46 results about "Power sector" patented technology

The invention relates to the technical field of electric power, and discloses a novel electric power system load prediction method, which comprises the following steps of: acquiring electric power and corresponding comprehensive energy system data in an area on site, performing feature matching classification, determining prediction indexes, expanding a prediction range, establishing a secondary prediction system, and performing GM (1, 2, 3, 4, 5, 6, 7, 8, 8, 9, 10) on the secondary prediction indexes, the method comprises: 1) performing grey prediction to obtain a predicted value sequence, and generating a grey prediction model; performing grey correlation degree analysis on the second-level prediction index and the first-level prediction index; constructing a Bayesian network structure; constructing a father node; sequentially setting the value domains of the father node and the child node; determining a probability value and probability distribution; and comparing a prediction result with an actual result for verification. According to the method, all factors which play a role in the future are included in the prediction model, the influence weight of each prediction index is accurately analyzed, and assistance is provided for future work key points of employees of electric power departments and related industries.

The invention discloses a source network load operation scene generation method, system and device under ice disaster disturbance based on transfer learning and a storage medium, and relates to the technical field of power system operation and analysis, and the method comprises the steps: firstly constructing a simulation sample library based on a power grid structure, a fault type and an icing condition, and then integrating and standardizing source domain samples, dividing risk levels, and constructing and pre-training a least square loss function condition generative adversarial network model; a final standardized target domain sample set is generated, a target domain ice disaster scene generator is obtained through transfer learning and model fine tuning, and then an ice disaster disturbance operation scene is generated; the ice disaster disturbance operation scene can be accurately generated, an electric power department can be helped to master risks in advance, equipment maintenance, resource allocation and emergency preparation can be made accordingly, the influence of ice disasters on an electric power system is reduced, power supply stability is guaranteed, power grid planning and transformation can be guided, and the overall disaster resistance and market risk management capacity can be improved.

The invention belongs to the field of path planning, and discloses a mobile energy storage vehicle path planning method and system of an improved ant colony algorithm based on positive and negative excitation, and the method comprises the steps: taking the information of a regional road traffic network and a power distribution network as the input, and building a basic two-dimensional model in combination with the road trafficability affected by extreme weather and the fault state of the power distribution network; and iterating an optimal traveling path of the mobile energy storage vehicle by using an ant colony algorithm based on the established basic two-dimensional model so as to meet the power distribution demand, including forming negative feedback based on the current road trafficability so as to dynamically adjust the pheromone concentration of each path in the ant colony algorithm. According to the method, road information of a traffic department region, road accompanying conditions in extreme weather, extreme weather forecast information of a meteorological department region, power distribution network information of an electric power department region and power distribution network fault conditions in extreme weather are combined, strong correlation factors of regional road congestion in an extreme weather environment are fully considered, and the method has reasonability; and the method is more practical and is higher in applicability.

The invention discloses a carbon emission prediction and novel power system planning method and system in the urban power field. The method comprises the following steps: calculating the energy demand quantity of each department according to the urban total production value GDP, population, industrial structure and energy consumption characteristic data; calculating the total carbon emission amount of the electric power department based on the energy demand in combination with the carbon emission factor; on the basis of the total carbon emission amount of an electric power department, urban energy endowment, emission reduction tasks, emission reduction policies and power generation technology improvement are considered, and on the basis of economy, population and electricity consumption parameters of an electric power demand end, various development situations of low carbon, zero carbon and negative carbon of an electric power system are designed; predicting carbon emission and carbon emission reduction corresponding to the demand end in each scene, and obtaining an emission reduction path from the demand end; and establishing a power system multi-scene optimization planning model by taking the lowest net present value of the total cost of the system as an objective function and taking urban power related constraints as constraint conditions, and calculating a power generation installed capacity development path meeting the system cost and the related constraints.

