575 results about "Smart grid" patented technology

The embodiment of the invention provides a power distribution network dynamic reconstruction method based on knowledge-guided large model enhanced fine tuning and related equipment, and belongs to the technical field of smart power grids and artificial intelligence. The method comprises the following steps: constructing a power distribution network dynamic knowledge graph, and providing structured knowledge guidance for model training; subgraph sampling is carried out based on the timestamp and converted into a fine tuning sample, and a training data set is generated; utilizing the data set to supervise, finely adjust and preheat the large language model; designing a multi-dimensional reward function of fusion format accuracy, economy and security based on mechanism knowledge in the knowledge graph and expert experience; a group relative strategy optimization mechanism is adopted to carry out reinforced fine tuning on the large language model, and the large language model is guided to output a safe, reliable and economical dynamic reconstruction strategy in interaction with the environment. According to the method, the problems of lack of training data, lack of physical knowledge guidance and insufficient decision reliability of a large language model in the power grid field are solved, and the intelligent level and decision quality of dynamic reconstruction of the power distribution network are remarkably improved.

The present invention belongs to the field of smart power grids and power system automation control. Disclosed is a load emergency control method based on a dynamic event triggering mechanism, which method comprises: on the basis of an indicator of safe operation of a system, performing region division on a distribution network; proposing an adaptive load level division method based on user response willingness, and by taking the minimization of the system operation cost of the distribution network as an objective, establishing a precise load control model of the distribution network; and using a dynamic event triggering mechanism to reduce communication between substations and a master station of the distribution network, so as to realize effective exchange and precise execution of load control policy information. The method of the present invention can precisely realize precise control of a load, and can effectively alleviate communication transmission pressure of a distribution network, thereby ensuring the stability of a power grid and the continuous supply of critical loads.

The invention relates to the technical field of intelligent power grid and electric vehicle cooperative control, and discloses a plug-and-play and flexible power regulation and control integrated vehicle network interaction cooperative control system, which comprises a protocol adaptive conversion module, a multi-modal data alignment module, a flexible power regulation and control module, a vehicle pile identity authentication module and a power grid state sensing module, and realizing inter-generation vehicle millisecond-level identification and data unified modeling through the protocol middleware. According to the method, the problems of protocol compatibility and data alignment in a plug-and-play scene are solved, and deep coordination between the charging process and the power grid state is realized through flexible power regulation and control and a multi-stage safety mechanism. The system guarantees the non-inductive charging experience of a user, reduces the impact on a power grid to the maximum extent, prolongs the service life of a battery, and improves the energy utilization efficiency.

The invention discloses an HPLC and HRF dual-mode communication method and system for an intelligent power grid, and the method comprises the steps: enabling a source communication node to transmit power grid service data through an HPLC and HRF dual channel, and forming a dual-mode data package; after receiving the data, the target communication node demodulates and recovers service data from the HPLC and HRF signals, synchronously measures and calculates the two paths of signals, and extracts real-time cable fingerprints reflecting power line medium characteristics and real-time space fingerprints reflecting space wireless characteristics; further, performing similarity comparison on the real-time dual-mode fingerprint and a pre-stored source node reference dual-mode fingerprint; and finally, judging the security state of the communication link and the validity of the data in a combined manner according to whether the comparison result meets a credible threshold value or not and by combining the integrity verification of the service data, and executing subsequent network operation accordingly. According to the invention, the physical layer fingerprints are invisibly extracted in normal service communication, so that real-time link authentication without special detection signals is realized, and man-in-the-middle attack and equipment counterfeit are effectively defended.

