14)≈37.25kW exceeds the lower threshold but does not reach the upper threshold, indicating that there is a certain degree of imbalance in power supply and demand, and optimization scheduling measures need to be taken.

[0266] Set a high optimization scheduling target value threshold O high =3.0 and low optimization scheduling target value threshold O low =1.5. At 2 pm, the optimized dispatch target value O(14)≈2.44189 is between the upper and lower thresholds, indicating that the current optimized dispatch scheme works well, but further optimization is still needed to improve the overall efficiency of the power system.

[0267] Through the above calculations, the specific power supply and demand gap and the optimized dispatch target value are obtained. These results can be used to generate detailed optimized dispatch plans to guide the management and dispatch of power systems. For example, the output power of the generator set and the working schedule of the power equipment can be adjusted according to the optimized dispatch target value to ensure the balance of power supply and demand.

[0268] 104. Automatically manage the power resource shortage situation based on the optimization scheduling results, ensure the normal operation of high-priority equipment, and generate power management decision suggestions.

[0269] Automatic management refers to monitoring and dispatching power resources through an automated system to ensure the stable operation of the power system. High-priority equipment refers to equipment with important functions or critical tasks in the power system, and its power supply must be guaranteed first. Power management decision recommendations are made based on the results of optimized dispatching and are used to guide the management and dispatching of the power system.

[0270] In the embodiment of the present application, according to the optimization scheduling results, the system automatically manages the power resources and gives priority to the power supply of high-priority equipment. By real-time monitoring of the usage status of power resources, the power distribution is dynamically adjusted to prevent local shortages. At the same time, the system generates detailed power management decision suggestions, including the adjustment of the operating status of the generator set, the optimization of the use plan of the power equipment, etc., to provide a scientific basis for the managers of the power system and ensure the efficient and safe operation of the power system.

[0271] Optionally, the automatic management of power resource shortage based on the optimization scheduling result in step 104 to ensure normal operation of high-priority equipment and generate power management decision suggestions includes:

[0272] The optimization scheduling result is used to automatically adjust the distribution of power resources to obtain a power resource allocation plan; based on the power resource allocation plan, a power resource management mechanism is established to monitor the use status of power resources in real time, dynamically adjust power distribution, and obtain a power resource management mechanism; according to the power resource management mechanism, an emergency response level is set in the case of power resource shortage, and response measures of different levels are defined to obtain an emergency response level setting; in combination with the optimization scheduling result and the emergency response level setting, a comprehensive assessment is made on the operating status of the power system, and specific power management decision suggestions are put forward to obtain power management decision suggestions.

[0273] Assume that there is a smart grid system that manages the power supply and demand of a city. Through real-time monitoring, power demand forecasting and optimization scheduling strategy, the system has generated optimized scheduling results. In order to ensure the normal operation of high-priority equipment under the condition of tight power resources and generate power management decision recommendations, the system will perform the following steps.

[0274] First, according to the optimization scheduling results, the allocation of power resources is automatically adjusted. For example, the optimization scheduling results show that the output power of generator set A is increased to 110%, and the production schedule of factory B is adjusted to 1:00 a.m. to 5:00 a.m. Generate a power resource allocation plan, including the specific output power of each generator set, the working schedule of each power-consuming equipment, etc. For example, the output power of generator set A is 110%, and the production time of factory B is from 1:00 a.m. to 5:00 a.m., and the power supply priority of hospital C is the highest, and its power supply must be ensured.

[0275] Secondly, establish a power resource management mechanism to monitor the usage status of power resources in real time. For example, through smart meters and sensors, collect current, voltage, power and other data of each device once a minute and transmit them to the cloud server for analysis. According to the real-time monitoring data, dynamically adjust the power distribution. For example, if it is found that the power consumption in a certain area suddenly increases, the system will automatically adjust the power distribution in other areas to ensure overall balance.

[0276] Furthermore, according to the power resource management mechanism, the emergency response level in the case of power resource shortage is set. For example, three emergency response levels are defined:

[0277] Level 1 response: When the power gap is less than 5%, start the backup generator set and notify non-critical users to reduce power consumption.

