225 results about "Energy balance" patented technology

The invention relates to the technical field of power system dispatching, and discloses a multi-agent reinforcement learning active power distribution network area coordination method and system, and the method comprises the steps: dividing a power distribution network into a plurality of areas, and each area is managed by an agent; collecting observation information; inputting the observation information into an upper reinforcement learning strategy network, and outputting control parameters; inputting the control parameters into a target function of the lower-layer local physical optimization model, and solving an output setting point of the equipment under the condition of meeting the safety operation constraint; constructing a De-POMDP problem, and obtaining a reward signal of each agent; a sequential updating mechanism is introduced, global network parameters are optimized, and corresponding decisions are obtained; and inputting the multi-agent decision into the global active power distribution network model to obtain the total operation cost, feeding back the total operation cost as an award to the reinforcement learning strategy network, updating global network parameters, and converging to obtain an optimal decision. According to the invention, regional wind-solar-storage multi-energy scheduling can be effectively optimized, and energy balance in the region is realized.

The invention discloses a new energy project intelligent planning method and system based on a large language model, and relates to the technical field of new energy planning, and the method comprises the steps: constructing a new energy project planning knowledge base; the new energy project planning knowledge base comprises basic data required by project planning and is used for providing data support for the optimization model; based on the training data in the new energy project planning knowledge base, performing field adaptability training on the large language model to obtain a special large language model in the new energy project planning field; and based on a project demand input by a user, analyzing project parameters through the special large language model, inputting an analysis result into the optimization model, and generating a planning scheme of a new energy project. According to the method, automatic conversion from a natural language demand to a professional planning scheme is realized, the accuracy of energy balance constraint is ensured through the topological structure diagram of the energy system, a flexible switching optimization target of economic benefits and environmental benefits is supported, and finally intelligent generation and evaluation of the planning scheme are realized.

The invention discloses an airport energy balance management method, system and device and a medium, and relates to the field of energy management. The method comprises the following steps: constructing an energy topological graph according to multi-source data; predicting energy load demands of the airport in different time periods according to the energy topological graph, determining the supply amount of renewable energy in different time periods according to the predicted illumination intensity and wind power, and determining a time-sharing energy supply and demand balance probability according to the energy load demands and the supply amount; determining a preliminary energy management plan according to the cost parameter, the time-sharing energy supply and demand balance probability and the equipment operation constraint, wherein the preliminary energy management plan comprises an energy storage system charging and discharging time sequence, a standby generator starting and stopping plan and a power grid electricity purchasing proportion; and executing the preliminary energy management plan through the digital twin of the airport to obtain first energy execution data, and adjusting the preliminary energy management plan through the difference between the first energy execution data and the second energy execution data at the current moment. By implementing the technical scheme provided by the invention, the energy cost is reduced.

The invention discloses a balance scheduling system for energy management and a balance scheduling method thereof, and relates to the technical field of energy management scheduling, and the balance scheduling system comprises an energy data acquisition module, an energy demand trend analysis module, an energy supply and demand dynamic prediction module, an energy balance scheduling decision module, a scheduling execution module and a performance monitoring module. After the energy supply and demand dynamic prediction module integrates real-time external factor data of the energy data acquisition module and a long-term historical rule of the energy demand trend analysis module, a reference prediction baseline based on a long-term trend is generated, and then a dynamic correction value is superposed to respond to short-term disturbance. And meanwhile, through an error traceability mechanism for separating a trend baseline from external correction, the module performance can be optimized in a targeted manner, if an error is derived from long-term trend deviation, a trend analysis model is calibrated, and if external data is lagged, priority adjustment of a data acquisition module is triggered, so that system self-diagnosis and prediction precision closed-loop improvement are realized.

