Power energy management system based on smart IoT

Abstract

The present invention discloses an electric energy management system based on smart Internet of Things, and relates to the technical field of energy management. The present invention comprises a data acquisition unit, an equipment status analysis unit, a power supply data analysis unit, a trend analysis unit and a decision support unit; the data acquisition unit is used to acquire and integrate data from different devices and sensors for preprocessing; the electric equipment and sensors that need to be monitored are determined, and they are physically or wirelessly connected to the data acquisition unit; the present invention significantly improves the efficiency and intelligence level of the electric energy management system by integrating smart Internet of Things technology. Compared with traditional manual monitoring and regular maintenance methods, the system can monitor the status of the power grid in real time, respond quickly to power grid anomalies, reduce response time, and use advanced data analysis technology to provide in-depth insights, thereby optimizing energy consumption patterns and equipment maintenance strategies.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to an electric energy management system based on smart Internet of Things. Background Art

[0002] As the scale and complexity of power systems increase, how to achieve efficient and intelligent management of power grids has become a technical problem that urgently needs to be solved. Existing power energy management systems mostly use manual monitoring and regular maintenance. This method has problems such as long response time, low efficiency, and limited prediction ability. It is difficult to meet the modern society's demand for efficient, intelligent and environmentally friendly energy management;

[0003] Traditional power energy management systems are often limited by data collection limitations, backward analysis methods, and insufficient decision support. They are often unable to monitor the state of the power grid in real time and accurately, and have limited capabilities for evaluating equipment performance and warning of faults. In addition, when processing large amounts of data, existing systems often lack efficient data analysis tools and models and are unable to provide in-depth insights, resulting in a lack of data support in the decision-making process and an inability to achieve optimized energy consumption patterns and equipment maintenance strategies.

[0004] The development of smart IoT technology provides new solutions for power energy management. By integrating advanced sensors, communication technologies and data analysis algorithms, smart IoT systems can achieve comprehensive monitoring and in-depth analysis of power grids. However, how to effectively integrate and apply these technologies to power energy management systems to achieve real-time monitoring, intelligent early warning and optimized decision-making is still a challenge in the current technological development. It is in this context that the present invention is proposed, aiming to overcome the limitations of existing technologies through innovative technical solutions and provide a more efficient and intelligent power energy management method.

[0005] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0006] The purpose of the present invention is to solve the deficiencies of traditional power energy management systems in real-time monitoring, intelligent early warning and optimized decision-making, and to propose a power energy management system based on smart Internet of Things.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The power energy management system based on smart IoT includes:

[0009] A data acquisition unit, used to acquire and integrate data from different devices and sensors for preprocessing;

[0010] An equipment status analysis unit, used to evaluate the health status of equipment in real time through acquired equipment status data;

[0011] The power supply data analysis unit is used to perform real-time abnormal analysis on the power parameters of each node collected from the power grid;

[0012] A trend analysis unit for analyzing stored data to identify energy consumption patterns and equipment performance degradation trends;

[0013] The decision support unit is used to integrate different analysis results and provide decision support. The specific process is as follows:

[0014] Collect and unify data formats from different analysis units to ensure data comparability, consolidate analysis results, and identify trends and issues;

[0015] Identify equipment failures and energy supply risks, and assess the impact;

[0016] Based on the analysis results, formulate multiple response plans, conduct quantitative evaluation on each plan, and rank the plans according to the evaluation results to determine the best option;

[0017] Provide decision makers with action plans and expected results, and develop detailed implementation plans for selected options, including time, resource and responsibility allocation;

[0018] Use simulation tools to predict the effectiveness of program implementation, provide support for decision-making, develop monitoring plans, and ensure that strategies can be adjusted in a timely manner during program implementation.

[0019] Furthermore, the specific process of quantitatively evaluating each solution and determining the best solution in the decision support unit is as follows:

[0020] Evaluate the feasibility, cost-effectiveness and potential impact of each alternative, and prioritize the alternatives based on the evaluation results;

[0021] The prioritization of alternatives includes a comprehensive assessment of the following parameters:

[0022] Cost-benefit analysis: initial investment cost, operating costs and expected cost savings or benefits;

[0023] Technical feasibility: technical maturity, ease of technical implementation and technical compatibility;

[0024] Time frame: time for implementation and time to achieve the expected results;

[0025] Resource requirements: human resources, materials and technical resources;

[0026] Risk assessment: technical risk, operational risk and market risk;

[0027] Environmental impact: carbon footprint, energy consumption and sustainability;

[0028] User and stakeholder feedback: stakeholder satisfaction and user acceptance;

[0029] Assign a weight to each parameter, then score each option on the performance of each parameter, and finally calculate the weighted score. The option with the highest weighted score among all alternative options is considered the final selected option.