[0278] Level 2 response: When the power gap is between 5% and 10%, start the backup generator set and limit the power consumption of some non-critical users.

[0279] Level 3 response: When the power gap exceeds 10%, start all backup generators and implement rotating power outages to ensure power supply to high-priority equipment (such as hospitals and traffic lights).

[0280] Finally, the operation status of the power system is comprehensively evaluated by combining the optimization dispatch results and the emergency response level setting. For example, the current power gap is 7%, which belongs to the second-level response level.

[0281] Decision-making suggestions: Propose specific power management decision suggestions. For example, start the backup generators B and C, limit the power consumption of factories D and E, and ensure the power supply of hospital C and traffic lights.

[0282] Here is a specific example:

[0283] Generator A outputs 110% power and factory B operates from 1am to 5am.

[0284] Power resource allocation plan: Generator set A outputs 110% power, factory B’s production time is from 1:00 to 5:00 in the morning, and hospital C has the highest power supply priority.

[0285] Establish a power resource management mechanism: Through smart meters and sensors, the current, voltage, power and other data of each device are collected every minute. According to the real-time monitoring data, the power distribution is adjusted dynamically. For example, if the power consumption in a certain area suddenly increases, the system automatically adjusts the power distribution in other areas.

[0286] Set emergency response levels: Define three emergency response levels, including starting backup generators, limiting electricity use by non-critical users, and other measures.

[0287] Comprehensive assessment and decision-making recommendations: The current power shortage is 7%, which is a secondary response level. Start backup generators B and C, limit the power consumption of factories D and E, and ensure the power supply of hospital C and traffic lights.

[0288] Through the above embodiments, automatic management of power resources based on optimized scheduling results is achieved, ensuring the normal operation of high-priority equipment under conditions of tight power resources, and generating specific power management decision recommendations, thereby improving the stability and reliability of the power system.

[0289] Figure 2 A schematic diagram of a remote power supply monitoring system for shelter equipment based on the Internet of Things is provided for the present application embodiment. Figure 2 As shown, the device comprises:

[0290] The monitoring module 21 is used to monitor each electrical device in real time and send the monitoring data to the cloud server to obtain the real-time monitoring data;

[0291] The prediction module 22 is used to predict the future power demand change trend based on the real-time monitoring data using a support vector machine model, and to generate an accurate power demand prediction report by performing a multi-dimensional comprehensive analysis based on seasonal factors and historical power consumption patterns;

[0292] The adjustment module 23 is used to start the optimization scheduling strategy based on the particle swarm optimization algorithm based on the power demand forecast report, dynamically adjust the output power of the generator set or the working schedule of the power equipment, use the fault tree analysis technology to evaluate the potential risk points, and generate an emergency response plan and optimization scheduling results when an imbalance between power supply and demand is predicted;

[0293] The management module 24 is used to automatically manage the power resource shortage situation based on the optimization scheduling result, ensure the normal operation of high-priority equipment, and generate power management decision suggestions.

[0294] Figure 2 The remote power supply monitoring system for shelter equipment based on the Internet of Things can be executed Figure 1The implementation principle and technical effect of the remote power supply monitoring method for shelter equipment based on the Internet of Things described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the remote power supply monitoring system for shelter equipment based on the Internet of Things in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0295] In one possible design, Figure 2 The remote power supply monitoring system for cabin equipment based on the Internet of Things of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0296] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0297] The processing component 32 is used to: monitor each power-consuming device in real time, send the monitoring data to the cloud server, and obtain real-time monitoring data; use the support vector machine model to predict the future trend of power demand changes based on the real-time monitoring data, and perform a multi-dimensional comprehensive analysis based on seasonal factors and historical power consumption patterns to generate an accurate power demand forecast report; based on the power demand forecast report, when an imbalance between power supply and demand is predicted, start an optimization scheduling strategy based on the particle swarm optimization algorithm, dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, use fault tree analysis technology to evaluate potential risk points, and generate emergency response plans and optimization scheduling results; based on the optimization scheduling results, automatically manage the power resource shortage situation, ensure the normal operation of high-priority equipment, and generate power management decision recommendations.

