CN117674140B - Power distribution network measurement and control system and method - Google Patents
Power distribution network measurement and control system and method Download PDFInfo
- Publication number
- CN117674140B CN117674140B CN202410128882.3A CN202410128882A CN117674140B CN 117674140 B CN117674140 B CN 117674140B CN 202410128882 A CN202410128882 A CN 202410128882A CN 117674140 B CN117674140 B CN 117674140B
- Authority
- CN
- China
- Prior art keywords
- data
- distribution network
- power distribution
- algorithm
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005259 measurement Methods 0.000 title claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 76
- 238000004364 calculation method Methods 0.000 claims abstract description 25
- 230000004927 fusion Effects 0.000 claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 230000005611 electricity Effects 0.000 claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000007405 data analysis Methods 0.000 claims abstract description 16
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000006399 behavior Effects 0.000 claims description 18
- 230000007246 mechanism Effects 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 16
- 238000002955 isolation Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 9
- 239000002245 particle Substances 0.000 claims description 7
- 230000007787 long-term memory Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioethics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Security & Cryptography (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to the technical field of power distribution network measurement and control, in particular to a power distribution network measurement and control system and method. The method comprises the following steps: edge computing equipment is deployed in the power distribution network, power grid operation, environment and user electricity consumption data are collected, and data fusion and anomaly detection are carried out through edge computing; load and fault prediction are carried out by using a deep learning algorithm; performing self-adaptive network topology reconstruction according to the real-time data and the prediction result, rapidly responding to faults, isolating fault areas and reconfiguring the network; periodically optimizing edge calculation parameters, topology reconstruction and energy management strategies through big data analysis and machine learning technologies; ensuring data security and adopting data encryption and access control technology. By applying the technologies of edge calculation, deep learning, self-adaptive network topology reconstruction and the like, the intelligent level, reliability and safety of the power grid can be improved, so that the method has the beneficial effects of sustainable operation and optimal management of the power system.
Description
Technical Field
The invention relates to the technical field of power distribution network measurement and control, in particular to a power distribution network measurement and control system and method.
Background
With the development of technology, in particular in the context of smart grids, the management of power distribution networks is increasingly dependent on advanced information technology and automation technology. However, existing power distribution network measurement and control systems and methods face a number of technical challenges. First, the fusion and processing of data is a big challenge. The traditional power distribution network measurement and control system is generally not efficient enough in terms of data processing and anomaly detection, and the deployment and use of edge computing equipment are often insufficient, so that power grid operation data, environment data and user electricity consumption behavior patterns cannot be effectively fused and processed. This limits the ability of the system to detect early anomalies, affecting the operational safety and efficiency of the grid. Secondly, the accuracy of load prediction and fault early warning is also a problem. The prior art has the defects in the aspects of load prediction and fault early warning by using a deep learning algorithm, which may lead to inaccurate prediction of the power grid load and delay of response time of fault early warning, thereby affecting the stability and reliability of the power grid. Finally, data security and user privacy protection are not negligible aspects of modern power distribution network measurement and control systems. The current system has defects in the data encryption and access control technology, and the safety of data and the privacy of users cannot be fully ensured.
Disclosure of Invention
In order to solve the problems, the invention provides a power distribution network measurement and control system and a power distribution network measurement and control method.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in one aspect, a power distribution network measurement and control method includes the following steps:
Edge computing equipment is deployed in the power distribution network, power grid operation data, environment data and a user electricity behavior mode are collected, and data fusion and early anomaly detection are carried out through edge computing;
carrying out load prediction and fault early warning based on the fused multi-source data by using a deep learning algorithm;
Performing a self-adaptive network topology reconstruction algorithm based on the real-time data and the prediction result, and dynamically adjusting the structure of the power distribution network;
Formulating a fault isolation strategy, combining a self-healing mechanism of the power distribution network, quickly responding to faults, automatically isolating fault areas and reconfiguring the network;
the method comprises the steps of periodically collecting operation data by utilizing big data analysis and machine learning technology, and optimizing edge calculation parameters, topology reconstruction algorithm and energy management strategy;
And the data encryption and access control technology is applied to ensure the safety of the collected, transmitted and processed data.
Further, the edge computing device is specifically configured to process and analyze grid parameters and ensure data synchronization and real-time communication between devices.
Further, the data fusion and early anomaly detection by edge calculation include the following steps:
deploying edge computing equipment, and collecting power grid operation data, environment data and a user electricity behavior mode;
Cleaning and formatting the collected multi-source data;
The edge computing equipment extracts key features from the processed data and performs data fusion on the key features;
and based on the fused data, performing abnormality detection by setting a threshold value.
Further, the key features are specifically extracting a fluctuation mode of voltage and current from power grid operation data, extracting environmental factors related to power grid performance from environmental data and extracting electricity consumption peaks and valleys from user behavior data.