[0030] Furthermore, the data acquisition unit acquires and integrates data from different devices and sensors, and performs preprocessing in the following specific steps:

[0031] Determine the monitoring object and connect the electrical equipment and sensors physically or wirelessly;

[0032] Set up unified data collection and communication protocols for devices and sensors to ensure that devices and sensors can send data to the data acquisition unit in real time;

[0033] Synchronize data timestamps, ensure data consistency, remove noise and outliers, and perform filtering and deduplication;

[0034] Convert the data into a standard format, normalize it, and attach device identification, timestamp, and data type metadata to the data;

[0035] Store and categorize preprocessed data in a database or data warehouse, automate the preprocessing process, and reduce manual operations;

[0036] Regularly optimize the preprocessing process based on performance and requirements, and record preprocessing process information for problem tracking and system debugging.

[0037] Furthermore, the specific operation steps of the device status analysis unit to evaluate the health status of the device in real time through the acquired device status data are as follows:

[0038] Receive pre-processed equipment status data and extract parameters, manufacturer information and historical data to set normal operation baselines and safety thresholds for equipment parameters;

[0039] Continuously monitor real-time data and compare it to baselines and thresholds, applying statistical or machine learning algorithms to identify abnormal patterns in the data;

[0040] Calculate equipment health indicators, including remaining service life, and then comprehensively evaluate the health of electrical equipment based on abnormal parameters of electrical equipment, analyze abnormal data, and diagnose potential causes of failures;

[0041] Provide maintenance and repair suggestions based on equipment status and diagnostic results. Record analysis results, including equipment status, anomalies, warnings, and maintenance suggestions;

[0042] Communicate information to relevant personnel through the user interface or notification system, and adjust the assessment model based on the feedback to improve accuracy and reliability.

[0043] Furthermore, the specific operation steps of the device status analysis unit for comprehensively evaluating the health status of the electrical equipment according to the abnormal parameters of the electrical equipment are as follows:

[0044] Exception parameters include:

[0045] Load fluctuation: The fluctuation of equipment load. The standard deviation of the load at different times is calculated and recorded as the negative wave value. This negative wave value is used to measure the load fluctuation of electrical equipment.

[0046] Failure rate: how often equipment fails;

[0047] Maintenance times: historical maintenance and repair records of the equipment;

[0048] Performance degradation indicators: including efficiency decline and response time increase. These indicators reflect the degradation of equipment performance over time. The initial efficiency and response time of the equipment are recorded. The efficiency decline percentage and response time increase percentage are calculated based on the existing efficiency and response time. After normalization, a cone model is established with the efficiency decline percentage as the base circle radius and the response time increase percentage as the height. The surface area of ​​the cone model is calculated and recorded as the performance value. This performance degradation value is used as the standard for measuring the performance degradation of electrical equipment.

[0049] Environmental factors: By monitoring the humidity and corrosive gas concentration environmental factors, and presetting the standard humidity and standard corrosive gas concentration, the humidity difference and the corrosive gas concentration difference are calculated. After normalization, the sum of the humidity difference and the corrosive gas concentration difference is calculated and recorded as the environmental excess value. This environmental excess value is used as a standard to measure the impact of environmental factors on the operation of electrical equipment;

[0050] The obtained negative wave value, failure rate, maintenance times, degradation value and ring overload value are calibrated as fc, gz, wc, xt and hc respectively, and after normalization, they are entered into the following formula: To get the state evaluation value ZKP, where The preset weight coefficients are negative wave value, failure rate, maintenance times, degradation value and ring overload value respectively, and the obtained status evaluation value ZKP is used as the health status standard of electrical equipment;

[0051] Then the remaining service life and condition evaluation value of the electrical equipment are normalized and entered into the following formula: To obtain the corrected life XZZ, where SSM is the remaining service life of the electrical equipment. For the preset standard status evaluation, is a preset correction factor, and the obtained corrected life XZZ is used as the final evaluation standard for the remaining service life of the electrical equipment;

[0052] The obtained condition evaluation value ZKP is compared with the preset standard condition evaluation value interval to determine whether the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval. When the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval, an early warning message is generated.

