Operation situation awareness method considering weak links of power distribution network

Abstract

The invention relates to an operation situation sensing method considering weak links of a power distribution network, and the method achieves the recognition and sorting of the weak links of the power distribution network through the construction of a multi-dimensional recognition index system, and can achieve the collection of the operation data of the weak links through a power distribution automation system, an advanced measurement system and an Internet of Things sensing device. Therefore, a high-quality data set is formed, and a powerful data basis is provided for subsequent evaluation; the comprehensive evaluation of the operation situation of the weak link is carried out from multiple latitudes of static safety, transient stability and risk level, and the safety condition can be comprehensively reflected, so that the evaluation accuracy is improved, the fault risk is effectively pre-judged in advance, and the reliable guarantee is provided for the safe and stable operation of the power distribution network; through visualization and early warning functions, visual and clean situation information is provided for operators, and the operators are assisted to carry out operation mode adjustment and risk prevention and control decision making, so that the safe and stable operation level of the power distribution network is improved; the method has the advantages of being accurate in prediction and efficient and convenient to use.

Description

Technical Field

[0001] This invention belongs to the field of power grid operation monitoring technology, specifically relating to an operation status perception method that takes into account the weak links of the distribution network. Background Technology

[0002] As the final link in the power system, the distribution network undertakes the important task of transmitting electrical energy from the transmission network to users. Its operating status is directly related to the reliability of power supply and power quality. With the large-scale integration of distributed power sources, the rapid growth of power load, and the increasing complexity of network topology, the dynamic changes in the operating status of the distribution network are becoming more and more significant, and the impact of weak links is becoming more and more prominent.

[0003] Currently, existing methods for assessing the operational status of distribution networks mostly focus on monitoring and evaluating overall operating parameters, neglecting the decisive role of weak links in the overall situation. This results in insufficient accuracy in situation assessment and makes it difficult to predict cascading failures caused by weak links in advance. Although some methods involve weak link analysis, they suffer from problems such as vague identification standards, incomplete data collection, and a lack of specificity in the evaluation models, making it impossible to achieve accurate and comprehensive perception of the operational status of the distribution network. Therefore, in order to improve the situational awareness capability of the distribution network and ensure its safe and stable operation, it is necessary to develop a precise and efficient method for assessing the operational status of the distribution network that takes into account its weak links. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method for accurate and efficient distribution network operation status perception that takes into account the weak links of the distribution network.

[0005] The objective of this invention is achieved as follows: a method for operational status awareness considering weak links in a power distribution network, comprising the following steps: Step 1: Based on the distribution network topology, equipment parameters, historical operating data and environmental factors, a multi-dimensional identification index system is constructed. The weak links of the distribution network are identified by combining the analytic hierarchy process (AHP) and the fuzzy comprehensive evaluation method. After identification, the weak links are sorted from most important to least important to form a list. Then, the list of weak links is updated in real time by combining the time-series weighted method and the grey relational analysis method. Step 2: Through the power distribution automation system, advanced measurement system and IoT sensing devices, the operational data of the weak links identified in Step 1 are collected in real time. The operational data includes electrical quantity data, equipment status data and environmental data. Then, an adaptive anomaly detection algorithm combined with an improved Kalman filter is used to clean and filter the collected data. Finally, after normalization and fusion processing, a high-quality dataset is formed. Step 3: For the identified weaknesses, construct an operational status assessment model, and input the high-quality dataset from Step 2 into the operational status assessment model to assess the operational status and development trend of the weaknesses in real time and generate assessment results. Step 4: Based on the evaluation results in Step 3, use time series analysis, machine learning or deep learning algorithms to make short-term predictions of key operational indicators of weak links, thereby forming a predictive trend chart. Step 5: Set the early warning threshold, and then visualize the real-time operating status, evaluation results and predicted trend chart of the weak link through the human-computer interaction interface; when the information in the evaluation results or predicted trend chart exceeds the preset threshold, generate early warning information of different levels, and push the early warning information to the handheld terminal of the operation and maintenance personnel through the wireless transmission component.

