12 results about "Power sector" patented technology

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 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 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.

The present application relates to the technical field of electric power, and discloses a kind of resident short-term electric power load automation prediction method, comprising the following steps: S1: model establishment: establish resident short-term electric power load automation prediction model;S2: regional division: the geographical position of each resident home in a large area is divided in space using K-means algorithm, and is divided into several characteristic related regions;S3: data collection: collect the total power consumption and temperature data of S2 region in the past two years;S4: data division: the data collected and counted in S3 is processed and divided by sliding window method;S5: model training: the data divided in S4 is input into the model established in S1 for data training;S6: result prediction: the future day or week dimension electric power load size of local is automatically predicted by the trained network;The present application can reduce the workload of personnel, and can make reasonable electricity price for the power department, to provide a guidance scheme for ensuring the normal work of power plant.

The invention relates to the technical field of artificial intelligence, and discloses a power field-oriented RAG and preference alignment collaborative optimization method and system. The method at least comprises the following steps: carrying out text slicing on a power business decision knowledge base, and carrying out vectorization representation and retrieval enhancement generation on each obtained text block to obtain a power business adaptive text; generating a plurality of power business decision-making problems and expert decision-making texts and common decision-making texts corresponding to each power business decision-making problem based on the power business adaptive text in combination with a preset first large language model and retrieval enhancement; and based on the preference data set, performing fine tuning training on a pre-trained second large language model by adopting a direct preference optimization and probability ratio preference optimization weighted fusion mode to obtain a target large language model. According to the method, a reliable intelligent modeling tool is provided for complex decision making of a power system, and a reusable optimization normal form is also provided for modeling of reinforcement learning in the professional field.

The utility model relates to the technical field of power distribution signal detection of an electric power department, in particular to a universal signal converter capable of setting various electric quantity parameter detection, which comprises a shell formed by splicing a front panel and a rear cover shell, an input wiring terminal strip, an eight-bit nixie tube, a key module and an output wiring terminal strip are sequentially embedded in the front panel from top to bottom, an upper layer circuit board and a lower layer circuit board are arranged in the rear cover shell, and the lower layer circuit board is electrically connected with the output wiring terminal strip. The upper layer circuit board is electrically connected with the lower layer circuit board through a first plug-in flat cable, the eight-bit nixie tube and the key module are electrically connected with the lower layer circuit board through a second plug-in flat cable, and the lower layer circuit board is provided with a control circuit used for adapting to multi-electric-quantity parameter detection. According to the utility model, the control circuit with the microprocessor as the core is adopted, and test modes and output modes of different parameters can be selected through operation setting, so that convenience is provided for general tests of various electric quantities.

The utility model provides an embedded 5G edge computing controller, which comprises a central processing unit CPU, a 5G module, an ADC module, a DAC module, a WIFI module and a DDR4 memory, and is characterized in that the central processing unit CPU is connected with the 5G module through a miniPCIE interface, the central processing unit CPU is connected with the ADC module and the DAC module through SPI interfaces, the central processing unit CPU is connected with the WIFI module through an SDIO interface, and the central processing unit CPU is connected with the DDR4 memory through a DDR interface. A core chip and an operating system of the equipment are all localized, domestic replacement and autonomous controllability are really achieved, meanwhile, the safety of data transmission is considered, the bandwidth is improved, delay is reduced, multiple interfaces are expanded, convenient secondary development is provided, and the requirements of multiple aspects such as data collection, data calculation and data secure transmission in the power field can be met.

The invention is suitable for the technical field of information extraction, and provides an intelligent enterprise production and operation information extraction method and system based on cloud computing, and the method comprises the following steps: uploading a production and operation knowledge graph and a data source directory, each part of source data in the data source directory corresponding to a data label and a timestamp; association between the source data and nodes in the production and operation knowledge graph is established through semantic analysis, so that each piece of source data corresponds to a node number; receiving keyword information, inputting the keyword information into a pre-trained power field large model, and processing to determine a structured query blueprint; matching the query blueprint with a production and operation knowledge graph, determining a matched node, and calling source data corresponding to the node; and carrying out fusion analysis and information extraction on all the called source data based on the business logic relationship in the production and operation knowledge graph. By using the method, key information can be more accurately understood and extracted, and the quality and effect of data processing are improved.

This invention discloses a method and apparatus for monitoring, analyzing, and modeling carbon emissions in the energy and power sector, specifically relating to the field of carbon emissions in the power industry. It addresses the problem that existing carbon emission analyses typically focus on specific regions, resulting in lengthy analyses and an inability to directly predict overall carbon emission trends. The method involves dividing the carbon emission regulatory area into several smaller regulatory regions, calculating the carbon emission intensity of each region, determining whether the intensity meets standards, and marking and issuing warnings for regions that do not meet the standards. This invention calculates the carbon emission intensity of each region, filters out regions that do not meet the standards, performs cluster analysis on different regions to filter out regions outside the standard range and issue alarms, and finally combines the status of all regions to predict and evaluate the overall region, facilitating the formulation of relevant optimization policies.

This disclosure relates to the power sector and discloses an adaptive grid-connected control method, system, device, and medium for adapting to phase angle abrupt changes. The method includes: establishing a full-state oscillator model to generate the internal potential of the photovoltaic-storage grid-connected power source; establishing a phase angle adaptive model to correct the internal potential of the photovoltaic-storage grid-connected power source; and establishing a current inner-loop control model to control the stable operation of the photovoltaic-storage grid-connected power source based on the corrected internal potential. This disclosure enables photovoltaic energy storage systems to provide stable synchronous grid-connected characteristics under large phase angle abrupt changes, and allows microgrids containing a very high proportion of new energy sources to achieve flexible and reliable grid-connected / off-grid stable operation.

This invention discloses a large-model-driven multi-objective photovoltaic-storage distribution network control method under extreme weather conditions, belonging to the field of distribution network control technology. The method includes: collecting real-time electrical data and extreme weather data from the distribution network; identifying topology change events and generating structured natural language scene descriptions; generating a dynamic reward function with four objectives—voltage stability, frequency recovery, etc.—adapted to the scenario using a lightweight large-language model fine-tuned with power sector corpora; extracting global high-dimensional features using a topology and feature dual-attention graph convolutional network; using a vector concatenated from features and reward weights as state input, generating multi-device collaborative control instructions through a near-end policy optimization algorithm, and outputting the instructions after verification. This invention achieves dynamic perception of the distribution network topology, dynamic adaptation of control objectives, and collaborative optimization control of multiple devices under extreme weather conditions, comprehensively improving the operational resilience and renewable energy utilization efficiency of high-proportion renewable energy distribution networks under extreme weather conditions.