[0053] Furthermore, the specific operation steps of the power supply data analysis unit for performing real-time abnormal analysis on the power parameters of each node collected from the power grid are as follows:

[0054] Receive pre-processed power parameter data from the data acquisition unit, continuously monitor the power grid status, and ensure the real-time and accuracy of the data;

[0055] Establish normal operation baselines for power parameters based on historical data and set safety thresholds for key parameters according to design standards;

[0056] Use statistical or machine learning algorithms to identify abnormal patterns in data, analyze real-time data streams, identify problems, and automatically trigger alarms and notify relevant personnel through abnormal judgment mechanisms;

[0057] Evaluate the impact of abnormalities on grid stability and power supply quality, record abnormal events and generate abnormal analysis reports;

[0058] Adjust grid operation parameters based on analysis results to restore normal conditions, provide operation optimization suggestions, and reduce future abnormal events;

[0059] Continuously optimize anomaly detection algorithms to improve detection accuracy and response speed.

[0060] Furthermore, the abnormality judgment mechanism process in the power supply data analysis unit is as follows:

[0061] Determine the normal operating range or mode of power parameters based on historical data, calculate the average and standard deviation statistical characteristics, and establish a baseline;

[0062] According to the design standards and empirical data, set upper and lower thresholds for each parameter, compare the real-time data with the baseline and threshold, and regard the parameters exceeding the threshold as potential abnormalities;

[0063] Apply supervised and unsupervised learning algorithms to identify abnormal patterns, evaluate the interrelationships between multiple parameters, and use multivariate methods to detect anomalies;

[0064] Identify unusual fluctuations in cyclical changes, trends or seasonal patterns, and detect rapid changes in voltage or frequency parameters, indicating transient events;

[0065] Analyze the association rules between parameters, identify chain abnormal patterns, and adjust baselines and thresholds based on new data to adapt to changes in grid operating conditions;

[0066] Assign severity scores to anomaly detection results and trigger alarms of corresponding levels based on the severity of the anomaly;

[0067] Manually review the anomaly detection results to eliminate false positives, and notify relevant personnel through communication channels after confirming the anomaly.

[0068] Furthermore, the specific process of the trend analysis unit identifying the energy consumption pattern and the equipment performance degradation trend is as follows:

[0069] Continuously collect power supply equipment status and power consumption parameter data from the data acquisition unit, integrate data from different sources to form a unified view;

[0070] Analyze data to identify cyclical, trending, and seasonal changes, establish long-term operating baselines for key parameters based on historical data, and use statistical or machine learning algorithms to identify long-term trends and short-term fluctuations;

[0071] Analyze changes in performance indicators, identify signs of equipment performance degradation, identify energy consumption patterns through cluster analysis methods, and analyze the correlation between different parameters;

[0072] Build models to predict future energy consumption and equipment performance, and integrate analysis results into decision support systems; adjust energy management and equipment maintenance strategies based on trend analysis feedback.

[0073] Furthermore, the process of constructing a model in the trend analysis unit to predict future energy consumption and equipment performance is as follows:

[0074] Explore data characteristics and patterns through visualization and statistical analysis to identify and select features that have the greatest impact on the prediction target;

[0075] Divide the data into training set, validation set and test set, and select the corresponding prediction model according to the problem and data characteristics;

[0076] Train the model using training set data and adjust parameters to optimize performance, evaluate model performance using validation sets and metrics, and optimize the model through parameter adjustment, feature selection, and ensemble learning methods;

[0077] Use cross-validation to evaluate model stability and generalization ability, select the best model based on the results and make adjustments;

[0078] Use the test set to validate the model to ensure prediction accuracy, and deploy the trained model for real-time or periodic prediction tasks;

[0079] Continuously monitor model performance to ensure forecast accuracy and regularly update models based on new data and feedback;

[0080] Generate prediction reports and visualization results, assist decision making, establish feedback mechanisms, collect user feedback, and continuously improve models.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] The present invention significantly improves the efficiency and intelligence level of the power energy management system by integrating smart IoT technology. Compared with the traditional manual monitoring and periodic maintenance methods, the system can monitor the power grid status in real time, respond quickly to power grid anomalies, reduce response time, and use advanced data analysis technology to provide in-depth insights, thereby optimizing energy consumption patterns and equipment maintenance strategies;

[0083] The present invention, through the equipment status analysis unit and the power supply data analysis unit, can evaluate the equipment health status in real time and perform abnormal analysis, timely discover and warn of potential equipment failures and energy supply risks, which not only enhances the stability of the power grid, but also improves the reliability and service life of the equipment, reduces unexpected downtime, and ensures the continuity and safety of power supply;