The invention relates to a method and a system for detecting abnormal electricity consumption of an electric energy meter, and relates to the technical field of electric power detection. According to the method for detecting abnormal power consumption of the electric energy meter, the data of the electric energy meter is collected and analyzed, so that the accuracy of wiring of the electric energy meter can be preliminarily judged through an instrument, the electric quantity needing to be compensated during a fault period is automatically calculated, the manual calculation processing time is shortened, and the field operation and maintenance working efficiency can be greatly improved; the electric quantity calculation method can be immediately corrected by analyzing acquired data of the electric energy meter, finding a wrong wiring condition, so that the device can acquire a real-time power consumption condition and automatically calculate the electric quantity needing to be compensated in a wrong wiring state and in abnormal operation, the operation and maintenance work difficulty of an electric power department is reduced, and the working efficiency is improved. And the efficiency of field operation and the timeliness of electric quantity compensation are improved.

The invention provides a method and system for detecting abnormity of a load switch of a low-voltage meter box, and the method comprises the steps: obtaining the target parameter information of a target low-voltage meter box, and screening the meter information in the target parameter information; the number of meters in the screened target parameter information is determined, if the number of meters in the screened target parameter information is larger than a preset first number threshold value, phase-by-phase checking is conducted on phase lines of the meters according to a preset checking standard, and a corresponding checking result is obtained; and determining whether the load switch corresponding to the meter is abnormal or not according to the troubleshooting result, and if so, outputting a corresponding alarm signal. The low-voltage load switch with poor contact can be found in time, loss of national assets caused by electric charge loss is avoided, electric appliance fire accidents are avoided, manpower and material resources can be saved, economic losses of an electric power department are reduced, and electric fire safety accidents are avoided.

The invention relates to the technical field of carbon tax analysis, and discloses a CGE model-based carbon tax income return method, system and device and a medium, and the method comprises the steps: constructing a dynamic CGE model which comprises four economic subjects, and dividing an economic population composed of the four economic subjects into 27 production departments; dividing each production department into an electric power department and a non-electric power department based on the production characteristics and the energy use types of each production department; based on a six-layer nested production function principle, respectively constructing production functions of a non-electric power department and an electric power department; performing parameter calibration on the dynamic CGE model in combination with related parameters to obtain a calibrated dynamic CGE model; and simulating the set reference scene and the main scene to obtain the influence of the electric power department and the non-electric power department under different carbon tax policy situations. According to the method, the dynamic CGE model is constructed to simulate the influence of a non-electric power department and an electric power department under different carbon tax policy situations, so that the influence of different carbon tax policies on an economic subject is analyzed.

The invention discloses a power electronic load-containing load equivalence and parameter identification method, which comprises the following steps of: preprocessing original power load data, and extracting data required by subsequent parameter identification; determining a load model structure, and performing aggregation equivalence on the power distribution network, the static load, the dynamic load and the power electronic load according to a principle that system response before and after aggregation remains unchanged; the method comprises the following steps: firstly, constructing a load model, then determining parameters, needing to be identified, of each type of load model, distinguishing dominant parameters and non-dominant parameters by adopting trajectory sensitivity, setting values of the non-dominant parameters as typical values, then identifying the dominant parameters through an improved quantum particle swarm algorithm, determining the values of the dominant parameters, and finally, performing accuracy evaluation on the established load model. According to the invention, a more accurate load model can be established for a modern power system containing a power electronic load, the simulation precision of the power system is improved, and the analysis and control of a power department on the power system are facilitated.

This invention is entitled "A High-Energy-Density Ironless Permanent Magnet Motor with Automatically Increased Power, Torque, and Power Generation and Charging." It belongs to the field of power motor technology. Its main features are: The stator's ironless windings are distributed along the circumference of an ironless, polymer-made precision-cast stator frame, which is directly and spaced apart and sheathed onto a stator-type housing or stator-type structural housing; the rotor's ironless permanent magnets are distributed along the circumference of an ironless, polymer-made precision-cast rotor frame, which is directly hingedly fixed to the main shaft; and the housing comprises two stator-type housings or rotor-type housings on either side and a rotor-type structure or stator-type structural housing in the middle. It boasts a high power per unit weight exceeding 7 kW / kg, a torque density of 25 Nm / kg, and a high magnetic field energy density of 500 to 25,000 rpm. This motor features a simple structure, high power density, high torque density, high magnetic field energy density, low cost, and excellent performance. It can be widely used in the transportation power sector as an ironless, coreless permanent magnet motor with automatically increased power, torque, and power generation and charging, and high energy density.