[0006] Furthermore, the weak links in the power distribution network in step 1 specifically include weak lines, weak nodes, and weak equipment.

[0007] Furthermore, the specific identification operation of the weak link in step 1 is as follows: the weight of each indicator is determined by the analytic hierarchy process, the degree of weakness of each node, device and line is quantitatively scored by the fuzzy comprehensive evaluation method, a scoring threshold is set, objects with scores higher than the threshold are defined as weak links, and sorted according to the scores.

[0008] Furthermore, the data normalization and fusion processing in step 2 specifically involves: using the Z-score standardization method to unify the data dimensions, and using an attention-based feature fusion algorithm to achieve multi-source data fusion.

[0009] Furthermore, the operational status assessment in step 3 includes static safety assessment, transient stability assessment, and risk level assessment. The static safety assessment involves calculating indicators such as the N-1 pass rate, voltage over-limit probability, and load rate over-limit probability of the weak link based on current operational data to assess its static safety. The transient stability assessment involves performing time-domain simulation or using data-driven methods to assess the transient stability margin of the weak link under fault conditions for a preset set of typical faults. The risk level assessment involves comprehensively considering the static safety level, transient stability level, equipment health status, and external environmental factors of the weak link, using risk theory to calculate its comprehensive risk index, and classifying the risk level.

[0010] Furthermore, the warning threshold in step 5 can be determined based on the power distribution network safety operation procedures and historical fault data, while the warning information is divided into three levels: mild warning, moderate warning, and severe warning.

[0011] The beneficial effects of this invention are: by constructing a multi-dimensional identification index system, this invention can identify and rank the weak links in the power distribution network; Through power distribution automation systems, advanced measurement systems, and IoT sensing devices, operational data from vulnerable points can be collected. Subsequently, the collected data can be cleaned, filtered, normalized, and fused to form a high-quality dataset, providing a strong data foundation for subsequent evaluation. By comprehensively assessing the operational status of weak links from multiple dimensions such as static safety, transient stability, and risk level, their safety status can be fully reflected, thereby improving the accuracy of the assessment, effectively predicting fault risks in advance, and providing reliable protection for the safe and stable operation of the distribution network. Through visualization and early warning functions, the invention provides operators with intuitive and clear situational information, assisting them in making operational adjustments and risk prevention decisions, thereby improving the safe and stable operation of the power distribution network. In summary, the invention has the advantages of accurate prediction and efficient and convenient use. Detailed Implementation

[0012] The present invention will now be further described.

[0013] Example: A method for operational status awareness considering weak links in a distribution network, comprising the following steps: Step 1: Based on the distribution network topology, equipment parameters, historical operating data, and environmental factors, a multi-dimensional identification index system is constructed. A combination of the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation is used to identify weak links in the distribution network. After identification, the weak links are ranked from most important to least important, forming a list. Then, a combination of time-series weighted analysis and grey relational analysis is used to update the list of weak links in real time. Specifically, weak links in the distribution network include weak lines, weak nodes, and weak equipment. The specific identification process involves: using the AHP to determine the weights of each index; using the fuzzy comprehensive evaluation method to quantify the degree of weakness of each node, equipment, and line; setting a scoring threshold; defining objects with scores higher than the threshold as weak links; and ranking them according to their scores. Step 2: Real-time data collection of operational data from the weak points identified in Step 1 is achieved through power distribution automation systems, advanced measurement systems, and IoT sensing devices. This operational data includes electrical quantity data, equipment status data, and environmental data. Subsequently, an adaptive anomaly detection algorithm combined with an improved Kalman filter is used to clean and filter the collected data. Finally, after normalization and fusion processing, a high-quality dataset is formed. Specifically, the normalization and fusion processing involves: using Z-score standardization to unify data dimensions, and employing an attention-based feature fusion algorithm to achieve multi-source data fusion. Step 3: For the identified weak links, construct an operational status assessment model and input the high-quality dataset from Step 2 into the operational status assessment model. The model will then assess the operational status and development trend of the weak links in real time and generate assessment results. The operational status assessment includes static safety assessment, transient stability assessment, and risk level assessment. Static safety assessment involves calculating the N-1 pass rate, voltage over-limit probability, and load rate over-limit probability of the weak links based on current operational data to evaluate their static safety. Transient stability assessment involves using time-domain simulation or data-driven methods to assess the transient stability margin of the weak links under fault conditions, based on a preset set of typical faults. Risk level assessment involves comprehensively considering the static safety level, transient stability level, equipment health status, and external environmental factors of the weak links, using risk theory to calculate their comprehensive risk index and classify the risk level. Step 4: Based on the evaluation results in Step 3, use time series analysis, machine learning or deep learning algorithms to make short-term predictions of key operational indicators of weak links, thereby forming a predictive trend chart. Step 5: Set the early warning threshold, and then visualize the real-time operating status, evaluation results, and predicted trend chart of the weak link through the human-machine interface; when the information in the evaluation results or predicted trend chart exceeds the preset threshold, generate early warning information of different levels, and push the early warning information to the handheld terminal of the operation and maintenance personnel through the wireless transmission component. The early warning threshold can be determined according to the distribution network safety operation procedures and historical fault data, and the early warning information is divided into three levels: mild early warning, moderate early warning, and severe early warning.