[0084] The present invention utilizes a decision support unit to integrate different analysis results, provide quantitative evaluation and priority sorting, and help decision makers choose the best solution. It not only improves the accuracy of decision-making, but also takes into account multiple factors such as cost-effectiveness, technical feasibility, time frame, resource requirements, risk assessment and environmental impact, thereby achieving reasonable allocation and optimal utilization of resources, thereby improving the economy and environmental sustainability of the entire power energy management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0086] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0087] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0089] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0090] like Figure 1 As shown, the power energy management system based on smart Internet of Things includes a data acquisition unit, an equipment status analysis unit, a power supply data analysis unit, a trend analysis unit and a decision support unit;

[0091] The data acquisition unit is used to acquire and integrate data from different devices and sensors for preprocessing;

[0092] Identify the electrical devices and sensors that need to be monitored and connect them to the data acquisition unit physically or wirelessly; define a unified data acquisition protocol for different types of electrical devices and sensors to ensure consistency in data format; establish data streams to ensure that electrical devices and sensors can send data to the data acquisition unit in real time, so that the data acquisition unit receives data streams from various electrical devices and sensors;

[0093] All received data are synchronized on the timestamp for subsequent analysis and processing; noise and outliers in the data are removed through filtering and deduplication methods, and the data is converted into a consistent format; the data is then normalized to eliminate dimensional differences between different electrical devices and sensors, and metadata is added to the data, such as device identification, timestamp, and data type;

[0094] Store the preprocessed data in an appropriate database or data warehouse, and classify the stored data into power supply equipment status data and power consumption parameter data; automate the above preprocessing process to reduce manual intervention and improve efficiency; optimize the preprocessing process based on system performance and data analysis requirements, and record the information during the data preprocessing process for subsequent problem tracking and system debugging.

[0095] The device status analysis unit is used to evaluate the health status of the device in real time through the acquired device status data;

[0096] First, the state data of the electrical equipment preprocessed by the data acquisition unit is received, and the received data is parsed to extract parameters in the data, such as temperature, vibration, current, voltage, etc.; a parameter baseline under normal operating conditions is established for each electrical equipment, and safety thresholds are set for key parameters based on the user manual information and historical operating data of the equipment manufacturer; the real-time data of the electrical equipment is continuously monitored and compared with the baseline and threshold;

[0097] Use statistical methods or machine learning algorithms to detect abnormal patterns in the data, calculate the health indicators of the electrical equipment, such as the remaining service life, based on the parameters of the electrical equipment, and then comprehensively evaluate the health status of the electrical equipment based on the abnormal parameters of the electrical equipment. The abnormal parameters include:

[0098] Load fluctuation: Fluctuation of equipment load. Frequent or drastic load changes may cause damage to the equipment. The standard deviation of the load at different times is calculated and recorded as a negative wave value. This negative wave value is used to measure the load fluctuation of the electrical equipment. Failure rate: The frequency of equipment failure. A high failure rate may indicate that the equipment is aging or under-maintained. Maintenance times: The historical maintenance and repair records of the equipment. A poor maintenance history may affect the health of the equipment. Performance degradation indicators: Including efficiency decline and response time increase. These indicators reflect the degradation of equipment performance over time. The initial efficiency and response time of the equipment are recorded, and the efficiency decline is calculated based on the current efficiency and response time. Percentage and response time increase percentage, after normalization, use the efficiency decrease percentage as the base circle radius and the response time increase percentage as the height to establish a cone model, calculate the surface area of ​​the cone model, record it as the performance value, and use this performance degradation value as the standard for measuring the performance degradation of electrical equipment; Environmental factors: by monitoring the humidity and corrosive gas concentration environmental factors, and presetting the standard humidity and standard corrosive gas concentration, calculate the humidity difference and the corrosive gas concentration difference, after normalization, calculate the sum of the humidity difference and the corrosive gas concentration difference, record it as the ring excess value, and use this ring excess value as the standard for measuring the impact of environmental factors on the operation of electrical equipment;

[0099] The obtained negative wave value, failure rate, maintenance times, degradation value and ring overload value are calibrated as fc, gz, wc, xt and hc respectively, and after normalization, they are entered into the following formula: To get the state evaluation value ZKP, where The preset weight coefficients are negative wave value, failure rate, maintenance times, degradation value and ring overload value respectively, and the obtained status evaluation value ZKP is used as the health status standard of electrical equipment;

[0100] Then the remaining service life and condition evaluation value of the electrical equipment are normalized and entered into the following formula: To obtain the corrected life XZZ, where SSM is the remaining service life of the electrical equipment. For the preset standard status evaluation, is a preset correction factor, the value of which is set between 0.92 and 1.26. The obtained corrected life XZZ is used as the final evaluation standard for the remaining service life of the electrical equipment. At the same time, the obtained condition evaluation value ZKP is compared with the preset standard condition evaluation value interval to determine whether the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval. When the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval, an early warning message is generated.