Furthermore, the deep learning algorithm is specifically a hybrid model combining a long-term and short-term memory network algorithm and a convolutional neural network algorithm.
Further, the process for constructing the hybrid model comprises the following steps:
Processing the time sequence data by using a long-term and short-term memory network algorithm, and extracting time sequence characteristics in the data;
Processing the image data through a convolutional neural network algorithm, and extracting spatial features in the data;
and (3) fusing the two characteristics, carrying out load prediction and fault early warning, and generating an analysis result.
Furthermore, the adaptive network topology reconstruction algorithm is performed based on the real-time data and the prediction result, and the power distribution network structure is dynamically adjusted, which comprises the following steps:
Obtaining analysis results of load prediction and fault early warning;
based on the analysis result, analyzing the topology structure of the current power distribution network, and identifying key nodes and paths in the power distribution network;
Determining an optimization target of topology reconstruction according to an operation target and a strategy of the power distribution network; the optimization targets include load balancing, fault response, energy efficiency, and system reliability;
based on the analysis result and the optimization target, a topology reconstruction scheme is formulated;
Automatically adjusting the structure of the power distribution network by using a self-adaptive topology reconstruction algorithm; the self-adaptive topology reconstruction algorithm is specifically a power distribution network reconstruction method based on a particle swarm optimization algorithm, and an optimal network structure is searched through a PSO algorithm to realize optimal configuration of resources.
Further, the method for making the fault isolation strategy, combining with a self-healing mechanism of the power distribution network, rapidly responding to the fault, automatically isolating the fault area and reconfiguring the network comprises the following steps:
monitoring the power distribution network in real time, detecting abnormal indexes by using a sensor and edge computing equipment, and analyzing data by using a deep learning algorithm;
when a fault is detected, automatically isolating a fault area;
After the fault area is isolated, a self-healing mechanism is started, the topological structure of the power grid is automatically recombined, and the normal power grid running state is recovered;
The performance and safety conditions of the distribution network are continuously monitored.
Further, the data encryption techniques include symmetric encryption, asymmetric encryption, and hash algorithms.
In another aspect, a power distribution network measurement and control system includes: the system comprises a data acquisition module, an edge calculation module, a data analysis module, a network topology optimization module and a data security module; the data acquisition module, the edge calculation module, the data security module, the network topology optimization module and the data analysis module are in communication connection;
the data acquisition module is used for acquiring power grid operation data, environment data and user electricity behavior data;
the edge calculation module is used for carrying out data fusion and early abnormality detection through edge calculation, implementing data synchronization and real-time communication and processing complex power grid parameters;
the data analysis module is used for carrying out load prediction and fault early warning through a deep learning algorithm, and analyzing the fusion data to generate a prediction model;
The network topology optimization module is used for dynamically adjusting the structure of the power distribution network according to real-time data and a prediction result by using a self-adaptive network topology reconstruction algorithm and managing fault isolation and self-healing mechanisms;
The data security module is used for realizing data encryption and access control and protecting data security and user privacy.
The invention has the beneficial effects that:
According to the invention, through the deployment of the edge computing equipment, the high-efficiency collection and processing of the power grid operation data, the environment data and the user electricity behavior mode are realized, and the speed and the accuracy of data processing are improved. And the load prediction and fault early warning are carried out based on the fused multi-source data by using a deep learning algorithm, so that the prediction accuracy and early warning timeliness of the power grid operation are remarkably improved. The structure of the power distribution network can be dynamically adjusted according to the real-time data and the prediction result through a self-adaptive network topology reconstruction algorithm, so that the stability and the reliability of the network are improved. When a fault occurs, an isolation strategy can be quickly formulated and combined with a self-healing mechanism response, a fault area is automatically isolated, and the network is reconfigured, so that the influence of the fault is reduced. And by utilizing big data analysis and machine learning technology, operation data are collected regularly and are used for optimizing edge calculation parameters, a topology reconstruction algorithm and an energy management strategy, so that continuous optimization and self-lifting of the system are realized. And the data encryption and access control technology is applied to ensure the safety of collected, transmitted and processed data, effectively prevent data leakage and illegal access and enhance the safety of the system.
Drawings
Fig. 1 is a schematic flow chart of a measurement and control method for a power distribution network in the invention.
Fig. 2 is a flowchart of step S3 in an embodiment of the invention.
Fig. 3 is a schematic block diagram of a measurement and control system for a power distribution network according to the present invention.
Detailed Description
Referring to fig. 1-3, the present invention relates to a measurement and control system and method for a power distribution network.