The invention relates to the technical field of energy meteorology and intelligent power grids, in particular to a multi-extreme meteorological high-risk scene set generation method, system and equipment based on a joint training generative adversarial network. The method comprises the following steps: constructing a physical information generative adversarial network framework comprising a generator, a discriminator, a predictor and a physical constraint module; designing a multi-objective loss function fusing adversarial loss, prediction loss, physical consistency loss and task performance loss; adopting a training strategy combining meta-learning initialization and incremental learning to jointly optimize parameters of the generator and the discriminator in stages; extreme risk scene data of specified disaster types, seasons and intensity grades are generated through condition vector control, and the extreme risk scene data are stored in a high-risk scene library after physical consistency verification. Through the method, a multi-extreme-weather high-risk scene set with statistical authenticity, physical rationality and task correlation can be directly generated, and the risk identification, scheduling optimization and toughness evaluation capabilities of the clean energy base under extreme weather conditions are remarkably improved; the problems of sample scarcity, model overfitting and lack of physical constraints in scene generation in the prior art are solved, efficient and automatic generation of a high-risk scene is realized, and reliable data support is provided for power grid toughness evaluation and scheduling decision of a clean energy base.

The invention discloses a power distribution network cluster dividing and planning method adaptive to distributed power consumption, and belongs to the technical field of intelligent power grid and distributed energy optimization scheduling. The invention aims to solve the current situation that the traditional centralized scheduling mode is difficult to effectively deal with the problems of power fluctuation and local imbalance of the distributed power supply, so that the operation efficiency of a power grid is low and the consumption capability of the distributed power supply is insufficient. The cluster dividing and planning method comprises the following steps: constructing a digital twin model of the power distribution network, and realizing high-precision real-time mapping and dynamic updating; based on the electrical distance and sensitivity characteristics, adaptive cluster division is realized by using a clustering algorithm; the fluctuation characteristics of the distributed power supply are accurately quantified through residual variance and wavelet energy analysis; establishing an operation cost and distributed power consumption dual-objective optimization model, and realizing economic dispatching; and a layered dynamic coordination control mechanism is designed to ensure voltage and frequency stability and overall economy of the power distribution network. According to the invention, the consumption capability of the distributed power supply and the economic operation level of the system are obviously improved.

The invention relates to the technical field of intelligent power grids, in particular to an optical storage agricultural micro-grid operation optimization method and system, and the method comprises the steps: constructing an optical storage agricultural greenhouse micro-grid, and constructing a robust optimization scheduling model under the photovoltaic output uncertainty to carry out robust optimization scheduling; based on the scheduling scheme of robust optimization scheduling, constructing a micro-grid load model for the light storage agricultural greenhouse; on the basis of the load demand in the micro-grid load model, a cost-benefit optimization model under two operation modes of autonomous investment construction and energy performance contract is constructed, and the cost-benefit is calculated on the basis of the cost-benefit optimization model under the actual operation mode, so that the energy storage capacity configuration and the operation strategy are subjected to collaborative optimization. And constructing an energy storage system capacity configuration and operation optimization model, and finally determining an energy storage configuration scheme and a multi-time scale scheduling strategy. According to the invention, the problems of photovoltaic output uncertainty, single investment operation mode and insufficient economical efficiency optimization of the existing system are effectively solved.

The invention relates to the technical field of power distribution automation and intelligent power grid equipment, in particular to an FTU-based intelligent voltage regulation protection bypass cooperative control system, which comprises a state acquisition module, a state identification module, a self-adaptive disturbance judgment module, a voltage regulation cooperative module and a state reconstruction module, the system establishes an operation state vector model by synchronously sampling the voltage and current of a distribution line and the states of a circuit breaker and a bypass switch; judging line operation conditions according to vector state classification, and generating corresponding action priorities and time windows; unified scheduling and interlocking control are carried out on the voltage regulation unit, the protection unit and the bypass unit through the cooperative control execution module, and logic cooperation and state closed-loop updating of multiple control objects are achieved; according to the invention, time sequence coordination and intelligent linkage of voltage regulation, protection and bypass operation can be realized under complex working conditions, the voltage stability and the operation reliability of the distribution line are improved, the fault conflict probability is reduced, and the operation and maintenance intervention is reduced.