[0014] In use, this invention first constructs a multi-dimensional identification index system based on the distribution network topology, equipment parameters, historical operating data, and environmental factors. It then employs a combination of the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation to identify weak links in the distribution network. Specifically, the AHP is used to determine the weights of each index; the fuzzy comprehensive evaluation is used to quantify the weakness of each node, device, and line; a scoring threshold is set; objects with scores exceeding the threshold are defined as weak links; and the scores are sorted to form a list. Finally, a combination of time-series weighted analysis and grey relational analysis is used to update the list of weak links in real time. The weak links in the distribution network specifically include weak lines. The system identifies weak points and vulnerable equipment. Then, through distribution automation systems, advanced measurement systems, and IoT sensing devices, it collects real-time operational data of these weak points, including electrical quantity data, equipment status data, and environmental data. Subsequently, an adaptive anomaly detection algorithm combined with an improved Kalman filter is used to clean and filter the collected data. Finally, after normalization and fusion processing, a high-quality dataset is formed. Specifically, the normalization and fusion processing involves using Z-score standardization to unify data dimensions and employing an attention-based feature fusion algorithm to fuse multi-source data. Finally, an operational status assessment model is constructed for these weak points, and the high-quality dataset is input into the system. Within the operational status assessment model, the operational status and development trend of vulnerable components are assessed in real time, generating assessment results. The operational status assessment includes static safety assessment, transient stability assessment, and risk level assessment. Static safety assessment calculates indicators such as the N-1 pass rate, voltage over-limit probability, and load rate over-limit probability of the vulnerable component based on current operational data, evaluating its static safety. Transient stability assessment uses time-domain simulation or data-driven methods to assess the transient stability margin of the vulnerable component under fault conditions, based on a preset set of typical faults. Risk level assessment comprehensively considers the static safety level, transient stability level, equipment health status, and external environmental factors of the vulnerable component, employing risk management principles. The process involves calculating comprehensive risk indicators and classifying risk levels. Finally, based on the assessment results, time series analysis, machine learning, or deep learning algorithms are used to make short-term predictions of key operational indicators for weak links, thus generating a predictive trend chart. After completing the above operations, early warning thresholds are determined according to the power distribution network safety operation procedures and historical fault data. Subsequently, the real-time operational status of weak links, assessment results, and predictive trend charts are visualized through a human-machine interface. When the assessment results or information in the predictive trend chart exceeds a preset threshold, early warning information for mild, moderate, or severe warnings is generated according to the amount of excess, and the warning information is pushed to the handheld terminals of maintenance personnel via wireless transmission components.