Example 1
A power distribution network measurement and control method comprises the following steps:
s1: edge computing equipment is deployed in the power distribution network, power grid operation data, environment data and a user electricity behavior mode are collected, and data fusion and early anomaly detection are carried out through edge computing; the edge computing equipment is particularly used for processing and analyzing the power grid parameters and ensuring data synchronization and real-time communication between the equipment;
the data fusion and early abnormality detection are carried out through edge calculation, and the method comprises the following steps:
deploying edge computing equipment, and collecting power grid operation data, environment data and a user electricity behavior mode;
Cleaning and formatting the collected multi-source data;
The edge computing equipment extracts key features from the processed data and performs data fusion on the key features; the key features are specifically that a fluctuation mode of voltage and current is extracted from power grid operation data, environmental factors related to power grid performance are extracted from environmental data, and electricity consumption peaks and valleys are extracted from user behavior data;
and based on the fused data, performing abnormality detection by setting a threshold value.
Specifically, edge computing devices are installed at key nodes of the distribution network (e.g., substations, power distribution cabinets). These devices are equipped with various sensors for collecting grid operation data, environmental data, and consumer electricity usage data in real time. The data collected by the device includes, but is not limited to, grid frequency fluctuations, load variations, climate conditions and consumer usage patterns. And cleaning the collected data, removing abnormal values and noise, and formatting the data for processing. Analyzing the voltage and current waveforms using a fourier transform algorithm to identify abnormal fluctuations or intermittent patterns; critical indicators are extracted, such as frequency deviation, transient voltage dip or peak values, which may be signs of grid load imbalance or equipment failure. Environmental parameters such as temperature, humidity, etc. are analyzed and correlated with the grid performance data to identify external factors that may affect the operation of the grid. Time series analysis is used to observe environmental trends and predict their potential impact on the grid. User power usage patterns, including peak and valley periods, are identified by data mining techniques, such as cluster analysis. Detecting unusual electrical behavior, such as sudden high power usage occurring during off-peak hours, may indicate illegal use of electricity or equipment failure. And forming a comprehensive data set by utilizing the processing capacity of edge calculation and combining the analysis results, and providing a comprehensive power grid state view. Data from different sources and features are effectively combined using data fusion algorithms, such as weighted averages or decision tree models. And setting the normal range of voltage, current, environmental parameters and user electricity consumption behaviors according to the historical data and industry standards. The edge computing device monitors the data in real time, compares to a set threshold, and immediately marks as abnormal once any parameter is found to be outside the normal range.
S2: carrying out load prediction and fault early warning based on the fused multi-source data by using a deep learning algorithm; the deep learning algorithm is specifically a hybrid model combining a long-term and short-term memory network algorithm and a convolutional neural network algorithm;
the construction process of the hybrid model comprises the following steps:
Processing the time sequence data by using a long-term and short-term memory network algorithm, and extracting time sequence characteristics in the data;
Processing the image data through a convolutional neural network algorithm, and extracting spatial features in the data;
the two characteristics are fused, load prediction and fault early warning are carried out, and an analysis result is generated;
In particular, the time series data of the power grid is preprocessed, for example normalized data, to adapt it to the LSTM network; including grid load data, power usage patterns, frequency fluctuations, etc. Designing an LSTM layer to capture long-term and short-term dependencies in time series data; multiple layers of LSTM structures can be used to handle complex time dependencies. LSTM networks effectively learn important timing features in data, such as periodic variations, trends, and seasonal fluctuations, through their internal gate control regimes. The LSTM model is trained by using the historical data of the power grid, and the performance of the model is optimized by adjusting network parameters (such as the layer number, the neuron number and the learning rate). If there is image data (e.g., a thermal image of the grid device), the necessary preprocessing, such as scaling, cropping, and normalization, is performed. The design of the convolution layer automatically extracts key spatial features in the image. This may include visual patterns of device status, signs of damage, or environmental changes. CNNs are able to capture detail and structural information in images by extracting spatial features in the image data through multiple convolution and pooling layers. And training a CNN model by using an image data set related to the power grid, and improving the recognition capability of the model to the state of the power grid equipment by adjusting parameters such as the size of a convolution kernel, the number of filters and the like. The LSTM extracted time series features and the CNN extracted spatial features are combined. May be implemented using weighted averaging or feature transformation techniques. After feature fusion, a hybrid deep learning model is constructed that contains LSTM and CNN layers. The model can process time sequence and space information simultaneously, and provides a more comprehensive view angle for power grid load prediction and fault early warning. The hybrid model is trained using historical data sets (including time series and image data). This process includes adjusting the network architecture, optimizing the loss function, and selecting the appropriate optimizers. And the model parameters are optimized through cross verification and different evaluation indexes, so that the model is ensured to have good performance on different data sets. The output of the hybrid model will be a prediction of future grid loads and an early warning of potential faults. These outputs may be presented in the form of probability distributions, trend graphs, or fault probabilities. The model output is applied to the operation and maintenance decisions of the grid. For example, when predicting high loads, adjusting load management of the grid; and when the fault is early warned, guiding a maintenance team to intervene in advance.