The invention discloses a comprehensive optimization method of a power grid, which relates to the technical field of power grid optimization, and comprises the following steps of: constructing a multi-dimensional data fusion layer, integrating data such as power grid real-time measurement, new energy prediction, load response and electric power science and technology information, establishing a'source-grid-load-storage 'collaborative optimization model, and introducing multi-target constraint. An improved interpretable reinforcement learning algorithm is adopted for solving, and a dynamic checking and iterative optimization mechanism is established. The comprehensive optimization method of the power supply power grid is suitable for real-time scheduling and medium and long term planning scenes of a complex smart power grid, can reduce the line loss rate of the power grid, improve the consumption rate of renewable energy sources and improve the decision interpretation degree, is obviously superior to an existing optimization method, provides powerful technical support for construction of a novel power system, and has good application prospects. The technical problems of insufficient collaboration, low decision transparency, weak anti-interference capability and the like of power grid optimization in a high-proportion renewable energy access scene are effectively solved.

The invention provides a distribution network traveling wave fault early warning positioning analysis method and system, and belongs to the technical field of smart power grids, and the method comprises the steps: obtaining a plurality of traveling wave signals of a distribution network line, and filtering the interference to obtain a high-fidelity traveling wave signal; constructing a basic wave velocity model and a dynamic wave velocity correction model, and calculating coordinates of a fault point by adopting a double-end, single-end and branch node three-dimensional positioning algorithm; extracting basic parameters of a time domain, a frequency domain and a polarity domain from the high-fidelity traveling wave signal, and obtaining coupling correlation characteristics among the basic parameters; establishing a fault mechanism model library, and substituting the basic parameters and the coupling correlation features into the model library for adaptation to determine a preliminary fault type; and performing parameter conflict verification on the preliminary fault type. According to the distribution network traveling wave fault early warning positioning analysis method provided by the invention, the signal acquisition dimension is expanded to electrical and vibration three-dimensional signals, the fault type identification accuracy is also improved, and different fault types with similar peak values can be accurately distinguished.

The invention provides a power transmission line fire risk grade zoning prediction method and system, and relates to the technical field of intelligent power grid environment perception and risk early warning, and the method comprises the steps: data collection and multi-source space-time fusion: collecting the regional characteristics of the historical fire occurrence space-time, real-time meteorological parameters, vegetation types and combustible rates of a power transmission line to form a multi-source data set, the multi-source data set realizes alignment coding through a unified geographic grid and a timestamp, and a fire risk sample set is generated. Through a multi-source data deep fusion and grid space-time alignment mechanism, unified coding and coupling modeling of regional features such as historical fire occurrence space-time, real-time meteorological parameters, vegetation types and combustible rates are realized; risk zoning precision and spatial resolution are remarkably improved, zoning granularity can be refined in practical application, the resolution is far better than that of a traditional method, and the overlapping rate of a risk zoning result and actual fire distribution is improved.

The invention discloses a resource scheduling system and method based on a smart power grid. The system comprises a power grid cloud edge collaborative data acquisition module, a double-layer time scale random scheduling modeling module, a random saddle point approximate optimization calculation module, a high-dimensional target Pareto scheduling analysis module, a resource scheduling instruction generation module and a scheduling effect feedback adjustment module. The method comprises the steps of collecting multi-dimensional data of a power grid through cloud edge cooperation, constructing a double-layer time scale random scheduling model, calculating a scheduling decision variable through a random saddle point approximate optimization algorithm, screening an optimal scheme through a high-dimensional target Pareto scheduling model, converting the optimal scheme into a scheduling instruction, and issuing and executing the scheduling instruction. And parameters of each module are adjusted according to actual operation data feedback. According to the method, scheduling cooperation of different time scales is realized, power grid scheduling economy, reliability and environmental protection are considered, resource scheduling precision and efficiency are improved, and a complex operation scene of a smart power grid is effectively adapted.

The invention relates to the technical field of intelligent power grid monitoring, in particular to a measuring and testing method for an intelligent low-voltage distribution box line, which comprises the following steps of: acquiring and decomposing an original signal of a reconstructed line to form a characteristic image; steady-state and outlier feature clusters are autonomously emerged through unsupervised clustering, and anomaly recognition without a preset threshold value is achieved. And parameterizing the steady-state features into a dynamic template for real-time comparison and marking of feature deviation events. For a deviation event, an original signal is deeply deconstructed to extract energy distribution and phase synchronization distortion characteristics, and the characteristics, a switching event and a load record are subjected to time sequence alignment and coupling analysis, so that the logic relevance of an abnormal source is locked. Based on the relevance, the sensing device is driven to adaptively adjust a sampling strategy, a new round of verification measurement is started, and a closed loop from sensing, diagnosis to optimization tracking is formed. According to the method, unknown abnormity can be adaptively identified, and automatic analysis of abnormity reasons and closed-loop optimization of a monitoring strategy are realized.