[0298] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0299] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0300] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0301] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0302] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0303] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0304] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a remote power supply monitoring method for cabin equipment based on the Internet of Things.

[0305] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0306] The device 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 paying creative labor.

[0307] 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, it 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.

[0308] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A remote power supply monitoring method for shelter equipment based on the Internet of Things, characterized in that: The following steps are involved: Monitor each electrical device in real time and send the monitoring data to the cloud server to obtain real-time monitoring data; Based on the real-time monitoring data, the support vector machine model is used to predict the future trend of electricity demand changes, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report; Based on the power demand forecast report, when an imbalance in power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and a fault tree analysis technique is used to evaluate potential risk points, generate an emergency response plan and an optimization scheduling result; Based on the optimization scheduling results, the power resource shortage situation is automatically managed to ensure the normal operation of high-priority equipment and generate power management decision suggestions.

2. The method according to claim 1, characterized in that The real-time monitoring data is used to predict the future trend of electricity demand changes using a support vector machine model, and a multi-dimensional comprehensive analysis is performed based on seasonal factors and historical electricity consumption patterns to generate an accurate electricity demand forecast report, including: Perform real-time monitoring on each electrical device and send the monitoring data to a cloud server to obtain the real-time monitoring data; Using the real-time monitoring data, combined with historical electricity consumption data, preprocessing the data based on seasonal factors and historical electricity consumption patterns to obtain the preprocessed data; The support vector machine model is trained according to the preprocessed data, and the prediction accuracy is improved by optimizing the model parameters, and the trained model is used to predict the future trend of power demand changes to obtain a power demand prediction value; Based on the electricity demand forecast value, combined with seasonal factors, historical electricity consumption patterns and external influencing factors, a comprehensive analysis is performed to generate an accurate electricity demand forecast report.

3. The method according to claim 2, characterized in that The real-time monitoring data is used in combination with historical electricity consumption data to pre-process the data based on seasonal factors and historical electricity consumption patterns to obtain the pre-processed data, including: Utilize the real-time monitoring data from each power-consuming device and combine it with the historical power consumption records to collect and integrate these data to obtain a comprehensive database; Based on the comprehensive database, the data therein are cleaned to remove abnormal values ​​and missing values ​​to obtain cleaned data; Utilizing the cleaned data, analyzing seasonal and periodic electricity consumption patterns, identifying electricity consumption characteristics in different time periods and electricity consumption patterns in different seasons, and obtaining electricity consumption pattern analysis results; Based on the power consumption pattern analysis results, statistical methods and data mining techniques are used to deeply process the cleaned data, extract key features, and obtain feature extraction results; Calculate the impact of external factors on the electricity consumption pattern, quantify the external factors and add them to the feature extraction results, perform further processing, improve the accuracy and reliability of the prediction model, and obtain feature data after considering the external factors; The characteristic data after considering the external factors are integrated to form pre-processed data.