The invention is suitable for the technical field of electric energy metering, and relates to an electric energy metering method and device of an electric energy meter. Corresponding fundamental wave voltage current components, harmonic wave voltage current components, corresponding fundamental wave phase angles and harmonic wave phase angles are extracted, and based on the data, fundamental wave positive sequence active power, reactive power, non-fundamental wave equivalent apparent power, voltage distortion power, current distortion power, harmonic wave apparent power, unbalanced apparent power and the like are obtained through calculation; various electric parameters of the electric energy meter are metered so as to guide an electric power department to charge, make economic decisions, measure main harmonic pollution sources and the like, and the quality of electric power service is greatly improved.

This application discloses a reliable AI scheduling method, system, and computer equipment for microgrids. It includes: conditional independence testing of multi-source data; constructing a candidate causal graph among variables, constrained by prior knowledge in the power sector; calculating the differences in causal effects caused by fluctuations in the current scheduling strategy; performing counterfactual reasoning verification based on different differentiated scheduling strategies; and scoring the current scheduling strategy on causal interpretability based on causal effect differences, counterfactual verification results, and link integrity, followed by AI scheduling. This application reveals the causal interaction mechanism between variables, and the counterfactual reasoning that changes in variables lead to changes in scheduling results, improving the interpretability of the scheduling strategy. It can trace the causal driving factors of each scheduling instruction, significantly reducing the rate of human intervention. Prior knowledge in the power sector ensures safe and compliant scheduling, making the results more reliable. It solves the problem of dependence on human intervention in the application of AI scheduling in microgrids.

The application discloses an evaluation device and method for evaluating current harmonic feed-in content of a power grid of a charging station, the evaluation device comprises a central controller CCU, a grid-side collector PQA, charging pile-side collectors Ax and charging piles Changx, the central controller CCU is the core of the evaluation device, the grid-side current collector PQA is installed at the output end of a transformer, and the charging pile-side collectors Ax are installed at the front end of each charging pile; the evaluation method establishes a functional relationship between each harmonic and the output power of the charging pile, evaluates the content of the charging station harmonic feed-in side of the distribution network, solves the quantitative evaluation problem of the current harmonic feed-in side of the power grid generated when the electric vehicle charging station operates, proposes an evaluation device and method for the current harmonic feed-in side of the power grid of the charging station, effectively evaluates the content of the charging station harmonic feed-in side of the distribution network, provides the user with a suggestion on whether it is necessary to install a filtering device, and guarantees the power supply quality of the power department.

The present invention relates to the technical field of lightning protection for power systems. Disclosed are a lightning activity analysis method and system for power transmission lines, and a device and a storage medium. The method comprises: acquiring characteristic parameters of towers of a power transmission line, and discretizing the characteristic parameters to obtain a tower attribute table; performing data mining on data items in the tower attribute table on the basis of an FP-Growth algorithm, so as to obtain frequent 1-itemsets and a frequent pattern tree, establishing a hash linked list on the basis of the frequent 1-itemsets and the frequent pattern tree, and performing association rule mining on the basis of the hash linked list, so as to obtain frequent multi-itemsets; selecting, from the frequent multi-itemsets, association rules using lightning trips as rule consequents, and analyzing the association rules to obtain a lightning activity analysis result; and on the basis of the lightning activity analysis result, establishing a lightning protection strategy for the power transmission line. The present invention improves the applicability of correlations from data analysis and the efficiency of pattern mining, thereby providing data support for lightning protection work on power transmission lines in electric power departments.

The invention relates to the related technical field of carbon transactions, in particular to a modeling method for introducing CCER transactions and a cancellation mechanism into a national carbon market, which comprises the following steps: S1, constructing a CGE model, S2, establishing a data basis of the CGE model, S3, constructing the CCER transactions and the cancellation mechanism, and S4, carrying out analogue simulation on a CCER scene. By constructing a modeling framework formed by CCER supply, offset and price, the traditional limitation is broken through, and a carbon transaction mechanism modeling method is perfected; the accuracy and the reliability of the model are improved by finely dividing electric power departments and reasonably distributing the cost; by designing various policy scenario simulation, the policy influence is deeply analyzed, and scientific basis and comprehensive support are provided for policy making. The modeling method is wide in application prospect, facilitates optimization of carbon market policies and promotes green, efficient and intelligent development of the energy internet.