S3: performing a self-adaptive network topology reconstruction algorithm based on the real-time data and the prediction result, and dynamically adjusting the structure of the power distribution network;
the step S3 specifically includes the following steps:
s31: obtaining analysis results of load prediction and fault early warning;
S32: based on the analysis result, analyzing the topology structure of the current power distribution network, and identifying key nodes and paths in the power distribution network;
s33: determining an optimization target of topology reconstruction according to an operation target and a strategy of the power distribution network; the optimization targets include load balancing, fault response, energy efficiency, and system reliability;
S34: based on the analysis result and the optimization target, a topology reconstruction scheme is formulated;
s35: automatically adjusting the structure of the power distribution network by using a self-adaptive topology reconstruction algorithm; the self-adaptive topology reconstruction algorithm is specifically a power distribution network reconstruction method based on a particle swarm optimization algorithm, and an optimal network structure is searched through a PSO algorithm to realize optimal configuration of resources.
Specifically, the analysis results of load prediction and fault early warning are obtained, and a current power grid topological graph is drawn, wherein the current power grid topological graph comprises all nodes (such as a transformer substation, a power distribution cabinet and a user access point) and connection paths (such as a power transmission line). Using graph theory algorithms, key nodes and paths are identified. Combining historical fault data with real-time monitoring data, weak points and potentially faulty areas in the power grid, such as overloaded lines or aged equipment, are identified. Optimization objectives include ensuring load balancing of individual nodes and paths to avoid overload or inefficient operation. The speed and the efficiency of fault detection and response are improved. Upon detection of a potential failure, the affected area can be quickly isolated and the network reconfigured to maintain stable operation. By optimizing the distribution path and the load distribution, the energy efficiency of the whole network is improved, and the energy loss is reduced. The overall reliability of the grid is enhanced, including the ability to resist environmental changes and to maintain stable operation in the face of emergencies. A series of possible topology alterations are designed based on the identified critical nodes, paths and potential points of failure. These schemes should take into account different load conditions, the probability of failure occurrence, and the impact on network stability. And using simulation software to perform multi-scene simulation test on each topology reconstruction scheme. And simulating different loads and fault conditions, and evaluating the influence of each scheme on the performance of the power grid. And according to the simulation result, evaluating the load balancing effect, fault response capability, energy efficiency and system reliability of each scheme. And selecting a scheme with the optimal comprehensive performance as an implementation plan of topology reconstruction. In the topology reconstruction process, an optimal topology structure is found by adopting a PSO-based algorithm. In PSO, each "particle" represents one possible network topology configuration, whose performance is evaluated by simulating grid operation. And in the running process of the algorithm, the searching direction of each particle is continuously adjusted according to the historical optimal position and the global optimal position of each particle. In the iterative process, the particles explore new network topology configuration and find the optimal solution meeting the optimization target. Once the algorithm finds the optimal network topology, the actual distribution network structure is automatically adjusted through the intelligent switch and the control system. For example, enabling a backup path, adjusting transformer load, or reconfiguring a power supply area.
S4: formulating a fault isolation strategy, combining a self-healing mechanism of the power distribution network, quickly responding to faults, automatically isolating fault areas and reconfiguring the network;
The step S4 specifically includes the following steps:
s41: monitoring the power distribution network in real time, detecting abnormal indexes by using a sensor and edge computing equipment, and analyzing data by using a deep learning algorithm;
S42: when a fault is detected, automatically isolating a fault area;
s43: after the fault area is isolated, a self-healing mechanism is started, the topological structure of the power grid is automatically recombined, and the normal power grid running state is recovered;
s44: the performance and safety conditions of the distribution network are continuously monitored.
Specifically, sensors installed at key points of the distribution network are used to monitor key indicators such as voltage level, current imbalance, frequency fluctuation and temperature rise in real time. These sensors are able to capture the immediate status and subtle changes of the grid. The edge computing device performs on-the-fly processing of the collected data, such as denoising, normalization, and trend analysis. This step enables preliminary fault identification before the data is transmitted to the central processing system. The preliminary processed data is fed into a deep learning model to further analyze and identify potential failure modes. These models can learn from historical data to more accurately identify abnormal patterns. Once the deep learning model confirms the fault, the system immediately starts a fault isolation protocol, sends out an instruction, and automatically activates a breaker or a disconnector in the power distribution network. The isolation strategy of the fault area is based on the principle of minimizing the influence on surrounding areas, only the line directly affected by the fault is isolated, other lines are kept to normally operate, the system ensures that the fault isolation process is rapidly carried out, and therefore the influence of the fault on the whole power grid and end users is reduced. After the fault area is isolated, the system automatically triggers a self-healing mechanism of the power grid. This includes reorganizing the topology of the grid using pre-set algorithms and rules, such as traffic-based redirection or priority-based load shifting. The system identifies and enables the backup power transmission path, ensuring continuity of the power supply. If the main line is isolated due to a fault, the system will automatically redirect the current to the backup line. According to the current power grid state and load requirements, the settings of the transformer and the distributor are dynamically adjusted to achieve more efficient load balancing and energy distribution. Even after fault handling and recovery to normal operation, the system continuously monitors various performance metrics of the power grid, such as voltage level, current flow and frequency stability, to ensure that the power grid is operating in an optimal state. Security assessments are made regularly, including analysis of possible risk points, sensitivity and response capability of the detection system.