The invention discloses an energy balance flexible guide mechanism hinge rigidity design method based on machine learning, and relates to the technical field of energy balance design. Constructing a mechanism parameter library by taking the hinge thickness as a structural parameter; converting the three-dimensional modeling software design scheme into a three-dimensional model library; performing three-dimensional grid division and finite element analysis to establish a grid library; constructing a three-dimensional simulation result database through finite element simulation results; establishing a mapping relation between the structure parameters and the performance characteristics by utilizing a machine learning method, and taking the mapping relation as a parameter library of machine learning; optimizing the design scheme through a machine learning method; and flexible guide mechanism scheme libraries under different index systems are constructed, and the flexible guide mechanism hinge meeting the requirements is obtained. An optimal flexible guide mechanism hinge design scheme is predicted through a machine learning method, mechanical properties of a hinge three-dimensional model are simulated in combination with finite element analysis, experiment and calculation requirements are reduced, and design efficiency and economic benefits are improved.

The invention relates to the technical field of metal smelting, in particular to a multi-gun top-blowing continuous blowing intelligent system and method. The system comprises a data acquisition module, an analysis processing module and a prediction feedback module. The method comprises the steps that the temperature, the liquid level and the material state in the furnace are monitored in real time and transmitted to the central data processing platform in real time for intelligent feedback control; dimensionality reduction is conducted on sensing data in the smelting process, the least principal components with the contribution rate exceeding 80% are extracted, and dimensionality reduction processing is achieved; carrying out thermal analysis by utilizing a material and energy balance equation, constructing a theoretical model of the blowing process, capturing a long-term dependency relationship, and predicting dynamic parameter change in the smelting process; and an interaction model of the intelligent agent and the smelting environment is constructed, a control strategy is updated in real time, and production parameters are adaptively adjusted. The problem of low-altitude pollution caused by converter blowing is solved, the defect of low efficiency of intermittent operation of current smelting is overcome, and a continuous and stable production process is realized.

The invention discloses a modern agricultural park comprehensive energy optimization scheduling method considering extreme temperature. According to the method, an extreme air temperature scene is determined based on a meteorological data set and an extreme air temperature event screening index, and energy supply and demand are predicted by using an energy supply-meteorological and agricultural load-meteorological coupling model. And constructing a weekly-ahead and day-ahead two-stage optimization scheduling model, and calculating an optimization scheduling result by using a commercial solver in combination with constraint conditions such as energy balance and the like. Meanwhile, adjustable resources such as a battery energy storage system and a demand response reservoir are considered, and the flexibility and stability of the system are improved. According to the method, the accuracy of source load prediction of the comprehensive energy system of the modern agricultural park at the extreme temperature is effectively improved, unbalanced cost deviation of different time scales is relieved, optimal scheduling of the comprehensive energy system of the agricultural park is achieved, stable supply of agricultural production energy is guaranteed, the energy utilization efficiency is improved, and the method has important application value.

The invention relates to a hybrid energy storage optimization method and device considering a fused salt heat storage coupling thermal power generating unit, and the method comprises the steps: analyzing the basic structure and energy flow relation of the fused salt heat storage coupling thermal power generating unit, and carrying out the transformation system division of the fused salt heat storage coupling thermal power generating unit; analyzing energy flow of each device of the fused salt heat storage coupling thermal power generating unit transformation system, and constructing an energy balance model and constraint conditions; building a corresponding mathematical model based on the energy balance model of each device; establishing a double-layer optimization configuration model of the corresponding hybrid energy storage system; solving the mathematical model and the double-layer optimization configuration model; according to the method, a mathematical model corresponding to molten salt heat storage coupled thermal power generating unit transformation system operation analysis is established based on the internal energy flow relation of molten salt heat storage and thermal power generating unit deep coupling, the electrochemical energy storage capacity and the molten salt heat storage capacity can be reasonably optimized through a model calculation result, multi-energy complementation of different types of energy is achieved, and the energy efficiency is improved. The system flexible adjustment capability is improved, and the system operation cost is reduced.