The application discloses a kind of wind turbine power characteristics evaluation method based on cloud model and optimal combination weighting based on survival analysis intelligent electric energy meter reliability evaluation method, step S101, electric energy meter original data acquisition and category characteristic numerical processing;Step S102, category characteristics are reduced dimension processing;Step S103, evaluate batch intelligent electric energy meter reliability;Step S104, evaluate the reliability of individual intelligent electric energy meter;The method can realize the reliability analysis of batch intelligent electric energy meter, and the survival rate of each individual intelligent electric energy meter is evaluated, which helps electric power department to find the abnormal condition of intelligent electric energy meter in time, provides theoretical support for the transformation of intelligent electric energy meter from "expiration rotation" to "state replacement", and improves the lean operation and maintenance management level of intelligent electric energy meter.

The invention relates to the technical field of power system online monitoring, and particularly discloses an icing galloping monitoring device evaluation method based on fuzzy comprehensive evaluation. In order to solve the problems that an existing evaluation method depends on experience judgment, standards are not uniform, evaluation dimensions are single, and a scientific basis cannot be provided for device type selection and arrangement, the method comprises the steps that a three-level evaluation index system of a tree structure is constructed, and weights of indexes of all levels are determined in a grading mode; and then dynamically adjusting the weight by adopting multiple strategies according to the actual configuration condition of the device, and finally calculating a comprehensive evaluation value and grade by applying a multi-level fuzzy comprehensive evaluation method. According to the method, comprehensive and accurate quantitative evaluation of the icing galloping monitoring device from technical parameters to overall performance is realized, the accuracy and comparability of an evaluation result are remarkably improved, and a scientific and reliable decision basis is provided for an electric power department to perform device type selection, purchase and optimized layout.

The present invention discloses a method and electronic device for testing the heat dissipation capacity of a power transformer. The method relates to the power sector and includes obtaining a first surface temperature and a second surface temperature of the power transformer; determining a temperature factor and an overload factor of the power transformer based on the first and second surface temperatures and a preset duration; and testing the heat dissipation capacity of the power transformer based on the temperature factor, the overload factor, and the thermal conductivity parameter of a heat-radiating coating to obtain a test result. The present invention addresses the technical problem of low power system stability caused by poor power transformer stability.

The invention provides a self-adaptive personalized federated learning method for transient stability of a power system. The method comprises the following steps: generating power system simulation data by using PSASP power system simulation software; dividing the standardized data set; constructing a basic model LSTM based on the processed data; based on the basic model LSTM, adaptive personalized federal learning is carried out to obtain a personalized model after training is completed; and taking actual power system data as the input of the personalized model, and verifying the accuracy and practicability of the personalized model. According to the method, each client is allowed to train a personalized model matched with data distribution of the client according to the uniqueness of data of different power departments, and the prediction accuracy of the model on the transient stability of the local power grid is enhanced; through parallel model training on a plurality of clients, distributed computing resources are effectively utilized, and the overall training efficiency and the capability of processing a large-scale data set are improved.

The invention relates to the technical field of data processing, in particular to a CGE modeling method for analyzing and canceling electricity price subsidy, which comprises the following steps: S1, constructing a CGE model; s2, a data basis of the CGE model; s3, establishing an electricity price subsidy mechanism; s4, the analogue simulation of the electricity price subsidy scene is canceled; by constructing a CGE model subdivided by an electric power department, the economic influence of canceling electricity price subsidy is accurately simulated, and a scientific basis is provided for policy making.

The application discloses an electric energy meter and a meter terminal clock field detection method and system, relates to the technical field of timing and synchronization, and comprises a clock calibrator GPS-7A system which is constructed and intercepts high-voltage signals for overload protection during data acquisition; converts the optocoupler on-off signal output by the electric energy meter into an identifiable electrical signal, and acquires standard time by using a GPS & Beidou receiver; measures the daily timing error of the electric energy meter and the overtime, and forcibly synchronizes the electric energy meter with the local time for timing by using high-precision local time. The application guarantees the interests of the power department and the power consumer, acquires more accurate matching parameters by matching the crystal oscillator and the load capacitor through the measurement of the daily timing error, simultaneously accesses two-way electric energy meters to improve the test efficiency, more quickly screens qualified products, effectively prevents the problem that the user mistakenly connects the 220V power supply to the test port, fully protects the core circuit of the equipment, effectively reduces the equipment failure rate, and provides a good use experience for the user.