The invention provides an intelligent power grid multi-sensor fusion line loss analysis system and method, and relates to the technical field of intelligent power grids, and the system comprises a line loss analysis matrix drawing module which draws a line loss analysis matrix and sets a line loss deviation value; the dynamic analysis module is used for determining line loss abnormal offset, and when the line loss abnormal offset exceeds a normal line loss preset threshold range corresponding to the power transmission line, a dynamic analysis mechanism is triggered: differential data calibration is carried out based on a line loss analysis matrix and the line loss offset; the dynamic distribution module is used for dynamically distributing line loss regulation gain factors of each monitoring section; and the line loss calibration module is used for performing line loss precision enhancement control on the intelligent power grid through each edge calibration execution unit deployed in each monitoring section. According to the method and the device, the technical problem of inaccurate line loss analysis caused by difficulty in accurately positioning line loss abnormal sections and causes in the prior art is solved, and the line loss problem of the power grid is accurately identified through multi-sensor monitoring and data fusion.

The invention relates to a power distribution network disturbance source identification method based on multi-modal feature fusion, and belongs to the technical field of refined disturbance monitoring and diagnosis of a smart power grid. The method comprises the steps of performing time-frequency transformation on extracted disturbance type current traveling wave data, generating a traveling wave panoramic oscillogram and a two-dimensional time-frequency diagram, fusing the traveling wave panoramic oscillogram and the two-dimensional time-frequency diagram into a three-channel time-frequency image, and extracting an image feature vector; carrying out Prony modal parameter fitting on the disturbance type current traveling wave data, extracting a modal parameter feature vector and projecting the modal parameter feature vector to a high-dimensional feature space; performing Clark transformation on the disturbance type current traveling wave data, calculating a zero-mode energy proportion feature and projecting the zero-mode energy proportion feature to a high-dimensional feature space; fusing the image feature vector, the projected physical feature vector and the projected modulus energy feature vector; and inputting the fused feature vector into a classifier, and outputting a category identification result of the power distribution network disturbance source. The technical problems that in the prior art, feature representation is single, physical interpretability is weak, and stable electric power fingerprints are difficult to form are solved.

The invention relates to the technical field of smart power grids, and discloses a wind-solar-storage coordinated power distribution network partition dynamic voltage control method and system, and the method achieves the precise self-adaptive division of control sub-regions through the dynamic clustering partition based on real-time voltage sensitivity. A double-layer cooperative control framework of'centralized optimization-decentralized execution 'is constructed, and distributed rolling optimization is performed by adopting an alternating direction multiplier method, so that the unification of global coordination and quick local response is realized; a multi-target energy storage optimization configuration model considering wind and light uncertainty is established and is deeply coordinated with an operation control strategy. Therefore, the effects of improving the voltage control precision, the response speed and the robustness of the high-proportion new energy power distribution network are achieved, and meanwhile, the system economy, the power supply reliability and the comprehensive utilization efficiency of wind, light and storage resources are remarkably improved.

A power load prediction method, system and device based on GHOA-CNN-iTransform-LSTM, and the method comprises the steps: firstly obtaining the multi-source data of a power load and analyzing the causal relationship, then constructing an analysis model based on scene injection, constructing an improved hiking optimization algorithm GHOA based on a hierarchical strategy evolution framework, optimizing the hyper-parameters of the analysis model, and finally obtaining the multi-source data of the power load. And finally, after the analysis model is trained, power load prediction of the smart power grid is realized. By acquiring the multi-source data, analyzing the causal relationship and adaptively transforming the kernel of the analysis model, the analysis model can integrate the time and the causal logic for dynamic allocation, accurate perception of external events is realized, a stable deduction result is obtained from complex data, and the accuracy of the deduction result is improved. According to the method, the self-adaptive optimization of the optimal parameters is realized through the hierarchical strategy evolution framework, the search strategy is ensured to dynamically adapt to the high dimension and complexity of the parameter space, and the precision and adaptability of power load prediction are ensured.