4. The method according to claim 3, characterized in that The cleaned data is used to analyze seasonal and periodic electricity consumption patterns, identify electricity consumption characteristics in different time periods and electricity consumption patterns in different seasons, and obtain electricity consumption pattern analysis results, including: Before calculating the electricity consumption E(t) at time t, a comprehensive electricity consumption pattern model is constructed by performing time series analysis, statistical feature extraction, and seasonal electricity consumption pattern analysis on the cleaned data to provide basic data for the calculation of E(t); Among them, E(t) is the electricity consumption at time t, reflecting the characteristics of electricity consumption in different time periods; α, β, γ, δ, ∈ are model parameters, obtained by fitting historical data, used to adjust the sensitivity and accuracy of the model; t is a time variable, indicating a specific moment or time period; T is the cycle length; D is the cycle length; φ, ψ are phase shifts, used to adjust the time starting point of the periodic function; S(t) is the seasonal electricity consumption pattern at time t, reflecting the difference in electricity consumption in different seasons; t0 is a specific time point, used to adjust the center position of the Gaussian function; σ is the standard deviation, used to control the width of the Gaussian function; After calculating E(t), the power consumption data is smoothed, and the power demand forecast value P(t) is generated by combining historical power demand data and external influencing factors using a time series forecasting model and optimization algorithm. Among them, P(t) is the predicted value of electricity demand at time t, which is used to evaluate the changing trend of future electricity demand; η, ζ, θ, κ, ρ, ν are model parameters, which are obtained by fitting historical data and are used to adjust the sensitivity and accuracy of the model; E(t) is the electricity consumption at time t, which reflects the characteristics of electricity consumption in different time periods; μ is the average value of electricity consumption, which is used to standardize electricity consumption data and improve the stability of the model; t is a time variable, which represents a specific moment or time period; Y is the annual cycle length, which is used to capture the annual electricity consumption pattern; Q is the quarterly cycle length, which is used to capture the quarterly electricity consumption pattern; ω, λ are phase offsets, which are used to adjust the time starting point of the periodic function; F(t) is the function affected by external factors at time t; After calculating P(t), a detailed power consumption pattern analysis report is generated through verification and calibration, visualization, and sensitivity analysis, providing a scientific basis for the management and dispatch of the power system.

5. The method according to claim 2, characterized in that: The support vector machine model is trained according to the preprocessed data, and the prediction accuracy is improved by optimizing the model parameters, and the trained model is used to predict the future trend of power demand changes to obtain the power demand prediction value, including: Using the preprocessed data as input of a support vector machine model to perform model training to obtain a preliminarily trained support vector machine model; Based on the initially trained support vector machine model, a cross-validation method is used to optimize the model parameters to improve the generalization ability and prediction accuracy of the model, thereby obtaining an optimized support vector machine model; Using the optimized support vector machine model, combined with the latest real-time monitoring data and preprocessing process, the trend of power demand changes in a certain period of time in the future is predicted to obtain a preliminary power demand forecast value; Based on the preliminary power demand forecast value, a comprehensive correction is performed in combination with seasonal factors, historical power consumption patterns and external influencing factors to generate a final power demand forecast report to obtain the power demand forecast value.

6. The method according to claim 1, characterized in that Based on the power demand forecast report, when an imbalance in power supply and demand is predicted, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, and the fault tree analysis technology is used to evaluate potential risk points, generate emergency response plans and optimization scheduling results, including: Using the power demand forecast report, the future power supply and demand balance is evaluated and processed, and when a power supply and demand imbalance is predicted, a power supply and demand imbalance warning signal is generated; Based on the power supply and demand imbalance warning signal, an optimization scheduling strategy based on a particle swarm optimization algorithm is initiated to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan; Using fault tree analysis technology, risk assessment is performed on the preliminary optimization scheduling plan to generate a risk assessment report; Based on the risk assessment report, conduct an in-depth analysis of various potential risk points and the chain reactions they may cause, and obtain an emergency response plan; Combined with the preliminary optimization scheduling plan and the emergency response plan, the management and scheduling of power resources are comprehensively processed to generate an optimization scheduling result.