S5: the method comprises the steps of periodically collecting operation data by utilizing big data analysis and machine learning technology, and optimizing edge calculation parameters, topology reconstruction algorithm and energy management strategy;
Specifically, multi-source data including load patterns, device operating states, fault histories, and environmental conditions are continuously collected by the edge computing device. A centralized data warehouse is established, storing and preprocessing such collected data, such as data cleansing and formatting. Models are developed using supervised and unsupervised learning techniques, such as decision trees, support vector machines, or neural networks, to identify load patterns, predict risk of failure, etc. Based on the machine learning analysis results, the edge calculation parameters are optimized, the topology reconstruction algorithm is adjusted to adapt to changing load conditions, and a more efficient energy management strategy is formulated.
S6: the data encryption and access control technology is used for guaranteeing the safety of collected, transmitted and processed data; the data encryption techniques include symmetric encryption, asymmetric encryption, and hash algorithms.
Specifically, the AES or DES algorithm is used for encrypting the transmitted and stored data, so that the safety of the data in the transmission process is ensured. Encryption of critical data, such as control commands and sensitive information, using RSA or ECC algorithms ensures that only specific recipients are able to decrypt. A unique hash value is generated for the data using SHA-256 or MD5 for verifying the integrity and consistency of the data. Powerful user authentication mechanisms are implemented, including multi-factor authentication such as passwords, biometrics, and security tokens. Different access rights are allocated according to the roles of the users, so that the users can only access the data and functions required by the roles of the users. A logging and monitoring system is implemented that tracks all access and operation to the system and data for investigation and response in the event of a security event.
In the embodiment, by deploying edge computing equipment at key nodes of the power distribution network and using a deep learning algorithm, the system can monitor the running state of the power grid in real time and predict loads and faults. This helps to find potential problems ahead of time and take corresponding action, thereby improving the reliability and stability of the grid. The multi-source data are fused through the edge computing equipment, the anomaly detection is carried out by utilizing the deep learning algorithm, and the system can more accurately identify the abnormal conditions in the operation of the power grid, including power fluctuation, environmental change and abnormal electricity consumption behaviors, so that the accuracy of fault diagnosis is improved. Based on the real-time data and the prediction result, the system adopts a self-adaptive network topology reconstruction algorithm to dynamically adjust the structure of the power distribution network. This helps optimize the performance of the power grid, improving load balancing, fault response, energy efficiency, and system reliability, thereby improving the operating efficiency of the overall power distribution system. The power distribution network detects faults through a real-time monitoring and deep learning algorithm, automatically isolates fault areas, and starts a self-healing mechanism to quickly recover the normal running state of the power grid. This helps to minimize the impact of faults on the grid, improving the robustness and recoverability of the grid. And data encryption and access control technology is adopted to ensure the safety of collected, transmitted and processed data. This includes the use of symmetric encryption, asymmetric encryption and hashing algorithms, as well as powerful user authentication mechanisms, helping to protect against potential network attacks and data leakage. With big data analysis and machine learning techniques, the system can collect operational data and optimize it periodically. Through continuous learning and adjustment of the model, the system can adapt to continuously changing load conditions, and the effects of a topology reconstruction algorithm and an energy management strategy are improved.
Example 2
The power distribution network measurement and control method according to embodiment 1, wherein a power distribution network measurement and control system comprises: the system comprises a data acquisition module, an edge calculation module, a data analysis module, a network topology optimization module and a data security module; the data acquisition module, the edge calculation module, the data security module, the network topology optimization module and the data analysis module are in communication connection;
the data acquisition module is used for acquiring power grid operation data, environment data and user electricity behavior data;
the edge calculation module is used for carrying out data fusion and early abnormality detection through edge calculation, implementing data synchronization and real-time communication and processing complex power grid parameters;
the data analysis module is used for carrying out load prediction and fault early warning through a deep learning algorithm, and analyzing the fusion data to generate a prediction model;
The network topology optimization module is used for dynamically adjusting the structure of the power distribution network according to real-time data and a prediction result by using a self-adaptive network topology reconstruction algorithm and managing fault isolation and self-healing mechanisms;
The data security module is used for realizing data encryption and access control and protecting data security and user privacy.