The invention relates to an intelligent power grid and artificial intelligence, in particular to a non-intrusive load detection method and system based on multi-state power consumption and machine learning, and the method comprises the steps: obtaining electric appliance level power consumption data; preprocessing the data; feature extraction and fusion; and classifying load anomalies. According to the scheme, the high generalization ability can be kept while the electricity stealing detection accuracy is improved, the integrated power consumption sequence and the electric appliance power consumption matrix are received at the same time to serve as input, the household overall electricity consumption information and the single equipment level characteristics are organically fused, and therefore more comprehensive modeling and analysis of the electricity consumption behavior of a user are achieved, and the user experience is improved. And the capability of identifying abnormal behaviors such as electricity stealing is enhanced.

The invention discloses an electric energy meter metering misalignment judgment method based on multi-source data and consistency check, and belongs to the technical field of intelligent power grid metering monitoring. The method comprises the steps of collecting electric energy meter daily electric quantity, transformer area total electric quantity and user load characteristic data; identifying and correcting data exception by adopting a sliding window and a self-adaptive quartile distance method; constructing a multivariate linear fitting model of the total electric quantity of the transformer area and the electric quantity of each sub-meter, and calculating the average residual contribution degree of each electric energy meter through least square estimation and residual analysis; and calculating a metering deviation index in combination with electric quantity volatility, judging a suspected misalignment electric energy meter based on a confidence interval, and controlling a list length and effectiveness according to an accumulated contribution ratio threshold. Remote, real-time and automatic monitoring of mass electric energy meters is realized, the defects of high cost, long period and high false alarm rate of a threshold value method in traditional manual checking are overcome, and the accuracy, robustness and interpretability of metering misalignment judgment are remarkably improved through multi-source data fusion and statistical checking.

The invention belongs to the technical field of intelligent power grids, and particularly relates to a power distribution network voltage model prediction control method and device, equipment and a medium. The control method comprises the following steps: acquiring a real-time power grid state and a prediction state in an observation scale which takes a current moment as a starting point and has a length of d; the voltage control device is input to a pre-trained SAC-MPC intelligent agent, a control action within an action scale with the length of 1 is output, and the action is a reactive power output instruction assigned to the voltage control device; and issuing and executing the control action of the next time step. According to the training method, a high-fidelity power distribution network operation environment is constructed, and based on an SAC algorithm framework, an intelligent agent is trained through environment interaction, experience playback and cooperative update of an Actor strategy network and Critic evaluation network parameters. Through combination of prospective prediction and real-time decision, the hysteresis problem of a traditional control method is solved, and rapid and smooth control of the voltage is realized.

The invention discloses a tunnel reluctance current sensor self-correction measurement method, system and device based on voltage feedback and a medium, and belongs to the technical field of current measurement and sensor anti-interference, and the method comprises the steps: extracting fundamental wave complex components at the fundamental wave frequency of a power supply voltage and an initial output voltage; calculating a filter coefficient according to the fundamental wave complex component and performing phase correction on the output voltage to obtain a corrected output voltage sequence aligned with the phase of the power supply voltage signal; calculating a voltage ratio signal according to the corrected output voltage and the power supply voltage and determining a ratio signal residual error; final current estimation is obtained according to the voltage ratio signal and the ratio signal residual error in combination with the ratio signal; according to the invention, a double-closed-loop compensation structure is adopted, so that channel mismatching and non-linear interference are effectively suppressed; the digital implementation mode enables the system to have good reconfigurability and environmental adaptability, and the system is suitable for application scenes such as intelligent power grids, distributed power monitoring and industrial online detection.