The invention provides a method and system for detecting abnormal contact of a metering device, and the method comprises the steps: extracting current and voltage data of the metering device in a preset time period; extracting data points in the current and voltage data according to a preset extraction standard, and determining whether a judgment condition is met or not according to the data of the extracted data points and the number of days where the data points are located; if yes, whether the voltage of the metering device in the preset time period meets a preset voltage state or not is determined; if the preset voltage state is met, judging that the metering device is in normal contact; and if the preset voltage state is not met and the switch is not the low-voltage load switch, judging that the metering device is in contact abnormally. According to the invention, timely contact of poor low voltage from hundreds of thousands of metering devices can be realized, real-time on-line monitoring of low voltage can be realized if the device is applied to a system, manpower and material resources can be saved, economic loss of an electric power department can be reduced, and occurrence of electric fire safety accidents can be avoided.

The present invention provides a method and system for power load forecasting, which relates to the fields of meteorology and power research, and includes the following steps: S1, obtaining load data and meteorological data within the past two years, and marking the data with date types; S2, constructing training data sets for different dates in a short period of time to carry out training, and obtaining prediction models for corresponding dates; S3, obtaining input data for short-term load forecasting; S4, inputting the data obtained in S3 into the corresponding prediction models to obtain short-term load forecasting results. The present invention uses power load data from the past two years and meteorological data from the corresponding time period to redefine the daily time range, distinguish between working days and non-working days, and adopts the LightGBM machine learning method to learn and train the changes in short-term power load, and obtain a 15-minute power load forecast for the next three days. The output power load forecast is more accurate and precise, providing strong support for the business decision-making of the power sector.

A concentrator box device used by the power department includes a concentrator box body, a solar panel, a battery, a text message module, and a relay; it also has a box door detection circuit and a timing circuit; the solar panel is installed on the outer upper end of the concentrator box body, and the box door detection circuit is equipped with a magnet and a reed switch, which are respectively installed at the rear end of the box door and the front end of the box body of the concentrator box body; the battery, the text message module, the box door detection circuit, the timing circuit, and the relay are installed in a component box and electrically connected. When someone opens the box door or stays in front of the box for too long (too long means that there may be a possibility that someone uses other tools to open the box door in front of the box door because there is no matching key), and there is a possibility of power theft, as well as when there is a power outage on site, the new device can immediately push a reminder text message to the remote relevant personnel through the text message module, and the relevant personnel can go to the site in time to deal with it after receiving the text message on their mobile phones, thereby playing the role of preventing power theft and providing reliable power supply.

The application provides a kind of multi-type hybrid charging station safe operation control method and system, belongs to charging station safety control technical field, including the following steps: install sensor in the area where charging pile, energy storage equipment and power distribution equipment are located, collect operating parameter data, data is transmitted to station central control system;Data is preprocessed and different dimension data is normalized, mark abnormal point when out of limit and record time, position and equipment information;Determine normal, potential failure or failure state of equipment;Risk is divided into low, medium and high three levels;Start warning when medium risk, risk is prompted through broadcast, SMS, monitoring pop-up window;When high risk, automatically cut off power supply of faulty equipment, and send alarm information containing location and fault type to fire department and power department.The multi-type hybrid charging station safe operation control method provided by the application can monitor all risks in real time, accurately warn and quickly dispose, and improve the safety and stability of charging station.

The invention discloses a steam turbine and an adjusting system network source coordination data information management system thereof, which comprises a test information module, a model and parameter information module, a modeling report information module and an information report generation module, wherein the test information module acquires test data information of a power generation enterprise in a turbine and its adjusting system network source coordination network-related test and filters the test data information; the model and parameter information module adopts a swarm intelligence algorithm to obtain important parameters of the identified steam turbine model, the adjustment system model and the execution mechanism model; the information report generation module obtains power generation enterprise storage information and fills a report template with the information; and the modeling report information module realizes management of parameter modeling reports of the steam turbine and the adjusting system thereof. According to the invention, the working efficiency of electric power departments and electric power workers is effectively improved, and the grid-related supervision and management support level of the grid-connected unit is improved.