In this embodiment, the data acquisition module is responsible for acquiring power grid operation data, environment data, and user electricity behavior data. This helps the system to obtain critical real-time information, including power system status, environmental conditions, and user requirements, providing a sufficient data base for analysis and decision making of the system. The edge calculation module processes the acquired data in real time through an edge calculation technology, wherein the data fusion and the early abnormality detection are included, the data processing efficiency is improved, and meanwhile, the timely abnormality detection and response are ensured.
And the data analysis module utilizes a deep learning algorithm to predict load and early warn faults. By learning historical data and modes, the system can more accurately predict future power grid loads and possible faults, and more intelligent support is provided for operation decisions. And the network topology optimization module dynamically adjusts the structure of the power distribution network according to the real-time data and the prediction result by using a self-adaptive network topology reconstruction algorithm. The method is beneficial to optimizing the performance of the power grid, improving load balance, fault response, energy efficiency and system reliability, and realizing more flexible and intelligent power grid operation. The system manages fault isolation and self-healing mechanisms through a network topology optimization module. Once the fault occurs, the system can automatically isolate the fault area, and the power grid structure is reconfigured in a self-adaptive mode, so that the rapid self-healing of the power grid is realized, and the influence of the fault on the whole system is reduced. The data security module is responsible for realizing data encryption and access control, and guaranteeing the security of collected, transmitted and processed data. By adopting the encryption technology and the access control, potential network attack and data leakage can be effectively prevented, and the privacy of the user is ensured to be fully protected.
The above embodiments are merely illustrative of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solution of the present invention should fall within the scope of protection defined by the claims of the present invention without departing from the spirit of the design of the present invention.
Claims (4)
1. The power distribution network measurement and control method is characterized by comprising the following steps of:
Edge computing equipment is deployed in the power distribution network, power grid operation data, environment data and a user electricity behavior mode are collected, and data fusion and early anomaly detection are carried out through edge computing;
Carrying out load prediction and fault early warning based on the fused multi-source data by using a deep learning algorithm; the multi-source data comprise power grid frequency fluctuation, load change, climate conditions and user power utilization modes;
Performing a self-adaptive network topology reconstruction algorithm based on the real-time data and the prediction result, and dynamically adjusting the structure of the power distribution network;
Formulating a fault isolation strategy, combining a self-healing mechanism of the power distribution network, quickly responding to faults, automatically isolating fault areas and reconfiguring the network;
the method comprises the steps of periodically collecting operation data by utilizing big data analysis and machine learning technology, and optimizing edge calculation parameters, topology reconstruction algorithm and energy management strategy;
The data encryption and access control technology is used for guaranteeing the safety of collected, transmitted and processed data;
the data fusion and early abnormality detection are carried out through edge calculation, and the method comprises the following steps:
deploying edge computing equipment, and collecting power grid operation data, environment data and a user electricity behavior mode;
Cleaning and formatting the collected multi-source data;
the edge computing equipment extracts key features from the processed data and performs data fusion on the key features; the key features are specifically that a fluctuation mode of voltage and current is extracted from power grid operation data, environmental factors related to power grid performance are extracted from environmental data, and electricity consumption peaks and valleys are extracted from user behavior data; the data fusion adopts a weighted average algorithm;
Based on the fused data, performing abnormality detection by setting a threshold;
the deep learning algorithm is specifically a hybrid model combining a long-term and short-term memory network algorithm and a convolutional neural network algorithm;
The construction process of the hybrid model comprises the following steps:
processing the time sequence data by using a long-term and short-term memory network algorithm, and extracting time sequence characteristics in the data; the time sequence characteristics comprise power grid load data, a power consumption mode and frequency fluctuation;
processing the image data through a convolutional neural network algorithm, and extracting spatial features in the data; the spatial features include visual patterns of device status, signs of damage, or environmental changes;
the two characteristics are fused, load prediction and fault early warning are carried out, and an analysis result is generated;
the self-adaptive network topology reconstruction algorithm is performed based on the real-time data and the prediction result, and the structure of the power distribution network is dynamically adjusted, and the method comprises the following steps:
Obtaining analysis results of load prediction and fault early warning, and drawing a power grid topological graph; the power grid topological graph comprises a transformer substation, a power distribution cabinet, a user access point and a power transmission line as a plurality of nodes and connection paths of the power grid topological graph;
based on the analysis result, analyzing the topology structure of the current power distribution network, and identifying key nodes and paths in the power distribution network by using a graph theory algorithm;
Determining an optimization target of topology reconstruction according to an operation target and a strategy of the power distribution network; the optimization targets include load balancing, fault response, energy efficiency, and system reliability;
based on the analysis result and the optimization target, a topology reconstruction scheme is formulated;
Automatically adjusting the structure of the power distribution network by using a self-adaptive topology reconstruction algorithm; the self-adaptive topology reconstruction algorithm is specifically a power distribution network reconstruction method based on a particle swarm optimization algorithm, and an optimal network structure is searched through a PSO algorithm to realize optimal configuration of resources;
The method for setting the fault isolation strategy, combining with a self-healing mechanism of the power distribution network, rapidly responding to faults, automatically isolating fault areas and reconfiguring the network comprises the following steps:
Monitoring the power distribution network in real time, detecting abnormal indexes by using a sensor and edge computing equipment, and analyzing data by using a deep learning algorithm; the anomaly indicators include voltage level, current balance, and frequency fluctuation;
When a fault is detected, automatically isolating a fault area; the isolation strategy of the fault area is based on a principle of minimizing the influence on surrounding areas;
After the fault area is isolated, a self-healing mechanism is started, the topological structure of the power grid is automatically recombined, and the normal power grid running state is recovered; the self-healing mechanism is specifically formulated based on traffic redirection or priority-based load transfer;
The performance and safety conditions of the distribution network are continuously monitored.