The invention discloses a reactive compensation equipment fault automatic early warning system based on an intelligent algorithm, which belongs to the technical field of intelligent power grids and comprises a fault data acquisition module, a feature processing module, a fault diagnosis and evaluation module and a visualization module. Matlab software, Simulink software, a configurable point fast Fourier transform algorithm, a fluorescence imaging technology, a capacitive detection technology and a related intelligent algorithm are combined, reactive power compensation equipment fault analysis is carried out from three angles of a lightning arrester, a capacitor and a reactor, and the fault of the reactive power compensation equipment is analyzed in a chart form. And the visual output of the output result of the reactive power compensation equipment fault diagnosis model is realized. According to the invention, intelligent and precise diagnosis and visual early warning of reactive power compensation equipment faults are realized by comprehensively collecting multi-dimensional data of the lightning arrester, the capacitor, the reactor and overall compensation.

The invention relates to the technical field of intelligent power grids, in particular to a charging pile off-peak parameter adjustment control system and method, and the system comprises a charging demand analysis module, a load fluctuation evaluation module, a power demand distribution module, a parameter adjustment control module and a dynamic adjustment and optimization module. According to the invention, by analyzing the charging demand and the power grid load information, generating the correlation model of the charging task and the power grid load, optimizing the distribution of the charging task and accurately evaluating the influence of load fluctuation, a basis is provided for the distribution of the power demand, the priority execution of the charging task in the load valley period is ensured, and the impact of the power grid load is avoided; the undistributed power demand is compared with the residual bearing capacity of the power grid, the matching sequence of the charging task and the power grid nodes is dynamically adjusted, the flexibility and accuracy of power grid load adjustment are improved, the scheme abandons the practice of depending on a preset time period or a simple algorithm, and the power grid demand is accurately responded based on real-time load change. And optimal balance of the power grid load is realized.

The invention relates to the technical field of intelligent power grid abnormity diagnosis, in particular to an intelligent electric energy meter operation data abnormity diagnosis method and system. The method comprises the steps of establishing a sliding window, collecting magnetic induction intensity and load current data, maintaining references of the magnetic induction intensity and the load current data according to historical data, calculating the change direction and intensity of a sampling point relative to the references, screening data with enhanced magnetic induction intensity and reduced load current, and carrying out weighted covariance calculation by utilizing an effective mask. Constructing a negative correlation response coupling index; constructing an abnormal definite diagnosis confidence reasoning model; calculating a causal confidence factor based on the coupling index; calculating an aging confidence factor based on the duration of an abnormal state; according to the scheme, industrial interference and electricity stealing attacks can be accurately distinguished, hidden attacks are captured, the false alarm rate is reduced, and diagnosis blind areas are eliminated.

The invention discloses a block chain enabling smart power grid transaction system based on a game theory, and relates to the technical field of regional chains, and the system comprises a strategy management module which is used for making a buying and selling strategy based on the optimal utility through the game theory according to the electric meter storage space of a user, power utilization historical information and transaction record information, the electric equipment of the whole network is dispatched through the block chain; the transaction contract module is used for creating and updating a transaction contract based on the operation strategy formulated by the strategy management module; and the user management module is used for managing the information of the power users and the historical electricity utilization records. According to the invention, an efficient, fair and transparent power transaction mode is constructed by using the security of the block chain technology and the real-time response characteristic of the smart power grid, and the method aims at fully utilizing the distributed power storage units to achieve power utilization peak regulation so as to reduce the energy loss.

The invention relates to the technical field of intelligent power grid relay protection, in particular to an electric power protection constant value multi-target collaborative optimization method based on a hierarchical optimization strategy, which comprises the following steps of: performing traceability acquisition on parameters of an electrical system of a power plant by utilizing a parameter traceability method to obtain a dynamic parameter set; performing association mapping on the topological information and the dynamic parameter set of the power plant electrical system to obtain a digital twinborn model; performing mixed semantic analysis on the protection setting value guide rule to obtain a rule constraint set; performing hierarchical optimization on the digital twinborn model based on the rule constraint set to obtain a local constant value solution set; performing consistency coordination on the local constant value solution set to obtain a setting value; adjusting the value of a setting value of a relay protection module of the digital twin model to the value of the setting value to obtain an electrical system model, and performing risk assessment on the electrical system model to obtain an assessment result; generating a constant value calculation book based on the evaluation result; and the accuracy and efficiency of setting calculation are obviously improved.