The invention discloses a method for processing carbon flux data obtained by a vortex correlation method. The method comprises the steps of data acquisition, original data preprocessing, data post-processing, data interpolation, data storage and additional description. The method comprises the following steps: capturing a signal by adopting an eddy correlation method, and recording original data in real time through a Smart Flux collector; in the preprocessing stage, invalid data, abnormal values, rainfall influence data and the like are removed by using Eddypro software, and necessary instrument error and inclination correction is carried out; in the post-processing stage, Eddypro and TOVI software are combined for further processing, including energy balance correction, quality control and the like; for missing data, adopting a linear interpolation method and other interpolation methods; the processed data can be stored in an Excel mode, an R language mode or a programming mode. According to the method, the carbon flux data quality can be effectively improved, and a solid foundation is provided for subsequent scientific research and data analysis.

The invention discloses an operation method and system for a cloud energy storage and sustainable distributed energy system, and relates to the technical field of energy scheduling, and the method comprises the steps: carrying out the cooperative management of the cloud energy storage and sustainable distributed energy system for electric energy storage through multi-stage dynamic configuration and dual-scene cooperative scheduling according to the charging power demand; according to a charging power demand, maximization of a comprehensive net present value for measuring investment profit is taken as a target to establish a target function, flexibility is added to the target function, and a design constraint, an energy balance constraint, a charging pile optimal scheduling constraint and a scheduling constraint of a battery energy storage system BESS and a transformer are taken as constraint conditions. Constructing an optimal scheduling model for measuring economic benefits and environmental benefits; the cloud energy storage and sustainable distributed energy system is subjected to optimization management through a collaborative management and optimization scheduling model and addition of an aggregator for energy coordinated scheduling. According to the invention, the stability of power supply can be improved.

The invention provides an ocean satellite Internet of Things multi-modal data narrow-band transmission scheduling method and device, belongs to the technical field of ocean satellite Internet of Things, and innovatively provides a multi-modal data narrow-band transmission scheduling strategy for challenges of ocean observation equipment in an energy-limited and dynamic satellite channel environment. The core of the method comprises the following steps: constructing a multi-modal data dynamic transmission model, and carrying out data value evaluation based on space-time intelligence; designing a congestion perception and hierarchical congestion control strategy to guarantee data timeliness; the transmission fairness is optimized in combination with the data value weight factor, the PAoI and the Jain fairness index; an energy dynamic evolution model is constructed, and long-term energy revenue and expenditure balance of equipment is guaranteed; based on a deep Q network and imitation learning, in combination with a security reinforcement learning framework, information timeliness, energy consumption and congestion are jointly optimized. According to the method, the deep and far sea observation and detection data transmission time delay, energy consumption and the congestion occurrence rate are remarkably reduced, and the information timeliness and the multi-modal data transmission scheduling fairness are improved.

The invention relates to an industrial park-based comprehensive energy flow direction on-line monitoring system and method, and the system comprises an energy modeling module which is used for representing instrument information, carrying out the modeling of collection labels and collection frequencies of different types of instruments, constructing nodes of different energy layered structures, carrying out the modeling of a directed flow direction relation between the nodes, and carrying out the modeling of the directed flow direction relation between the nodes; binding the logic relationship between the node and the instrument; the data acquisition module is used for performing data acquisition through an instrument, performing edge processing and encrypted transmission through communication equipment, and storing the data in a database; the energy monitoring module is used for monitoring and counting the state of the instrument and monitoring the energy flow direction of the enterprise in real time according to the directed flow direction of the node; and the statistical analysis module is used for providing energy balance analysis for different links of the enterprise energy in the conversion and use process according to the nodes, evaluating the energy consumption loss degrees of the different links, visualizing the nodes with abnormal loss and giving an alarm. Through the real-time and accurate calculation of the energy loss among the nodes at all levels, the backtracking of the nodes with abnormal loss and the timely pushing of the alarm information, the enterprise can timely discover the problems occurring in the energy supply, and can quickly find out the corresponding solution, reduce the energy consumption loss and guarantee the robustness of the energy flow network.