[0101] Conduct in-depth analysis of abnormal conditions, diagnose possible causes of faults, and provide maintenance and repair suggestions based on the status of electrical equipment and fault diagnosis results; record the results of electrical equipment status analysis, including normal, abnormal, warning and maintenance suggestions, and inform relevant personnel of the analysis results and warning information through the user interface or notification system; adjust the equipment status assessment model based on feedback from maintenance and repair operations to improve accuracy.

[0102] The power supply data analysis unit is used to perform real-time abnormal analysis on the power parameters of each node collected from the power grid;

[0103] Obtain pre-processed power parameter data such as voltage, current, power, frequency, etc. of each node of the power grid from the data acquisition unit; monitor the operation status of the power grid in real time to ensure the real-time and accuracy of the data, and establish a normal operating baseline or mode for the power parameters of the power grid; set safety thresholds for key parameters based on the design standards and historical data of the power grid, and use statistical methods or machine learning algorithms to identify abnormal patterns in the data;

[0104] Identify common patterns and potential abnormal behaviors in power grid operation, and quickly analyze real-time data streams to detect problems in a timely manner; detect anomalies through the abnormal judgment mechanism, and the system automatically triggers an alarm to notify relevant personnel. The abnormal judgment mechanism is as follows:

[0105] First, a baseline is established by collecting a large amount of historical data of the power grid under normal operating conditions, and analyzing these data to determine the typical range or pattern of power parameters (such as voltage, current, power, frequency, etc.); using statistical methods to determine the statistical characteristics of the parameters, such as mean, standard deviation, distribution, etc. The baseline can be a function of these statistical characteristics, for example, the mean plus or minus a few standard deviations;

[0106] Set upper and lower thresholds for each key parameter based on the grid’s design standards, operational experience, and historical data. These thresholds define the normal range of fluctuations in the parameters; compare the power parameters collected in real time with the baseline and thresholds. If any parameter exceeds the preset threshold, it is marked as a potential anomaly;

[0107] Use machine learning algorithms to identify patterns and trends in data. Algorithms can be supervised learning (such as classification algorithms) or unsupervised learning (such as clustering algorithms) to discover abnormal patterns in data; use algorithms such as isolation forests, single-class support vector machines, neural networks, etc. to detect anomalies in data. These algorithms can identify data points that do not conform to normal patterns without a clear baseline; consider the relationship between multiple parameters, use multivariate statistical methods or machine learning models to evaluate the state of the power grid, perform time series analysis on power parameters to identify periodic changes, trends or seasonal patterns, and detect abnormal fluctuations on this basis; monitor the rate of change of parameters, such as rapid changes in voltage or frequency may indicate transient events in the power grid, analyze the association rules between different parameters, and identify whether other parameters also show abnormal patterns when one parameter is abnormal;

[0108] Continuously learn and adjust baselines and thresholds based on new data to adapt to changes in grid operating conditions; assign a score to the anomaly detection result to indicate the severity of the anomaly, trigger different levels of alarms based on the severity and type of the anomaly, and manually review the anomaly detection results to eliminate false alarms or confirm real problems. After confirming that it is not a false alarm, notify relevant personnel through appropriate communication channels.

[0109] Assess the impact of anomalies on grid stability and power supply quality, record detailed information of abnormal events, including time, parameters, impact range, etc., generate anomaly analysis reports, and provide a basis for further decision-making; according to the results of anomaly analysis, automatically or manually adjust grid operation parameters to restore normal status, provide grid operation optimization suggestions to reduce future abnormal events, and continuously optimize anomaly detection algorithms through continuous learning to improve accuracy and response speed.

[0110] The trend analysis unit is used to analyze the stored data and identify energy consumption patterns and equipment performance degradation trends;

[0111] Continuously collect power supply equipment status data and power consumption parameter data through the data acquisition unit, integrate data from different sources and types, and provide a unified data view for analysis; analyze time series data to identify periodic patterns, trends and seasonal changes, and establish long-term operating baselines or averages for key parameters based on historical data;

[0112] Use statistical methods or machine learning algorithms to identify long-term trends and short-term fluctuations in data, and analyze changes in equipment performance indicators over time to identify signs of performance degradation; use methods such as cluster analysis to identify patterns and categories of energy consumption, and analyze correlations between different parameters to understand how they affect each other;

[0113] Build a prediction model to predict future energy consumption and equipment performance. The specific process is as follows:

[0114] The pre-processed power supply equipment status data and power consumption parameter data are visualized and statistically analyzed to explore the basic characteristics and patterns of the data; the features that have the greatest impact on the prediction target are selected to improve the performance of the model, and the data set is divided into training set, validation set and test set;

[0115] According to the nature of the problem and the characteristics of the data, select the corresponding prediction model, such as linear regression, decision tree, random forest, gradient boosting machine, neural network, etc.; use the training set data to train the model, adjust the model parameters to obtain the best performance, use the validation set to evaluate the performance of the model, and select indicators such as mean square error (MSE) and coefficient of determination (R²);

[0116] Optimize the model by adjusting model parameters, using feature selection or ensemble learning, and use cross-validation techniques to evaluate the stability and generalization ability of the model. Select the best model based on the results of cross-validation and make further adjustments. Use the test set to perform final validation on the model to ensure the model's predictive ability, explain the model's prediction results, deploy the trained model for real-time or periodic prediction tasks, and continuously monitor the performance of the model in actual applications to ensure the accuracy of the prediction results.

[0117] Based on new data and feedback, the model is updated regularly to adapt to the changing environment, and forecast reports and visualization results are generated to help decision makers understand the forecast results. A feedback mechanism is established to collect user feedback and the accuracy of forecast results to continuously improve the model.

[0118] Integrate the results of trend analysis into the decision support system to provide a basis for energy management and equipment maintenance. Adjust the energy consumption pattern and equipment maintenance strategy based on the feedback from trend analysis. The specific process is as follows:

[0119] Deeply understand the key indicators and findings in the trend analysis report, including energy consumption patterns, equipment performance degradation trends, etc. Based on the analysis results, identify key areas that need improvement or adjustment, such as energy use in a specific time period, maintenance requirements for specific equipment, etc. Set specific, quantifiable goals for adjustments, such as reducing energy consumption percentage, extending equipment life, etc., and formulate specific strategies and measures based on the goals, including: optimizing energy use time, implementing demand response; introducing energy-saving technologies or upgrading existing equipment; adjusting production plans, balancing loads; formulating preventive maintenance plans based on equipment performance degradation trends, including:

[0120] Set maintenance cycles and checkpoints; determine parts that need to be replaced or repaired; reasonably allocate human, material and financial resources according to strategies and plans, and convert strategies and plans into specific operational steps for implementation.

[0121] The decision support unit is used to integrate different analysis results and provide decision support;

[0122] Collect analysis results from the equipment status analysis unit, power supply data analysis unit, and trend analysis unit to ensure that data and results from different analysis units are standardized for easy integration and comparison; integrate data and analysis results from different sources to form a comprehensive view, conduct comprehensive analysis on the integrated data to identify overall trends and potential problems, and evaluate risk factors in the analysis results, such as equipment failure risk, unstable energy supply, etc.; based on the comprehensive analysis results, formulate alternative plans to deal with different situations, evaluate the feasibility, cost-effectiveness and potential impact of each alternative plan, and prioritize the alternative plans according to the evaluation results of the plan. The specific process is as follows:

[0123] The prioritization of alternatives involves a comprehensive evaluation of the following parameters:

[0124] Cost-benefit analysis: initial investment cost, operating cost, expected cost savings or benefits; technical feasibility: technology maturity, ease of technology implementation, technology compatibility; time frame: implementation time, time to achieve expected results; resource requirements: manpower requirements, material requirements, technical resource requirements; risk assessment: technical risk, operational risk, market risk; environmental impact: carbon footprint, energy consumption, sustainability; user and stakeholder feedback: stakeholder satisfaction, user acceptance;

[0125] Each parameter is assigned a weight to reflect its importance in the decision-making process. Each option is then scored on its performance on each parameter, and finally a weighted score is calculated. The option with the highest weighted score among all alternative options is considered the final selected option.

[0126] Provide clear advice to decision makers, including recommended action plans and expected results, and develop detailed implementation plans for selected plans, including timetables, resource allocation, and responsibility allocation; use simulation tools to predict the effects of the plan after implementation to provide further support for decision-making, and develop a monitoring plan after the implementation of the plan to ensure that the strategy can be adjusted in a timely manner.