The invention discloses an electric energy meter and metering terminal clock on-site detection method and system, and relates to the technical field of timing and synchronization, and the method comprises the steps: constructing a clock calibrator GPS-7A system, and intercepting a high-voltage signal for overload protection during data collection; an optocoupler on-off signal output by the electric energy meter is converted into a recognizable electric signal, and GPSamp is used; the Beidou receiver obtains standard time; the daily timing error of the electric energy meter and the timeout time are measured, and the high-precision local time is utilized to force the electric energy meter to synchronize with the local time for time calibration. According to the invention, benefits of an electric power department and electricity customers are ensured, a crystal oscillator and a load capacitor are matched through measurement of daily timing errors, and more accurate matching parameters are obtained; the two paths of electric energy meters are simultaneously connected, so that the test efficiency is improved, qualified products are screened more quickly, the problem that a user misconnects a 220V power supply to a test port is effectively prevented, a core circuit of equipment is fully protected, the failure rate of the equipment is practically and effectively reduced, and good use experience is provided for a user.

This invention relates to a method for extracting multimodal entity relationships in the power industry based on transfer learning, comprising the following steps: collecting and preprocessing power industry text and image data; constructing a cross-modal relationship feature extraction model to obtain high-level features r of multimodal data in the power industry. t High-level features of open-domain multimodal corpora s Constructing a power multimodal entity relationship extraction model based on transfer learning: This involves extracting high-level features r... s High-level features r corresponding to the power sector t Adaptation enables higher-level features r t With high-level features r s The high-level feature r with the smallest difference value is selected when the difference value is less than a preset threshold. t With high-level features r s The result is input to the next layer; the classification relationship output layer outputs the relationship recognition result. The beneficial effects of this invention are: it utilizes rich corpora from other fields to extract entity relationships from multimodal power data, thus alleviating the problem of limited labeled corpus resources in the power field.

The invention discloses a village power consumption prediction method based on a random forest algorithm, and belongs to the technical field of power consumption prediction. The random forest algorithm is trained through village power consumption influence factors and village power consumption results corresponding to the village power consumption influence factors; therefore, the village power consumption prediction model can be obtained, finally, the village power consumption prediction model is adopted to predict the village power consumption, the problem of inaccurate traditional prediction is avoided, the random forest algorithm is improved through the parameter optimization algorithm, the model with the best prediction effect can be determined, and the prediction accuracy is improved. The method further improves the prediction accuracy, is higher in prediction precision and stability, helps an electric power department to reasonably plan electric power resources, and improves the rural electric power supply level.

The present invention provides a critical load importance evaluation method for different power outage scenarios, including the following processes: establishing a critical load importance index evaluation model based on known power grid critical loads; calculating the influence weights of various evaluation indicators on load importance in the critical load importance evaluation index model through a hierarchical analysis method; calculating the quantitative indicators of economic losses and social impacts of critical loads based on the critical load importance index evaluation model; weighted summing the influence weights of various price indicators of critical loads on load importance, as well as the quantitative indicators of economic losses and social impacts, to obtain the importance of critical loads. The method provided by the present invention can form a refined and rapid evaluation of the importance of critical loads for different power outage scenarios, and provide a basis for emergency decision-making in the power sector.

The application discloses a power grid reconstruction site selection method, system, device and medium based on quantitative scoring, and the method comprises the following steps: acquiring feeder topology structure data, automatic power grid nodes and medium and low voltage user data of a region to be reconstructed in a distribution network; segmenting the feeder with the automatic power grid nodes as endpoints to obtain segmented regions, and then performing power supply safety analysis to obtain qualified sites; calculating the scrap net value and investment cost of power equipment in all qualified sites, and using z-score standardization sigmod conversion scoring to obtain scrap net value scoring and investment cost scoring; performing weighted summation based on the scrap net value scoring and the investment cost scoring, acquiring quantitative scoring of the qualified sites, sorting, and selecting the qualified site with the highest quantitative scoring as the best power grid reconstruction site. The application comprehensively considers the influencing factors when selecting the automatic site, simply and effectively realizes the automatic selection of the power grid reconstruction site, and improves the efficiency of power grid analysis and power grid planning of the power department.