The invention relates to the technical field of circuit breakers, and discloses a switching-on and switching-off structure of a reclosing circuit breaker, which comprises a shell, a static contact, a moving contact, a switching-on and switching-off knife switch and a switching-on assembly, and the static contact and the moving contact are arranged in the shell. The closing assembly comprises a driving motor and a transmission part arranged between the opening and closing knife switch and an output shaft of the driving motor, the driving motor can drive the transmission part to act, and the transmission part can drive the opening and closing knife switch to act. When an instantaneous fault of a circuit where the circuit breaker is located disappears, the driving motor drives the transmission part to act and further drives the opening and closing knife switch to act, direct driving of a power source is achieved, the mechanical structure is simplified, the fault probability caused by complex mechanical interlocking and lock catch abrasion and jamming is reduced, the mechanical response time is shortened, and the service life of the circuit breaker is prolonged. And the execution speed of the automatic reclosing is improved, so that the intelligent power grid can recover power supply more quickly.

The invention discloses a schedulable resource clustering method based on non-intrusive load identification and related equipment, relates to the technical field of smart power grids, and aims to solve the problem that flexible loads on a user side are dispersed and changeable and are difficult to be effectively utilized by a virtual power plant. The method comprises the following steps: identifying a load start-stop event of a user side through a non-intrusive load monitoring algorithm and extracting electrical characteristics of the load start-stop event; matching the electrical features with a preset load feature library to calculate a confidence coefficient, and performing double screening in combination with a feature deviation value of a continuous event so as to accurately identify a target load which operates stably; thirdly, in combination with scheduling time constraints set by a user, constructing schedulability vectors for each target load; and finally, performing multi-dimensional feature clustering and optimization on each vector at the cloud to form a virtual machine set meeting the requirements of power and response time. According to the method and the device, massive dispersed flexible loads can be accurately quantified and aggregated into large-scale reliable resources in a low-cost mode, and the aggregation efficiency and the utilization rate of the user-side flexible loads are improved.

The invention provides a distributed photovoltaic power generation capacity prediction method and system based on XGBoost, and relates to the technical field of photovoltaic power generation. Historical power generation capacity data of a distributed photovoltaic power station and hour-level solar irradiance data of a corresponding geographic position are collected, periodic mapping of a [0, 2pi] interval is carried out on a timestamp, sine and cosine characteristics are calculated, and the power generation capacity of the distributed photovoltaic power station is predicted. And taking the processed time period characteristics and solar irradiance data as input, and training an XGBoost regression model to realize generating capacity prediction. The method does not need an extra abnormal point screening step, naturally has robustness by means of a weighted tree integration mechanism of XGBoost, is light in model structure and high in training and prediction speed, remarkably reduces computing resource consumption while ensuring more than 95% of prediction accuracy, is suitable for a multi-site distributed deployment scene, and has a wide application prospect. And intelligent power grid dispatching and distributed energy management can be effectively supported.

The invention discloses a distributed energy cooperative control method and device for a photovoltaic power plant, and relates to the technical field of intelligent power grid control. The distributed energy cooperative control method and device for the photovoltaic power plant comprises the following steps: S1, collecting working data of an inverter, and preprocessing the working data of the inverter to obtain the preprocessed working data of the inverter; s2, constructing a to-be-classified inverter set, extracting a reference sample, evaluating a network exit risk, and outputting a network exit state label of the to-be-classified inverter; s3, identifying a power intervention candidate region, extracting non-off-grid inverters to construct a power compensation resource set, screening out a power regulation target, and evaluating the regulation priority of the power regulation target; and S4, calculating a power adjustment step length of the power adjustment target, performing power adjustment, and constructing a feeder adjustment database after adjustment to realize closed-loop adaptive optimization of power control. The problem that the voltage drop abnormity at the tail end of the feeder line is not identified, so that the grid-off fault of the inverter is misjudged is solved.