7. The method according to claim 6, characterized in that Based on the power supply and demand imbalance warning signal, the optimization scheduling strategy based on the particle swarm optimization algorithm is started to dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment to obtain a preliminary optimization scheduling plan, including: Before calculating the power supply and demand gap G(t) at time t, the power supply and demand model is constructed by analyzing and preprocessing the power demand forecast and historical operation data to prepare basic data for the calculation of G(t); Where G(t) is the gap between electricity supply and demand at time t, reflecting the degree of imbalance between electricity supply and demand; N is the number of generating units; M is the number of power-consuming devices; w i is the weight of the i-th generator set, reflecting its importance in the power system; P gen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; v j is the weight of the jth electrical equipment, reflecting its importance in the power system; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j (t) is the power consumption adjustment of the jth electrical equipment at time t; After calculating G(t), normalization is performed, the power adjustment ratio is calculated, and the particle swarm optimization algorithm is used to adjust power generation and power consumption, and finally the optimized scheduling target value O(t) is generated; Among them, O(t) is the optimized dispatch target value at time t, reflecting the effect of the optimized dispatch scheme; η, ζ, θ, κ are model parameters, obtained by fitting historical data, and used to adjust the sensitivity and accuracy of the model; G(t) is the gap between power supply and demand at time t, reflecting the degree of imbalance between power supply and demand; N is the number of generators; M is the number of power-consuming equipment; R gen,i (t) is the current output power of the i-th generator set at time t; ΔP gen,i (t) is the power adjustment of the i-th generator set at time t; P max,i is the maximum output power of the ith generator set; P load,j (t) is the current power consumption of the jth electrical equipment at time t; ΔP load,j (t) is the power consumption adjustment of the jth electrical equipment at time t; P max,j is the maximum power consumption of the jth electrical equipment; After calculating O(t), a detailed optimization scheduling plan is formed through the steps of verification and calibration, visualization, and sensitivity analysis to guide power system management and scheduling.

8. The method according to claim 6, characterized in that The method of using the fault tree analysis technology to perform risk assessment on the preliminary optimization scheduling plan and generate a risk assessment report includes: Using fault tree analysis technology, systematically analyze the key links and potential risk points in the preliminary optimization scheduling plan, identify various factors that may cause power system failures, and obtain a list of risk factors; Based on the risk factor list, a fault tree model is constructed to clarify the logical relationship between various risk factors and their influence on the overall system stability, and a fault tree structure diagram is obtained; Using the fault tree structure diagram, qualitative and quantitative risk assessment is performed to calculate the probability of occurrence of each risk event and the severity of its consequences, thereby obtaining risk assessment data; Based on the risk assessment data, analyze the impact of different risk events on the balance of power supply and demand, evaluate the risks that may arise during the implementation of the optimized scheduling plan, and obtain risk assessment conclusions; Based on the risk assessment conclusions, risk prevention and control recommendations are put forward and a risk assessment report is formed.

9. The method according to claim 1, characterized in that: The automatic management of power resource shortage based on the optimization scheduling result ensures the normal operation of high-priority equipment and generates power management decision suggestions, including: Using the optimization scheduling result, the allocation of power resources is automatically adjusted to obtain a power resource allocation plan; Based on the power resource allocation scheme, a power resource management mechanism is established to monitor the usage status of power resources in real time and dynamically adjust power allocation to obtain a power resource management mechanism; According to the power resource management mechanism, an emergency response level is set in the case of power resource shortage, and response measures of different levels are defined to obtain an emergency response level setting; In combination with the optimization dispatch result and the emergency response level setting, a comprehensive assessment is made on the operating status of the power system, and specific power management decision suggestions are put forward to obtain power management decision suggestions.

10. A remote power supply monitoring system for shelter equipment based on the Internet of Things, characterized in that: include: The monitoring module is used to monitor each electrical device in real time and send the monitoring data to the cloud server to obtain real-time monitoring data; A prediction module is used to predict the future trend of electricity demand changes based on the real-time monitoring data using a support vector machine model, and to generate an accurate electricity demand forecast report by performing a multi-dimensional comprehensive analysis based on seasonal factors and historical electricity consumption patterns; An adjustment module is used to start an optimization scheduling strategy based on a particle swarm optimization algorithm based on the power demand forecast report, dynamically adjust the output power of the generator set or the working schedule of the power-consuming equipment, use the fault tree analysis technology to evaluate potential risk points, and generate an emergency response plan and optimization scheduling results when an imbalance between power supply and demand is predicted; The management module is used to automatically manage the power resource shortage situation based on the optimization scheduling results, ensure the normal operation of high-priority equipment, and generate power management decision suggestions.

Images