[0127] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The power energy management system based on smart IoT is characterized by: include: The data acquisition unit is used to acquire and integrate data from different devices and sensors for preprocessing; the specific process is as follows: Determine the monitoring object and connect the electrical equipment and sensors physically or wirelessly; Set up unified data collection and communication protocols for devices and sensors to ensure that devices and sensors can send data to the data acquisition unit in real time; Synchronize data timestamps, ensure data consistency, remove noise and outliers, and perform filtering and deduplication; Convert the data into a standard format, normalize it, and attach device identification, timestamp, and data type metadata to the data; Store and categorize preprocessed data in a database or data warehouse, automate the preprocessing process, and reduce manual operations; Regularly optimize the preprocessing process according to performance and requirements, and record preprocessing process information for problem tracking and system debugging; The device status analysis unit is used to evaluate the device health status in real time through the acquired device status data; the specific steps are as follows: Receive pre-processed equipment status data and extract parameters, manufacturer information and historical data to set normal operation baselines and safety thresholds for equipment parameters; Continuously monitor real-time data and compare it to baselines and thresholds, applying statistical or machine learning algorithms to identify abnormal patterns in the data; Calculate equipment health indicators, including remaining service life, and then comprehensively evaluate the health of electrical equipment based on abnormal parameters of electrical equipment, analyze abnormal data, and diagnose potential causes of failures; Provide maintenance and repair suggestions based on equipment status and diagnostic results. Record analysis results, including equipment status, anomalies, warnings, and maintenance suggestions; Communicate information to relevant personnel through the user interface or notification system, and adjust the assessment model based on the feedback to improve accuracy and reliability; The power supply data analysis unit is used to perform real-time abnormal analysis on the power parameters of each node collected from the power grid; A trend analysis unit for analyzing stored data to identify energy consumption patterns and equipment performance degradation trends; The decision support unit is used to integrate different analysis results and provide decision support. The specific process is as follows: Collect and unify data formats from different analysis units to ensure data comparability, consolidate analysis results, and identify trends and issues; Identify equipment failures and energy supply risks, and assess the impact; Based on the analysis results, formulate multiple response plans, conduct quantitative evaluation on each plan, sort the plans according to the evaluation results, and determine the best option. The specific process is as follows: Evaluate the feasibility, cost-effectiveness and potential impact of each alternative, and prioritize the alternatives based on the evaluation results; The prioritization of alternatives includes a comprehensive assessment of the following parameters: Cost-benefit analysis: initial investment cost, operating costs and expected cost savings or benefits; Technical feasibility: technical maturity, ease of technical implementation and technical compatibility; Time frame: time for implementation and time to achieve the expected results; Resource requirements: human resources, materials and technical resources; Risk assessment: technical risk, operational risk and market risk; Environmental impact: carbon footprint, energy consumption and sustainability; User and stakeholder feedback: stakeholder satisfaction and user acceptance; Assign weights to each parameter, then score each option on each parameter, and finally calculate the weighted score. The option with the highest weighted score among all alternative options is considered the final option. Provide decision makers with action plans and expected results, and develop detailed implementation plans for selected options, including time, resource and responsibility allocation; Use simulation tools to predict the effectiveness of program implementation, provide support for decision-making, develop monitoring plans, and ensure that strategies can be adjusted in a timely manner during program implementation.

2. The power energy management system based on smart Internet of Things according to claim 1 is characterized in that: The specific operation steps of the device status analysis unit for comprehensively evaluating the health status of the electrical equipment according to the abnormal parameters of the electrical equipment are as follows: Exception parameters include: Load fluctuation: The fluctuation of equipment load. The standard deviation of the load at different times is calculated and recorded as the negative wave value. This negative wave value is used to measure the load fluctuation of electrical equipment. Failure rate: how often equipment fails; Maintenance times: historical maintenance and repair records of the equipment; Performance degradation indicators: including efficiency decline and response time increase. These indicators reflect the degradation of equipment performance over time. The initial efficiency and response time of the equipment are recorded. The efficiency decline percentage and response time increase percentage are calculated based on the existing efficiency and response time. After normalization, a cone model is established with the efficiency decline percentage as the base circle radius and the response time increase percentage as the height. The surface area of ​​the cone model is calculated and recorded as the performance value. This performance degradation value is used as the standard for measuring the performance degradation of electrical equipment. Environmental factors: By monitoring the humidity and corrosive gas concentration environmental factors, and presetting the standard humidity and standard corrosive gas concentration, the humidity difference and the corrosive gas concentration difference are calculated. After normalization, the sum of the humidity difference and the corrosive gas concentration difference is calculated and recorded as the environmental excess value. This environmental excess value is used as a standard to measure the impact of environmental factors on the operation of electrical equipment; The obtained negative wave value, failure rate, maintenance times, degradation value and ring overload value are calibrated as fc, gz, wc, xt and hc respectively, and after normalization, they are entered into the following formula: To get the state evaluation value ZKP, where The preset weight coefficients are negative wave value, failure rate, maintenance times, degradation value and ring overload value respectively, and the obtained status evaluation value ZKP is used as the health status standard of electrical equipment; Then the remaining service life and condition evaluation value of the electrical equipment are normalized and entered into the following formula: To obtain the corrected life XZZ, where SSM is the remaining service life of the electrical equipment. For the preset standard status evaluation, is a preset correction factor, and the obtained corrected life XZZ is used as the final evaluation standard for the remaining service life of the electrical equipment; The obtained condition evaluation value ZKP is compared with the preset standard condition evaluation value interval to determine whether the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval. When the condition evaluation value ZKP belongs to the preset standard condition evaluation value interval, an early warning message is generated.