The invention discloses an actual evapotranspiration calculation method based on multi-source remote sensing data. Comprising the following steps: S1, acquiring multi-source remote sensing data; S2, based on an energy balance principle; S3, adopting a dynamic data fusion algorithm based on machine learning; S4, constructing an actual evapotranspiration calculation model adapted by regions; the method can accurately estimate the actual evapotranspiration of the heterogeneous region through multi-source remote sensing data fusion and a dynamic calculation model, is suitable for scenes such as agricultural areas, wetlands, urban green lands and forests, keeps high calculation precision and adaptability under various weather conditions, and has a wide application prospect. The problems of low resolution, data missing, lack of regional adaptability, low calculation efficiency and the like in the prior art are effectively solved, the precision, adaptability and efficiency of evapotranspiration calculation are improved, and more efficient technical support is provided for large-scale water resource management, ecological assessment and agricultural production.

The embodiment of the invention provides a thermal power plant waste heat gradient utilization management method and system, belongs to the field of energy and power engineering, and aims at solving the problems that in the prior art, waste heat gradient matching is unreasonable, the low-temperature waste heat recovery efficiency is low, and the system integration degree is insufficient. The method comprises the following steps: constructing a multi-physics field coupling digital twinborn model and performing real-time correction; establishing a dynamic matching matrix of the residual heat source and the heat consumption load based on balance analysis; solving a Pareto optimal operation scheme through a multi-objective optimization model; and generating and issuing a cooperative control instruction. The system comprises a panoramic data sensing module, a digital twin modeling module, a balance and optimization decision module and a cooperative control instruction generation module. Through global optimization and dynamic regulation and control, the waste heat utilization efficiency, the economical efficiency and the equipment reliability are remarkably improved.

The invention relates to the technical field of energy management, and discloses an energy internet architecture and an energy router thereof, and the energy internet architecture comprises a data acquisition and monitoring module, an energy management module, a fault detection and response module, a user interface and control module and an intelligent optimization module. The data acquisition and monitoring module is used for monitoring and acquiring various parameters in the system in real time, processing and transmitting data, and ensuring that the state of the system is transparent and controllable; the energy management module is used for predicting future energy demands, optimizing distribution of energy resources and managing the charging and discharging process of the energy storage system, and the fault detection and response module is used for monitoring the system state in real time, detecting, diagnosing and identifying faults and executing preset emergency treatment measures. Accurate prediction and optimal scheduling of energy demands are achieved through the first converter, the second converter and the energy management module, so that efficient utilization of energy and energy balance of the system are ensured, the optimal operation state is achieved under different load conditions, and the overall energy efficiency is improved.

The invention relates to an anti-reflux control method based on time interval distribution. The method comprises the following steps: acquiring a multi-source fused operation data set; obtaining a trend prediction result set according to the operation data set; according to the trend prediction result set, dividing the prediction time window into a plurality of continuous control time periods, and based on the power generation prediction value, the load prediction value and the uncertainty index of each time period, calculating a corresponding time period countercurrent risk level, and generating a time period risk assessment result; obtaining a time period budget allocation table according to a time period risk assessment result; according to the time period budget distribution table, performing time-division power adjustment on the photovoltaic inverter, the energy storage unit and the controllable load, and realizing smooth transition between adjacent time periods through a cross-time period energy balance mechanism; and monitoring the grid-connected point power and the equipment operation state in real time, and when power deviation or load sudden change is detected, dynamically correcting the current output according to the residual capacity of the time period budget allocation table. According to the invention, the photovoltaic anti-reflux control effect can be improved.

The invention provides a multi-source complementary intelligent power supply management method and system in a mobile square cabin. The method comprises the following steps: collecting real-time state data of multi-type energy supply equipment, and generating a comprehensive energy management data set; based on the comprehensive energy management data set, dynamically evaluating real-time efficiency by adopting an interval optimization algorithm based on an evolutionary strategy, and generating an energy combination strategy report by applying a Markov decision process; based on the energy combination strategy report, adopting a gradient descent optimization algorithm to adjust working parameters of the multi-type energy supply equipment, and applying a real-time energy balance technology to generate an optimized energy configuration scheme; and based on the optimized energy configuration scheme, monitoring the operation condition of a power supply system, optimizing working parameters, and generating an intelligent power supply management parameter set. According to the technical scheme, the intelligent power supply management effect can be effectively improved.

The invention discloses an industrial park integrated energy system optimization method and system, and belongs to the technical field of building and energy system design optimizing.By determining constraint conditions of energy balance constraint, equipment capacity constraint and equipment operation constraint, load data in an industrial park are used as initial conditions, design parameters and meteorological data are input, and the optimal energy balance constraint, equipment capacity constraint and equipment operation constraint are determined; taking the hydrogen doping ratio as a decision variable, constructing a comprehensive energy system optimization model and determining a target function; solving the objective function by taking minimization of annual total cost, carbon emission and energy consumption of the integrated energy system as an objective, and outputting a Pareto solution set; and performing multi-target sorting on the Pareto solution set, screening out an optimal solution corresponding to the decision variable, and obtaining a real-time power condition of each device corresponding to the optimal solution. According to the comprehensive energy system optimization model constructed by the method, the use proportion of hydrogen energy can be adjusted under different operation conditions, so that the optimal energy efficiency and environmental protection effect are achieved.

The invention discloses an electric heat comprehensive energy balance control method and system based on a master-slave game, and belongs to the technical field of comprehensive energy management, and the method comprises the steps: taking the benefit maximization of a comprehensive energy operator as a first objective function, constructing an upper layer model, and generating an optimal energy selling price, and decision variables comprise an electricity selling price and a heat selling price; building a lower-layer model by taking user income maximization as a second objective function, and determining an optimal output plan and a load adjustment plan in the lower-layer model through an optimal energy pricing given by the upper-layer model; and taking a comprehensive energy operator corresponding to the upper-layer model as a leader, taking a load aggregator corresponding to the lower-layer model as a follower, and achieving Stackelberg equilibrium through a master-slave game, so that electric heating comprehensive energy is subjected to equilibrium control. According to the method, better global economic performance can be obtained, and the balance between the electricity price and the customer satisfaction is considered at the same time.

The invention relates to the technical field of intelligent water affairs, in particular to a three-level combined processing method for urban water consumption prediction, which comprises the following steps: S1, data restoration: correcting abnormal values in an urban water consumption time sequence by using a dynamic threshold correction method based on multi-scale wavelet decomposition; s2, performing feature decoupling; and S3, performing prediction fusion. According to the method in the technical scheme, a dynamic threshold correction method based on multi-scale wavelet decomposition is adopted, signal hierarchical analysis is achieved through discrete wavelet transformation, a dynamic threshold mechanism is constructed in combination with MAD robust statistics, and abnormal points are effectively recognized and corrected; constructing a dynamic frequency band division joint model of variational mode decomposition and spectrum energy balance, proposing a dynamic frequency band recombination strategy guided by amplitude ranking, and performing energy balance division and inverse transformation reconstruction on VMD high-frequency sub-components through fast Fourier transform spectrum analysis; fine separation and multi-band phase synchronization of high-frequency abrupt change characteristics and periodic fluctuation are realized; and finally, constructing a long-short-term memory network to predict and reconstruct all sub-components.

The invention provides a multi-microgrid energy collaborative optimization method and system. The method comprises the following steps: S1, establishing an energy collaborative network topology structure comprising a plurality of microgrid nodes; s2, constructing an energy balance model based on the real-time power demand, the new energy output prediction and the power grid dispatching instruction; s3, taking the minimization of the total operation cost of the multi-microgrid system as a target to form an optimization function; s4, an improved whale optimization algorithm is adopted to solve the optimization function, and an energy scheduling scheme of each microgrid in each time period is obtained; s5, regulating and controlling an energy storage device, a charging pile and an adjustable load in each micro-grid according to the energy scheduling scheme, and coordinating the energy flow direction and the transmission power between the micro-grids; and S6, monitoring the actual operation state and the energy interaction effect of each micro-grid, and when it is detected that the predicted deviation exceeds a preset threshold value, re-executing the steps S2 to S5 based on the real-time data. According to the invention, energy collaboration among multiple microgrids can be realized, the new energy consumption capability is improved, the operation cost is reduced, and the economy and stability of power grid operation are enhanced.

The invention discloses an electric charge abnormity error processing method and system based on intelligent verification, and relates to the technical field of electric power billing, and the method comprises the steps: obtaining electric charge abnormity first data, carrying out the abnormity detection of electric charge calculation based on a neural network algorithm, and enabling the electric charge abnormity first data to comprise an electricity price feature, a force adjustment standard feature and a definite proportion feature; when the electric charge calculation is abnormal, correcting the electric quantity based on load flow calculation and an energy balance algorithm, retrieving historical electricity price information of a user, performing consistency verification on the historical electricity price information and current electricity price information, judging and updating the electricity price of the user, and recalculating the electric charge; real-time updating three-color labeling display is performed on an electric charge correction calculation result based on a visualization technology, contribution degrees of input parameters to electric charges are obtained based on a local sensitivity method, and importance ranking is performed on the input parameters according to the contribution degrees; according to the invention, through accurate correction of the key parameters of electricity charge calculation, the efficiency and accuracy of electricity charge error processing are effectively improved, the working pressure of basic units is reduced, and the customer satisfaction is improved.

The invention relates to the technical field of power systems and energy storage, and discloses a new energy and pumped storage coordinated cross-time energy balance method and system. The method comprises the following steps: performing feature extraction and dynamic modeling on wind power output night monitoring data and solar waste heat power generation night monitoring data to obtain a new energy excess power prediction value; performing water level trend analysis and energy storage capability evaluation on the real-time water level data of the pumped storage upper reservoir and the watershed incoming water forecast data to obtain a pumped storage acceptance power upper limit value; performing power adjustment on the new energy power generation end based on a comparison result to obtain new energy actual output data; performing threshold judgment and response coefficient calculation on the supply-demand deviation value to obtain a demand side adjustment scheme; and performing dynamic planning optimization and constraint condition correction on the time-phased power data sequence to obtain a multi-energy collaborative power regulation instruction sequence covering the whole time period. According to the method, accurate response to new energy output fluctuation and efficient utilization of pumped storage resources are achieved.

The invention discloses an electric power system resource scheduling method and device, and belongs to the technical field of electric power systems, and the method comprises the steps: obtaining the resource data of an electric power system when the natural climbing amount of the electric power system is not greater than the climbing demand of the electric power system, and taking the minimization of the total operation cost of the electric power system and the maximization of the climbing service demand response as targets; constructing an objective function, a system power balance constraint, a transmission capacity constraint, an energy storage charging and discharging constraint, an energy storage energy balance constraint, a climbing ability constraint and a climbing service demand constraint; and solving the target function under each constraint to obtain the output of each thermal power generating unit and each energy storage system in each scheduling period and the up-climbing demand quantity and the down-climbing demand quantity of each flexible climbing price interval in each scheduling period, and scheduling the resources of the power system according to the solving result. By implementing the invention, the problem that the power supply and demand of the power system are unbalanced when the natural climbing amount is not greater than the climbing demand in the prior art can be solved, and the operation stability of the power system is improved.

The invention discloses an energy-saving QoS (Quality of Service) routing protocol implementation method based on ant colony optimization, which aims at solving the problems of low routing efficiency and high path energy consumption in a UANET (User Ad Hoc Network) based on RF / FSO (Radio Frequency / Free Space Optimization) communication, and realizes an energy-saving QoS routing protocol based on ant colony optimization. An energy-saving QoS routing algorithm based on ant colony optimization is provided, and node neighborhood energy density is considered in a path transition probability model, so that the search efficiency of the ant colony algorithm is improved, and energy balance in the network is ensured; energy and distance factors are added into a pheromone updating rule, and the difference between the optimal path and other paths is increased; a self-adaptive pheromone volatilization mechanism is added, and the volatilization rate of pheromones is dynamically adjusted according to the real-time state of the network; and a cross-layer data exchange interface is added, so that real-time updating of link interaction data is ensured, and stable communication in a dynamic network environment is supported.

The invention provides a solar energy-radio frequency energy dual-driven low-altitude polarization switching dynamic power management system, and relates to the technical field of low-altitude flight. The system integrates a high-efficiency solar energy collection unit and a radio frequency energy collection unit with dynamic polarization adaptive switching capability, is assisted by a high-performance hybrid energy storage unit, and carries out unified coordination control through an intelligent power management unit. The radio frequency energy collection unit adopts a reconfigurable antenna technology, can sense the polarization characteristic of an environment radio frequency signal in real time, and dynamically switches the polarization state of an antenna to maximize the instantaneous energy capture efficiency; the intelligent power management unit executes a dynamic and collaborative energy flow scheduling strategy based on comprehensive analysis of solar irradiance, environment radio frequency spectrum and polarization characteristics, energy storage unit state, future energy income and expenditure prediction and real-time load demand; and the energy self-sustaining capability, the task endurance time and the working stability of low-altitude equipment in a complex and changeable environment are improved.

A method of real-time energy-tracking including: measuring the energy produced by an energy generator and the energy consumed by an energy consumer; collecting generated energy measurements and consumed energy measurements over a specified time period; receiving data packets containing these measurements along with associated temporal metadata, wherein by aligning the generated energy measurements with the consumed energy measurements based on this temporal data, the method creates matched sets of measurements, wherein for each matched set, it assesses the energy balance by comparing the generated energy to the corresponding consumed energy, thereby identifying any real-time energy deficit or excess.

The invention discloses an intelligent calibration method and system for the electric quantity of an instrument, and relates to the technical field of electric energy metering of an electric power system.The intelligent calibration method comprises the steps that an electric meter network diagram with a main meter and sub-meters as nodes is constructed, and robust composite correlation indexes are calculated on the basis of reading increments in a sliding time window; the interference of common background load and instantaneous noise is suppressed by using a threshold clipping and main table purification mechanism, so that the depiction capability of the correlation graph on a physical connection relationship is improved fundamentally, and the phase to which the sub-table belongs can be identified more accurately in a stock area with unknown phase or incomplete topology; a graph neural network model is introduced based on the network graph, electric meter embedding representation with physical meaning is obtained through neighborhood information aggregation, phase grouping is achieved in combination with unsupervised clustering, split-phase energy balance loss is designed in the training stage, and the difference between the reading of a main meter and the sum of the reading of sub-meters in each phase group is used as a constraint. Alignment of the embedding space and the energy conservation relation is pushed in a self-supervised mode.

The invention relates to a source-grid-load-storage integrated optimal configuration method of an enterprise power grid, and belongs to the technical field of power system planning of the enterprise power grid. The invention aims to realize source network load storage collaborative configuration through a multi-dimensional data processing and optimization model. The method comprises the following steps: generating a year-round wind and light output per unit value based on wind and light historical data, wind speed or illumination data; constructing annual typical load data of the enterprise through load curve generation, k-means clustering and random sampling; a mixed integer linear programming model is established in combination with constraints such as investment operation cost and energy balance; key indexes such as green electricity proportion, energy abandoning and electricity purchasing cost are calculated through the model; and performing scheme checking on the maximum / minimum load day and the maximum / minimum green power ratio day. According to the method, through data driving and optimization modeling, the green power consumption efficiency can be effectively improved, the wind curtailment and light curtailment amount is reduced, meanwhile, the investment and operation cost is optimized, and scientific support is provided for source network load storage integrated configuration of an enterprise power grid.

The invention provides a three-layer nested IES collaborative optimization method fusing semantic evolution and reinforcement learning, and belongs to the technical field of integrated energy system scheduling, and the method comprises the steps: constructing an IES mathematical model, an energy balance constraint and an optimization target, and abstracting a scheduling task into a Markov decision process MDP quintuple; building an ARDRL model containing a semantic knowledge layer, an evolutionary optimization layer and a distributed evaluation layer, generating a candidate reward function population through a large language model, and quantifying the fitness through Thompson sampling optimization and SAC intelligent agent distributed evaluation; and finally, carrying out iterative optimization by taking the fitness as feedback, and outputting an optimal reward function to guide IES collaborative scheduling. According to the method, a reward function does not need to be designed manually, the robustness and comprehensive performance of a scheduling strategy are improved, and economic, safe and low-carbon multi-target optimal balance is realized.