91results about "Generation forecast in ac network" patented technology

The application relates to the field of information technology, in particular to a smart charging pile control method and system supporting photovoltaic storage linkage. The method comprises the following steps: acquiring real-time output data of a photovoltaic power generation system in a park, short-time predicted load of the park, charging state information of new energy vehicles, energy storage state data of fast charging and energy storage devices, and driving time of users; according to a preset scheduling period, the real-time output data, the short-time predicted load of the park and the energy storage state data are read, and whether there is light abandonment and power gap in the next scheduling period is judged; when there is light abandonment, new energy vehicles in a chargeable state are dispatched to consume abandoned light power for charging, and the consumed power is recorded; when there is a power gap, new energy vehicles meeting preset discharge conditions are controlled to reversely discharge to the park through charging piles, and the discharged power is recorded; the charging power, the consumed power and the discharged power of the new energy vehicles are respectively subjected to cost measurement, and the final charging cost is obtained.

The application provides a kind of wind and light storage power station day-to-day active power optimization scheduling method and system, comprising: obtaining target wind power, photovoltaic power station single-day historical output data to obtain wind power, photovoltaic power day-to-day power prediction curve;The wind power, photovoltaic power day-to-day power prediction curve is input into the day-to-day optimization scheduling target model established in advance, respectively with tracking scheduling plan output and smooth output fluctuation as scheduling target, solve wind-light-storage day-to-day optimization scheduling output curve.The method target is clear and distinct, optimization objective function and parameter can be selected and set according to the actual operation of wind-light-storage new energy power station, can meet the demand of wind-light-storage new energy power station application scene, has guiding significance and practical value for new energy engineering.

In the context of an electrical utility system, changing cloud conditions may cause a customer having solar panels to greatly increase or decrease electrical demand in a difficult-to-predict manner. Accordingly, a spinning reserve maintained by an electric utility company must be larger, and is therefore more expensive. In an example, the spinning reserve may be managed by: calculating a stable sequence of forecasts of smoothed real-time consumption, wherein the calculating is based at least in part on smoothed estimates of consumption data. A stable sequence of forecasts of real-time measured load may be calculated by subtracting forecasts of real-time distributed solar photovoltaic (PV) generation data from the stable sequence of forecasts of smoothed real-time consumption. The spinning reserve of the electricity system may be controlled based at least in part on the stable sequence of forecasts of real-time measured load.

This invention provides a wind power plant scheduling method and system based on fatigue distribution. [Solution] The solution includes establishing multiple wind turbine points based on the parameters of the wind turbine unit, generating predicted power for each wind turbine point within the current adjustment cycle based on a predetermined power prediction model based on historical environmental parameters, generating an initial scheduling policy based on the power grid scheduling command and the predicted power for all wind turbine points within the current adjustment cycle, obtaining fatigue evaluation values ​​for each wind turbine point, determining whether or not to modify the initial scheduling policy based on all fatigue evaluation values, generating an initial scheduling policy based on the operating parameters of each wind turbine unit, optimizing and adjusting the initial scheduling policy, and optimizing the uniformity of the fatigue distribution of the wind power plant while assuming no loss of power generation.

The present disclosure belongs to the technical field of power system restoration, and particularly relates to an orderly black start method and system of a new energy power generation unit, comprising: acquiring system parameters of the new energy power generation unit; constructing a black start system model of the new energy power generation unit based on the acquired system parameters; evaluating the black start capability of the constructed black start system model to obtain a black start utility output of the new energy power generation unit; and optimizing the start order of the new energy power generation unit according to the acquired system parameters of the new energy power generation unit and the obtained black start utility output, combining an orderly participation algorithm to complete the orderly black start of the new energy power generation unit.

An example operation includes at least one of receiving data comprising at least one of weather data, grid load data, or energy usage data related to an area, executing an Artificial Intelligence (AI) model to predict energy production in the area and energy consumption in the area, based on the received data, determining an optimized energy-related output in a timeframe, based on the predicted energy production and the predicted energy consumption, and setting, by a device associated with a location in the area, at least one control at the location based on a parameter associated with the optimized energy-related output, to produce the optimized energy-related output within the timeframe.

A multi-timescale coordinated optimization scheduling method for an electrical power system that includes a number of distributed energy resources (DERs) is disclosed. The method includes performing long-timescale optimization scheduling for the electrical power system based at least on renewable energy generation forecast data of the DERs to obtain long-timescale operation planning data. The method further includes performing mid-timescale optimization scheduling for the electrical power system based on the long-timescale operation planning data and measured data of the DERs to obtain mid-timescale operation planning data. The method further includes performing at least close to real-time optimization scheduling for the electrical power system based on the mid-timescale operation planning data, the measured data of the DERs and grid signals of the electrical power system to obtain short-timescale power setpoints for the DERs. An electrical power system in which the method is used is also disclosed.

The application discloses an interval optimization scheduling method considering new energy uncertainty and power grid flexibility demand, and comprises the following steps: constructing a new energy output uncertainty model, the new energy output uncertainty model considering wind power and photovoltaic output values and wind power and photovoltaic output prediction error probability density curves in each period to obtain wind power and photovoltaic output intervals; establishing a multi-objective interval optimization scheduling model with the minimum power system comprehensive operation cost, the minimum voltage offset, the maximum power supply margin of the whole network and the maximum consumption margin of the whole network as targets; solving the multi-objective interval optimization scheduling model by using an NSGA-11 multi-objective genetic algorithm to obtain multiple sets of optimal objective functions and corresponding Pareto solution sets; and realizing interval optimization scheduling according to the obtained interval scheduling plan scheme corresponding to the Pareto optimal solution set.

The application discloses a photovoltaic ultra-short-term power prediction method based on cloud image multi-feature extraction, and belongs to the field of electric power. The prediction method comprises the following steps: acquiring a change image of a cloud cluster, and obtaining a ground-based cloud image sequence; all cloud images in the ground-based cloud image sequence are preprocessed to obtain a preprocessed image sequence; cloud image features are acquired based on the preprocessed image sequence; historical photovoltaic output power data and the cloud image features are subjected to deep learning to acquire a photovoltaic ultra-short-term power prediction model, so that photovoltaic ultra-short-term power prediction can be performed. The problem of insufficient cloud image feature extraction features in the prior art, which further leads to the problem of excessively low prediction result accuracy, is solved. Through accurate analysis of the features of the cloud image, the CNN and Autoformer methods are combined to construct a photovoltaic ultra-short-term power prediction model, and then photovoltaic ultra-short-term power prediction is performed.

A method for managing power trading to sell power of a renewable energy power plant according to an embodiment may comprise the steps of: generating an initial bid by using a first predicted power generation value of the renewable energy power plant; transmitting the initial bid to a power exchange server within a predetermined initial bidding period; generating a prior-revised bid by using an overbid capacity generated on the basis of the first predicted power generation value and a second predicted power generation value of the renewable energy power plant; transmitting the prior-revised bid to the power exchange server within a predetermined prior-revision bidding period; generating a real-time-revised bid by using the overbid capacity generated on the basis of the first predicted power generation value and the second predicted power generation value of the renewable energy power plant; and transmitting the real-time-revised bid to the power exchange server within a predetermined real-time revision bidding period.

This invention relates to a regional generalization method for an adaptive graph spatiotemporal prediction model for wind power clusters, belonging to the field of wind power prediction and new energy power system dispatching technology. The technical solution is as follows: first, a regional generalization method for the adaptive graph spatiotemporal prediction model of wind power clusters is used to solve the adaptability and accuracy problems of cross-regional prediction; then, the transparency and credibility of prediction decisions are improved by relying on the model structure interpretability analysis method. This includes the following two steps: first, achieving effective generalization prediction; second, endowing the prediction with interpretability. The beneficial effects of this invention are: significantly improved generalization performance, reducing computational costs and deployment cycle; optimized prediction accuracy, enabling the adaptive graph spatiotemporal prediction model of wind power clusters to more accurately capture the spatiotemporal correlation between wind farms, reducing short-term wind power prediction errors by 10%-20%, and providing more reliable data support for grid dispatching; and enhanced interpretability, meeting the requirements of the dispatching system for model auditability and reducing operation and maintenance decision risks.

An optimization method for stabilizing photovoltaic (PV) power generation fluctuations using distributed energy storage based on scenario sets is proposed. This method establishes a dispatchable capacity model for distributed energy storage based on its physical characteristics; establishes node voltage constraints and branch transmission capacity constraints for the distribution network; introduces reactive power regulation equipment to establish a dispatchable reactive power support range; and maintains power and voltage stability through distributed energy storage and various reactive power regulation devices while considering branch transmission capacity constraints. Finally, a coordinated optimization model for distributed energy storage based on PV power generation prediction scenarios is established. This invention prioritizes the basic safety of the distribution network and can be well applied to cities with abundant solar resources. By equipping distributed energy storage and certain reactive power regulation devices, it alleviates power and voltage fluctuations caused by intermittent PV power generation, thereby improving grid operational stability, reducing economic costs, and conserving resources.

An energy management system for microgrid systems. The energy management system includes a controller. The controller is configured to receive forecasted weather condition data, predict a power generation profile and / or a power demand profile of a microgrid system in response to the forecasted weather condition data, determine a performance model and / or a degradation model of one or more system components of the microgrid system in response to the power generation profile and / or the power demand profile, derive an energy management optimization strategy in response to the performance model and / or the degradation model of the one or more system components of the microgrid system, and control an operation mode of the one or more system components of the microgrid system in response to the energy management optimization strategy.

The application belongs to the technical field of artificial intelligence, and particularly relates to a wind power prediction method based on multi-objective optimization, which comprises wind power data acquisition and training data set construction, adaptive sliding window and dynamic fluctuation decomposition of wind power time series data, short-term power prediction model construction and short-term power prediction. The method can autonomously adjust the historical window length and decomposition scale according to the inherent fluctuation characteristics of the data, realize the multi-scale accurate representation of the non-stationary power sequence, construct a dynamic space-time graph by fusing the geographical distance and the correlation of instantaneous power, design a graph attention network combined with the trend similarity gate, realize the dynamic fine modeling of the spatial correlation, dynamically balance the prediction accuracy and interval prediction reliability through the fluctuation intensity adaptive loss function, synchronously output the deterministic and probabilistic prediction results, and embed the rated power limit and the climbing rate constraint in the model in a soft manner, so that the prediction results conform to the actual operation law of the wind turbine.

A method for operating a microgrid system (100) comprising: receiving a microgrid on or off schedule input (208) containing a schedule of required electrical power generation for the microgrid system (100) for a given period; filtering the scheduled on or off input and converting the scheduled on or off input into power levels (608) to meet the power demand for required electrical power generation of the on or off schedule input for the microgrid system (100); receiving an actual load level for the microgrid system (100) based on one or more electrical loads (116) electrically coupled to the microgrid system (100); and comparing the schedule of required electrical power generation with the actual electrical power generation required for the microgrid system (100).and switching one or more electrical systems on or off in real time to compensate for a difference between the planned required electrical energy generation and the actual required electrical energy generation.

The source network load storage collaborative multi-time scale self-balancing scheduling method and system of the active power distribution network maximizes the difference between the maximum value of the operation income of the day-ahead market transaction of the active power distribution network and the minimum value of the tie line power as a day-ahead scheduling objective function; takes the scheduling power balance constraint as a day-ahead scheduling constraint condition; obtains the error of the intraday prediction value and the day-ahead prediction value of the new energy unit output power and the adjustment amount of the intraday planning value compared with the day-ahead planning value of the building load power, and minimizes the difference between the error and the adjustment amount as an intraday scheduling objective function; takes the day-ahead scheduling constraint condition as an intraday scheduling constraint condition; takes the day-ahead scheduling objective function, the day-ahead scheduling constraint condition, the intraday scheduling objective function and the intraday scheduling constraint condition to form a multi-time scale self-balancing optimization scheduling model; iteratively solves the multi-time scale self-balancing optimization scheduling model to obtain the scheduling scheme of the active power distribution network under the source network load storage collaboration, and optimizes the tie line power to improve the safety of the active power distribution network.

In an electronic apparatus, reference information stored on a memory includes standard appliance ownership information describing owned home appliances of at least one standard household and standard monthly power consumption information of the standard household. A processor obtains first monthly power consumption information of a first household which owns a first home appliance of a same type as a standard home appliance described in the standard appliance ownership information. Based on a difference between the standard and first monthly power consumption information being within a threshold range, the processor compares appliance monthly power consumption information of the standard home appliance and of the first home appliance, and, based on the result being within a threshold range, predicts first appliance ownership information on owned home appliances of the first household based on the standard appliance ownership information. The processor then provides guide information associated with the first appliance ownership information.

The application discloses a kind of based on environmental perception's foldable photovoltaic module deployment control method, it is related to photovoltaic module control technical field, the steps of this method include: obtaining environmental data and photovoltaic module mechanical state by sensor network;Satellite image data in the environmental data is extracted, to obtain environmental occlusion feature, output future environmental occlusion loss coefficient;By the photovoltaic module mechanical state, assess future deployment structure risk index;Based on the environmental occlusion loss coefficient and deployment structure risk index, establish benefit-loss model, the benefit-loss model is used to output future deployment benefit;Set photovoltaic panel action control algorithm, future deployment benefit is taken as input, and the deployment control parameter of foldable photovoltaic module is output.The application solves the problem that the existing control strategy is mostly to maximize instantaneous power generation as target, ignores equipment loss and safety risk.

The application discloses a wind power prediction method and system fusing wind field images and multiple physical constraints, and belongs to the technical field of new energy power generation, aiming to improve the accuracy and stability of short-term wind power prediction. The method comprises the following steps: obtaining wind field image data and performing pretreatment; extracting features by using a dynamic time sequence encoder, wherein the dynamic time sequence encoder comprises two parallel branches of a Fourier neural operator and a convolution gate recurrent unit, which are respectively used for capturing global frequency spectrum features and local transient features of the wind field; introducing spatial variable gate parameters and learnable channel weights to fuse features of each branch; based on the fused features, a neural network architecture driven by physical information is used to realize multi-step wind field simulation; and multi-step wind power prediction is performed on multiple wind farms by using a time sequence fusion Transformer according to multi-step wind field images obtained through the wind field simulation. The application overcomes the shortcomings of existing methods in capturing the space-time dependence and local rapid disturbance of the wind field.

A method may include obtaining irradiance data at a first time and a second time from sensors, determining whether one or more solar modules of a plurality of networked power plants will be covered by a shadow or shade at a third time based on the irradiance data, and generating, based on the determination, a power output prediction for each power plant of the networked power plants at the third time. The method may further include receiving power delivery profiles for first and second loads, adjusting a power output of one or more power plants of the networked power plants based at least in part on the power output prediction and the power delivery profiles for the first and second loads, and allocating a combined power output of the power plants to the first and second loads based on first and second load reliability thresholds.

An example discrete, time-domain computational method finds optimal power resources in a microgrid for reliability and resilience. The method involves receiving, by an input module, inputs including microgrid parameters, control conditions, natural resource datasets, and a load profile for the microgrid. The method forecasts, by a forecasting module based on the inputs, forecasted values for a plurality of power grid outcomes related to reliability and resilience, to inform power resource investment decisions. The method generates, by a forecasted results generator, a results report including the forecasted values. The results report is readable by several stakeholders, including Military installations, remote communities, campuses, and institutions.

The present application relates to the technical field of power grids, and particularly relates to an output scheduling method and apparatus for a renewable energy power plant, and a computer device, a computer-readable storage medium and a computer program product. The method comprises: on the basis of a renewable energy output prediction scenario set for each renewable energy station in a renewable energy power plant, determining a target renewable energy output reference parameter and a target renewable energy output prediction error parameter of each renewable energy station, and on the basis of the target renewable energy output reference parameter and the target renewable energy output prediction error parameter of each renewable energy station, determining a renewable energy output uncertainty set for each renewable energy station; and by using the renewable energy output uncertainty set for each renewable energy station as a constraint condition, solving an output scheduling objective function pre-constructed for the renewable energy power plant, so as to obtain a target net output value of each renewable energy station, such that output scheduling is performed on each renewable energy station. By means of using the method, the function of an energy storage apparatus configured in a renewable energy power plant can be fully exerted.

An asset management system helps ensure the safety of technicians performing maintenance on electrical power generation assets. The system includes an electronic device operated by a technician. Prior to performing maintenance on a power generation asset, the technician utilizes the electronic device to scan an identification marker on the asset. The electronic device then retrieves, from an asset database, status data regarding the safety status of the asset. The electronic device displays the status data to the technician.

The present application relates to a kind of offshore wind power diversification consumption comprehensive prediction energy management fast calculation method, belong to new energy field.The method specifically includes the following steps: establish the nonlinear optimization control model and optimization control problem of offshore wind power-hydrogen production and storage-hydrogen fuel cell-battery coupling system, the active power of wind turbine is carried out day-ahead, short-time and ultra-short-time load prediction within day, global optimization is carried out using dynamic programming and convex programming combination iteration method, respectively obtain the energy storage state of battery and hydrogen storage tank under day-ahead scheduling, the switch sequence of hydrogen production electrolytic cell under short-time prediction control within day, the real-time output of battery, electrolytic cell and hydrogen fuel cell under ultra-short-time prediction control, the method is aimed at the diversification consumption problem of offshore wind power-hydrogen production-hydrogen fuel cell-battery coupling system, constructs multi-time scale prediction energy management and realizes the solution of different time scale prediction control problem.

In an example method, a system accesses a first data set representing parameters for implementing and operating a Power-to-X plant, and determines one or more configurations of the Power-to-X plant based on the first data set and a Bayesian optimization process. The configurations are determined by parsing the first data set to identify fields in the first data set, each representing a respective parameter; generating a plurality of data vectors representing respective first candidate configurations of the Power-to-X plant; inputting the data vectors and the first data set into a computer model; predicting, based on the computer model, a performance of the Power-to-X plant according to each of the first candidate configurations; and generating, using the Bayesian optimization process, one or more second candidate configurations based on the predicted performance. Further, the system generates and stores a second data set representing the one or more configurations of the Power-to-X plant.

The application relates to the technical field of power system real-time scheduling, and discloses a power system real-time scheduling method, system, device and medium, the method comprising: predicting wind and light load uncertainty of a power system under different time scales; constructing a flexible resource model suitable for different response times; constructing a net load set based on the uncertainty; determining power system flexibility constraints; establishing and solving a scheduling model containing the constraints to realize real-time scheduling. The application improves the accuracy and reliability of real-time scheduling by considering uncertain factors and flexible resource responses in the power system. It constructs a flexible resource model and a net load uncertainty set suitable for different time scales to adapt to system dynamic changes and support stable operation. This method can also reduce operating costs and improve resource utilization efficiency, and has an important influence on the sustainable development of the power system.

The application provides a device health state prediction method, an electronic device and a system, and the steps of the method comprise: predicting power generation power of a first prediction time period based on historical power generation power generation sets; calculating a health consumption value of the first prediction time period based on the power generation power of the first prediction time period; calculating an expected health value of the first prediction time period based on a current health value of the power generation set and the health consumption value of the first prediction time period; comparing the health value of the first prediction time period with a health threshold value, and determining whether maintenance of the power generation set in the first prediction time period is needed based on a comparison result; and if it is determined that the maintenance of the power generation set in the first prediction time period is needed, sending a first maintenance instruction to a control end, wherein the first maintenance instruction is used to instruct a worker to maintain the power generation set after the first prediction time period. The scheme can predict the state of the power generation set, determine whether maintenance is needed, evaluate the health state of the power generation device, and determine a maintenance time.

The present application relates to a method for automatic scheduling based on load and distributed energy fluctuation, comprising the following steps: data acquisition: acquiring load prediction time series data and distributed energy generation prediction time series data, generating an initial scheduling plan based on the load prediction time series data and the distributed energy generation prediction time series data, the initial scheduling plan including a conventional unit output plan and a storage energy charging and discharging plan; data acquisition: real-time acquisition of load actual power time series data and distributed energy actual power time series data; fluctuation decomposition: adaptive variational mode decomposition is performed on the load actual power time series data and the distributed energy actual power time series data respectively, and load fluctuation components and distributed energy fluctuation components are extracted; index calculation: according to the load fluctuation components and the distributed energy fluctuation components; the present application can accurately quantify fluctuation dynamic scheduling to improve the stability and economy of the power grid.

The application relates to the technical field of power distribution scheduling, in particular to a distributed new energy power distribution network optimization scheduling method and system. The method is characterized in that: the power distribution network information model is constructed through step S1; the mutation prediction result and the mutation state are acquired through step S2; the scheduling cost is calculated and the target execution decision is output through step S3; and the scheduling optimization process is feedback optimized through step S4. The system comprises a power grid information acquisition module, a weather mutation prediction module, a new energy distribution monitoring module and a scheduling feedback optimization module. The application collects target power distribution network information, constructs a power distribution network information model according to the target power distribution network information, predicts weather mutation, and outputs the best target execution decision, so that the power distribution network can be efficiently optimized and scheduled, and the power generation cost is reduced.

The application discloses a wind power distribution method based on adaptive adjustment, an electronic device and a medium, and relates to the technical field of wind power generation. The method comprises the following steps: obtaining a wind farm ultra-short-term regulation instruction; predicting multi-unit power and health characteristics, and constructing a unit characteristic grid; performing attention-driven distribution based on a regulation target and the grid to obtain an initial scheme; constructing a twin wind farm model and deducing a wake effect to obtain a corrected group; and calling a cost model to combine the twin model to progressively optimize and obtain a power distribution parameter optimization result. The method solves the technical problem that the existing wind farm power distribution method is difficult to comprehensively consider the health state of a wind turbine generator, the wake effect and the regulation cost, resulting in low power distribution precision, insufficient overall operation efficiency and safety of the wind farm, and achieves the technical effects of realizing accurate distribution of wind farm power under the premise of meeting the grid ultra-short-term regulation demand, reducing unit fatigue loss and wake interference, and improving the overall operation efficiency and reliability of the wind farm.