2. The power distribution network measurement and control method according to claim 1, wherein the edge computing device is specifically configured to process and analyze power grid parameters and ensure data synchronization and real-time communication between devices.
3. The method for measuring and controlling power distribution network according to claim 1, wherein the algorithm used in the data encryption comprises symmetric encryption, asymmetric encryption and hash algorithm.
4. A power distribution network measurement and control system, characterized in that the system is applied to a power distribution network measurement and control method as claimed in any one of claims 1-3, comprising: the system comprises a data acquisition module, an edge calculation module, a data analysis module, a network topology optimization module and a data security module; the data acquisition module, the edge calculation module, the data security module, the network topology optimization module and the data analysis module are in communication connection;
the data acquisition module is used for acquiring power grid operation data, environment data and user electricity behavior data;
the edge calculation module is used for carrying out data fusion and early abnormality detection through edge calculation, implementing data synchronization and real-time communication and processing complex power grid parameters;
the data analysis module is used for carrying out load prediction and fault early warning through a deep learning algorithm, and analyzing the fusion data to generate a prediction model;
The network topology optimization module is used for dynamically adjusting the structure of the power distribution network according to real-time data and a prediction result by using a self-adaptive network topology reconstruction algorithm and managing fault isolation and self-healing mechanisms;
The data security module is used for realizing data encryption and access control and protecting data security and user privacy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128882.3A CN117674140B (en) | 2024-01-31 | 2024-01-31 | Power distribution network measurement and control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410128882.3A CN117674140B (en) | 2024-01-31 | 2024-01-31 | Power distribution network measurement and control system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117674140A CN117674140A (en) | 2024-03-08 |
| CN117674140B true CN117674140B (en) | 2024-06-04 |
Family
ID=90079186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410128882.3A Active CN117674140B (en) | 2024-01-31 | 2024-01-31 | Power distribution network measurement and control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117674140B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118137671A (en) * | 2024-03-26 | 2024-06-04 | 国网甘肃省电力公司天水供电公司 | Intelligent power distribution network fault early warning system based on natural disasters |
| CN118017509B (en) * | 2024-04-10 | 2024-07-16 | 国网江苏省电力有限公司南通供电分公司 | Large-scale power distribution network parallel optimization method based on digital twin space |
| CN118229086A (en) * | 2024-04-12 | 2024-06-21 | 江苏思行达信息技术股份有限公司 | Service monitoring and risk prediction closed-loop method based on power grid marketing management |
| CN118157132B (en) * | 2024-05-10 | 2024-08-02 | 南京亿顺弘信息技术有限公司 | Data mining method and device for voltage monitoring system based on neural network |
| CN118157333B (en) * | 2024-05-13 | 2024-08-20 | 苏州火炎焱网络科技有限公司 | Intelligent monitoring method and system for distribution transformer area based on Internet of things technology |
| CN118226179B (en) * | 2024-05-17 | 2024-08-02 | 中域高科（武汉）信息技术有限公司 | Distribution network automatic relay protection test system |
| CN118249295B (en) * | 2024-05-27 | 2024-07-26 | 希格玛电气(珠海)有限公司 | Intelligent protection system of power distribution device |
| CN118367551B (en) * | 2024-06-19 | 2024-08-20 | 泰亿达科技集团有限公司 | Power grid intelligent power distribution method, system and medium for balanced distribution optimization |
| CN118472938B (en) * | 2024-06-20 | 2024-09-24 | 广东电网有限责任公司阳江供电局 | Multi-level cooperative power grid real-time control method and control system thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104734153A (en) * | 2014-12-18 | 2015-06-24 | 国家电网公司 | Method of reconstructing power distribution network containing distributed power supply |
| JP2018057096A (en) * | 2016-09-27 | 2018-04-05 | 株式会社日立製作所 | Power system characteristic estimating device and method, and power system managing apparatus |
| CN112669172A (en) * | 2020-12-31 | 2021-04-16 | 国电南瑞南京控制系统有限公司 | Power distribution network regional autonomous rapid response method and system based on dynamic fusion of edge data |