[0015] This invention, by constructing a multi-dimensional identification index system, enables the identification and ranking of weak links in the distribution network. Through distribution automation systems, advanced measurement systems, and IoT sensing devices, operational data of these weak links can be collected. The collected data is then cleaned, filtered, normalized, and fused to form a high-quality dataset, providing a strong data foundation for subsequent assessments. By comprehensively assessing the operational status of weak links from multiple dimensions—static safety, transient stability, and risk level—the invention comprehensively reflects their safety situation, thereby improving the accuracy of the assessment, effectively predicting fault risks in advance, and providing reliable guarantees for the safe and stable operation of the distribution network. Through visualization and early warning functions, the invention provides operators with intuitive and clear situational information, assisting them in adjusting operating methods and making risk prevention and control decisions, thereby improving the safe and stable operation level of the distribution network. In summary, this invention has the advantages of accurate prediction and efficient and convenient use.

[0016] The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A method for operational status awareness considering weak links in a power distribution network, characterized in that, Includes the following steps: Step 1: Based on the distribution network topology, equipment parameters, historical operating data and environmental factors, a multi-dimensional identification index system is constructed. The weak links of the distribution network are identified by combining the analytic hierarchy process (AHP) and the fuzzy comprehensive evaluation method. After identification, the weak links are sorted from most important to least important to form a list. Then, the list of weak links is updated in real time by combining the time-series weighted method and the grey relational analysis method. Step 2: Through the power distribution automation system, advanced measurement system and Internet of Things sensing devices, collect the operational data of the weak links identified in Step 1 in real time. The operational data includes electrical quantity data, equipment status data and environmental data. Subsequently, an adaptive anomaly detection algorithm combined with an improved Kalman filter was used to clean and filter the collected data. Finally, after normalization and fusion processing, a high-quality dataset was formed. Step 3: For the identified weaknesses, construct an operational status assessment model, and input the high-quality dataset from Step 2 into the operational status assessment model to assess the operational status and development trend of the weaknesses in real time and generate assessment results. Step 4: Based on the evaluation results in Step 3, use time series analysis, machine learning or deep learning algorithms to make short-term predictions of key operational indicators of weak links, thereby forming a predictive trend chart. Step 5: Set the early warning threshold, and then visualize the real-time operating status, evaluation results and predicted trend chart of the weak link through the human-computer interaction interface; when the information in the evaluation results or predicted trend chart exceeds the preset threshold, generate early warning information of different levels, and push the early warning information to the handheld terminal of the operation and maintenance personnel through the wireless transmission component.

2. The operational status awareness method considering weak links in the distribution network as described in claim 1, characterized in that: The weak links in the power distribution network in step 1 specifically include weak lines, weak nodes, and weak equipment.

3. The operational status perception method considering weak links in the distribution network as described in claim 1, characterized in that: The specific identification operation of the weak link in step 1 is as follows: the weight of each indicator is determined by the analytic hierarchy process, the degree of weakness of each node, equipment and line is quantitatively scored by the fuzzy comprehensive evaluation method, a scoring threshold is set, objects with scores higher than the threshold are defined as weak links, and sorted according to the scores.

4. The operational status perception method considering weak links in the distribution network as described in claim 1, characterized in that: The data normalization and fusion process in step 2 specifically involves: using the Z-score standardization method to unify the data dimensions, and using an attention-based feature fusion algorithm to achieve multi-source data fusion.

5. The operational status perception method considering weak links in the distribution network as described in claim 1, characterized in that: Step 3, the operational status assessment, includes static safety assessment, transient stability assessment, and risk level assessment. Static safety assessment involves calculating indicators such as the N-1 pass rate, voltage over-limit probability, and load rate over-limit probability of the weak link based on current operational data to evaluate its static safety. Transient stability assessment involves performing time-domain simulation or using data-driven methods to assess the transient stability margin of the weak link under fault conditions, targeting a preset set of typical faults. Risk level assessment involves comprehensively considering the static safety level, transient stability level, equipment health status, and external environmental factors of the weak link, using risk theory to calculate its comprehensive risk index, and classifying the risk level.

6. The operational status perception method considering weak links in the distribution network as described in claim 1, characterized in that: In step 5, the warning threshold can be determined based on the power distribution network safety operation procedures and historical fault data, while the warning information is divided into three levels: mild warning, moderate warning, and severe warning.