3. The power energy management system based on smart Internet of Things according to claim 1 is characterized in that: The specific operation steps of the power supply data analysis unit for performing real-time abnormal analysis on the power parameters of each node collected by the power grid are as follows: Receive pre-processed power parameter data from the data acquisition unit, continuously monitor the power grid status, and ensure the real-time and accuracy of the data; Establish normal operation baselines for power parameters based on historical data and set safety thresholds for key parameters according to design standards; Use statistical or machine learning algorithms to identify abnormal patterns in data, analyze real-time data streams, identify problems, and automatically trigger alarms and notify relevant personnel through abnormal judgment mechanisms; Evaluate the impact of abnormalities on grid stability and power supply quality, record abnormal events and generate abnormal analysis reports; Adjust grid operation parameters based on analysis results to restore normal conditions, provide operation optimization suggestions, and reduce future abnormal events; Continuously optimize anomaly detection algorithms to improve detection accuracy and response speed.

4. The power energy management system based on smart Internet of Things according to claim 3 is characterized in that: The abnormality judgment mechanism process in the power supply data analysis unit is as follows: Determine the normal operating range or mode of power parameters based on historical data, calculate the average and standard deviation statistical characteristics, and establish a baseline; According to the design standards and empirical data, set upper and lower thresholds for each parameter, compare the real-time data with the baseline and threshold, and regard the parameters exceeding the threshold as potential abnormalities; Apply supervised and unsupervised learning algorithms to identify abnormal patterns, evaluate the interrelationships between multiple parameters, and use multivariate methods to detect anomalies; Identify unusual fluctuations in cyclical changes, trends or seasonal patterns, and detect rapid changes in voltage or frequency parameters, indicating transient events; Analyze the association rules between parameters, identify chain abnormal patterns, and adjust baselines and thresholds based on new data to adapt to changes in grid operating conditions; Assign severity scores to anomaly detection results and trigger alarms of corresponding levels based on the severity of the anomaly; Manually review the anomaly detection results to eliminate false positives, and notify relevant personnel through communication channels after confirming the anomaly.

5. The power energy management system based on smart Internet of Things according to claim 1 is characterized in that: The specific process of the trend analysis unit identifying the energy consumption pattern and the equipment performance degradation trend is as follows: Continuously collect power supply equipment status and power consumption parameter data from the data acquisition unit, integrate data from different sources to form a unified view; Analyze data to identify cyclical, trending, and seasonal changes, establish long-term operating baselines for key parameters based on historical data, and use statistical or machine learning algorithms to identify long-term trends and short-term fluctuations; Analyze changes in performance indicators, identify signs of equipment performance degradation, identify energy consumption patterns through cluster analysis methods, and analyze the correlation between different parameters; Build models to predict future energy consumption and equipment performance, and integrate analysis results into decision support systems; Adjust energy management and equipment maintenance strategies based on trend analysis feedback.

6. The power energy management system based on intelligent Internet of Things according to claim 5 is characterized in that: The process of constructing a model in the trend analysis unit to predict future energy consumption and equipment performance is as follows: Explore data characteristics and patterns through visualization and statistical analysis to identify and select features that have the greatest impact on the prediction target; Divide the data into training set, validation set and test set, and select the corresponding prediction model according to the problem and data characteristics; Train the model using training set data and adjust parameters to optimize performance, evaluate model performance using validation sets and metrics, and optimize the model through parameter adjustment, feature selection, and ensemble learning methods; Use cross-validation to evaluate model stability and generalization ability, select the best model based on the results and make adjustments; Use the test set to validate the model to ensure prediction accuracy, and deploy the trained model for real-time or periodic prediction tasks; Continuously monitor model performance to ensure forecast accuracy and regularly update models based on new data and feedback; Generate prediction reports and visualization results, assist decision making, establish feedback mechanisms, collect user feedback, and continuously improve models.

Images