| CN114595874A (en) * | 2022-02-24 | 2022-06-07 | 武汉大学 | Ultra-short-term power load prediction method based on dynamic neural network |
| CN116470504A (en) * | 2023-05-15 | 2023-07-21 | 东方电子股份有限公司 | Self-healing control system of distributed power distribution network |
| CN117040105A (en) * | 2023-06-21 | 2023-11-10 | 北京智芯微电子科技有限公司 | Fault self-adaption and self-healing method, intelligent agent terminal and intelligent terminal |
| CN117411192A (en) * | 2023-12-15 | 2024-01-16 | 东莞市华灏技术有限公司 | Monitoring method and system for uninterruptible power supply parallel operation system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311008B (en) * | 2020-02-21 | 2021-04-30 | 山东大学 | AC/DC large power grid dynamic security risk situation rolling prospective early warning method and system |
-
2024
- 2024-01-31 CN CN202410128882.3A patent/CN117674140B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104734153A (en) * | 2014-12-18 | 2015-06-24 | 国家电网公司 | Method of reconstructing power distribution network containing distributed power supply |
| JP2018057096A (en) * | 2016-09-27 | 2018-04-05 | 株式会社日立製作所 | Power system characteristic estimating device and method, and power system managing apparatus |
| CN112669172A (en) * | 2020-12-31 | 2021-04-16 | 国电南瑞南京控制系统有限公司 | Power distribution network regional autonomous rapid response method and system based on dynamic fusion of edge data |
| CN114595874A (en) * | 2022-02-24 | 2022-06-07 | 武汉大学 | Ultra-short-term power load prediction method based on dynamic neural network |
| CN116470504A (en) * | 2023-05-15 | 2023-07-21 | 东方电子股份有限公司 | Self-healing control system of distributed power distribution network |
| CN117040105A (en) * | 2023-06-21 | 2023-11-10 | 北京智芯微电子科技有限公司 | Fault self-adaption and self-healing method, intelligent agent terminal and intelligent terminal |
| CN117411192A (en) * | 2023-12-15 | 2024-01-16 | 东莞市华灏技术有限公司 | Monitoring method and system for uninterruptible power supply parallel operation system |
Non-Patent Citations (1)
| Title |
|---|
| 基于多Agent免疫算法的智能配电网自愈技术研究;纪秀 等;计算机测量与控制;20160225;第24卷(第2期);第247-250页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117674140A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117674140B (en) | Power distribution network measurement and control system and method | |
| Mohammadpourfard et al. | A statistical unsupervised method against false data injection attacks: A visualization-based approach | |
| US10452845B2 (en) | Generic framework to detect cyber threats in electric power grid | |
| Pei et al. | PMU placement protection against coordinated false data injection attacks in smart grid | |
| CN109787979B (en) | Method for detecting electric power network event and invasion | |
| Guo et al. | Online data validation for distribution operations against cybertampering | |
| CN117408162B (en) | Power grid fault control method based on digital twin | |
| US12039045B2 (en) | Event analysis in an electric power system | |
| Ruan et al. | Deep learning for cybersecurity in smart grids: Review and perspectives | |
| Diaba et al. | Cyber security in power systems using meta-heuristic and deep learning algorithms | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| Wang et al. | Data-driven anomaly detection for power system generation control | |
| WO2024003367A1 (en) | Method and device for forecasting upcoming faults in power systems | |
| CN118035814A (en) | State fault early warning method and system based on digital twin field data analysis equipment | |
| Nagaraj et al. | Glass: A graph learning approach for software defined network based smart grid ddos security | |
| CN117031201A (en) | Multi-scene topology anomaly identification method and system for power distribution network | |
| Kaitovic et al. | Proactive failure management in smart grids for improved resilience: A methodology for failure prediction and mitigation | |
| Mohammadi et al. | A review of cyber–resilient smart grid | |
| Hossain-McKenzie et al. | Adaptive, cyber-physical special protection schemes to defend the electric grid against predictable and unpredictable disturbances | |
| Gokarn et al. | Enhancing cyber physical system security via anomaly detection using behaviour analysis | |
| Lu et al. | A multi-layer, hierarchical information management system for the smart grid | |
| Fahim et al. | The role of machine learning in improving power distribution systems resilience | |
| Ma | Enhancing grid reliability with phasor measurement units | |
| Salehpour et al. | An RTDS-based Early-stage Attack Detection Mechanism for Smart Grid Networks | |
| Ten et al. | Anomaly extraction and correlations for power infrastructure cyber systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |