80 results about "Energy forecasting" patented technology

The invention, which relates to the technical field of energy management, discloses a multi-target collaborative optimization prediction system and method for regional-level water-wind-light power generation power, and the system comprises a data collection module which is used for obtaining power generation power data, meteorological environment data and power grid load demand data in real time; the optimization processor is used for receiving the data fed back by the data acquisition module, and constructing a multi-target optimization model based on spatial-temporal feature extraction to generate a plurality of candidate optimization paths; the screening module is used for screening the candidate paths through a dynamic weight distribution algorithm and screening out an optimal collaborative optimization path; and the dynamic feedback module is used for carrying out online correction on the optimal collaborative optimization path in the real-time optimization process according to the power grid frequency deviation, the energy storage charge state and the meteorological abrupt change signal. The optimization processor constructs the multi-target optimization model based on the spatial-temporal characteristics, generates a plurality of candidate optimization paths and screens out the optimal path, and compared with a traditional single energy prediction and simple scheduling mode, the precision of power generation power prediction is improved.

The invention relates to the technical field of energy prediction, in particular to an energy short-term load prediction method and system based on SE-Block improved Transform. The method comprises the steps of performing reversible normalization preprocessing based on acquired multi-element load sequence data; carrying out feature extraction and fusion on the preprocessed data by utilizing improved cross-scale interaction Patching, wherein the feature extraction and fusion comprise multi-scale feature extraction, cross-scale interaction alignment, residual error correction and dynamic fusion; and performing feature screening on the fused features based on a channel attention mechanism, wherein the feature screening comprises feature response based on improved SE-Block and non-linear interaction of context vectors. Aiming at the non-stationarity of the actual load caused by the influence of meteorological conditions and user behaviors, the model accurately depicts the fluctuation details of the load curve by automatically eliminating the noise interference among multiple variables, and the robustness of the model in the multi-element load prediction of the integrated energy system is reflected.

The invention discloses a photovoltaic power ultra-short-term prediction method, system and device and a storage medium, and relates to the technical field of new energy prediction. The method comprises the following steps: constructing an improved ensemble empirical mode decomposition algorithm to decompose original photovoltaic power data, and distinguishing and reconstructing a plurality of decomposed intrinsic mode functions to obtain reconstruction sequences of high, medium and low frequency components; for high-frequency and intermediate-frequency components, carrying out dynamic denoising by adopting an extended Kalman filtering algorithm; and inputting the original data, the low-frequency component, the denoised high-frequency component and the denoised intermediate-frequency component into a WTConv1d module, extracting multi-scale features through a wavelet filter and convolution operation, and inputting a multi-dimensional input matrix constructed by the multi-scale features and meteorological data into a Transform model for prediction. According to the method, noise interference can be effectively suppressed, multi-time scale feature expression is enhanced, and a self-attention mechanism is fully utilized to capture a cross-scale dependency relationship, so that the prediction precision and stability are improved.

The invention relates to the technical field of power system regulation and control, in particular to a park multi-resource intelligent flexible control method and device considering energy and carbon consumption collaboration, and the method comprises the steps: obtaining historical energy consumption data and historical carbon emission data in a target park; training the historical energy consumption data and the historical carbon emission data based on a feature-level constraint preference optimization algorithm to obtain a park multi-energy prediction model based on feature-level constraint preference optimization so as to predict energy demands in a future time period; constructing a park multi-resource optimization scheduling model according to the energy demand in the future time period; and based on a preset energy storage equipment charging and discharging strategy and a preset flexible load control strategy of the target park, generating a multi-resource energy-carbon cooperative flexible control strategy of the target park according to the park multi-resource optimization scheduling model. Therefore, the problem that an existing cooperative control method cannot meet the comprehensive requirements of the modern park in the aspects of energy conservation, carbon reduction, cost optimization and system stability is solved.

The invention relates to the cross technical field of weather forecast and energy prediction, and discloses a physical-data fused weather-wind and light power combined prediction method and system, and the method comprises the steps: constructing an initial combined prediction model, and enabling a weather forecast model and a wind and light power prediction model to be connected into a whole through the model; performing end-to-end training on the initial joint prediction model by adopting a historical meteorological data sample and a historical wind-solar power generation power data sample; and inputting the meteorological data of the target area into the trained joint prediction model, and outputting a wind-solar power generation power prediction value in a future time period. By adopting the end-to-end joint training method based on the differentiable calculation path, global collaborative optimization of the weather forecast model and the wind and light power prediction model is realized, so that the core problem of power prediction misalignment caused by unidirectional transmission and accumulative amplification of the weather model error in the traditional series architecture is solved; and the precision of final power prediction is ensured from the system level.

The invention discloses a distributed photovoltaic user power behavior control scheduling method and system, and the method comprises the steps: deploying an edge controller at a photovoltaic user local device, and collecting power data in real time; a sliding window autoregression model is adopted to carry out short-term load prediction, and an edge controller realizes energy storage state adjustment and load matching balance by constructing an edge node objective function; carrying out constrained quadratic programming solution on the edge node target function, taking a solution result as a node local scheduling strategy, and regularly uploading a current state and a control result to the cloud; the cloud optimization layer collects all edge node state data, constructs a global system state set, and establishes a multi-target joint scheduling model on the cloud optimization layer; and solving and optimizing the multi-target joint scheduling model to generate a global scheduling strategy, and issuing the global scheduling strategy to each edge node. According to the invention, energy prediction and real-time load scheduling are independently executed on the edge side controller on the basis of local data, and the response speed is improved.

The invention discloses an intelligent building integrated control method and system based on cloud computing, relates to the technical field of building integrated control, and adopts an environment sensing module to collect building environment data in real time, ensure the accuracy and timeliness of the data and provide basic data support for intelligent regulation and control. And through the energy prediction and scheduling module, the future power load Ppr and the personnel density Dus are dynamically predicted based on the time sequence prediction model and the regression model, the energy supply is optimized, and the unnecessary energy consumption is reduced. And a user behavior analysis module is adopted to accurately identify the peak period, the equipment use frequency and the energy consumption mode in the building based on the personnel density and the equipment use data, so that the energy waste is reduced. The operation mode of the air conditioner heating and ventilating system is dynamically adjusted, continuous operation of high-power refrigerating or heating equipment in the low-load period is avoided, and therefore unnecessary energy consumption is reduced. Intelligent light adjustment is realized, illumination brightness is adjusted according to personnel activity conditions, and long-term invalid operation of the illumination system is avoided.

The invention discloses an energy prediction management method and system based on a time sequence large model, and relates to the field of energy prediction, and the method comprises the steps: obtaining enterprise energy consumption historical data, environment data and enterprise operation data, and constructing the enterprise energy consumption historical data into a time sequence with the length T according to a time sequence; dividing the time sequence into a plurality of subsequences according to a preset length L, executing attention calculation on the plurality of subsequences through a time sequence large model to obtain association strength among the sequences, and retrieving a plurality of historical fragments most similar to a current energy consumption mode from enterprise energy consumption historical data according to the time sequence large model based on the association strength; generating an energy consumption prediction value of a preset future time period according to the historical fragment, the environment data and the enterprise operation data based on a time sequence large model; and sending the energy consumption prediction value to the target client. By implementing the method, the accuracy of enterprise energy prediction can be improved.

The application discloses a kind of cascade reservoir group scheduling method and system for clean energy consumption, first, obtain the long sequence of the relative error of clean energy each period output and its mean, variance, according to which the output scene set is generated by using clean energy prediction output;Second, a large-scale scene set is reduced to several typical output scenes using clustering algorithm, and then the photovoltaic output process and its occurrence probability of different scenes are obtained;Finally, construct the applicable cascade reservoir group joint scheduling model, and then solve to obtain reasonable and feasible scheduling scheme using efficient optimization algorithm.The method disclosed by the application can quickly respond to the randomness and uncertainty characteristics of the clean energy output process, effectively handle the coupling operation constraints of cascade power stations, significantly improve the model calculation efficiency and scheduling scheme quality, and is suitable for the cascade reservoir group joint scheduling problem for clean energy consumption.

The invention discloses a regional energy demand prediction processing method and electronic equipment. The method comprises the following steps: acquiring historical industrial data corresponding to a target area in a plurality of industrial dimensions; determining multiple groups of influence factor indexes influencing the energy demand; multiple energy prediction scenes are determined, and the multiple energy prediction scenes correspond to different carbon emission strategies; based on the historical industrial data corresponding to the plurality of industrial dimensions and the plurality of groups of influence factor indexes, adopting a long-term energy substitution planning system LEAP model to obtain energy demand prediction results corresponding to the target area in the plurality of energy prediction scenes, the source demand prediction result comprises an electric energy demand prediction result, a natural gas demand prediction result and a cold / heat load demand prediction result. According to the invention, the technical problems of lack of pertinence and low accuracy of energy demand prediction caused by incomplete consideration factors of regional energy demand prediction in related technologies are solved.

This invention discloses a method for predicting energy data in semiconductor factories based on the fusion of multiple time-series models. The method includes: cleaning and defining the features of energy data; selecting and training multiple individual models based on the data characteristics of the processed energy data; selecting a suitable individual model based on scenario discrimination indicators, wherein the scenario discrimination indicators include fluctuation amplitude and seasonal cycle; the fluctuation amplitude is calculated by the standard deviation of the data or the range within a moving window, and the seasonal cycle is obtained by detecting the cycle strength using an autocorrelation function; fusing the prediction results of the selected models; evaluating the fused model and making energy predictions based on the evaluation results. This invention can adaptively select the optimal model, ensuring the accuracy and stability of energy prediction.

The invention discloses an energy-based economic key element linkage prediction method and system, and relates to the technical field of economics and prediction modeling, and the method comprises the steps: determining and collecting a data source, and carrying out the preprocessing of the obtained data; exporting key business data based on the multi-dimensional data model, and constructing an energy consumption data and economic growth prediction model; training an energy consumption data and economic growth prediction model, and performing result evaluation and model optimization; and economic growth and energy prediction are carried out by using the optimized model, and analysis is carried out according to a prediction result and a corresponding decision is provided. By constructing the data cube model, data from different fields can be efficiently integrated, multi-dimensional comprehensive analysis is realized, and the comprehensiveness of the prediction model is improved; according to the method, the optimized model is utilized, a more flexible nonlinear modeling method is adopted, the complex relation between economic growth and energy consumption is better captured, and the prediction accuracy is improved.

The invention discloses an energy system scheduling method and device and a medium, and the method comprises the steps: inputting an energy characteristic parameter corresponding to an energy system into a preset energy prediction model, and outputting a corresponding energy demand prediction result; wherein the energy demand prediction result refers to a confidence interval formed by energy demand prediction values with different confidence degrees under each prediction time step; according to the boundary value of the confidence interval, constructing a power balance constraint relationship of the energy system, and based on the balance constraint relationship, solving a pre-constructed multi-objective optimization function to obtain a plurality of scheduling strategies; and selecting a target scheduling strategy from the plurality of scheduling strategies, and scheduling the energy system through the target scheduling strategy.

According to the virtual power plant-oriented energy storage power station combined regulation and control method and system, historical data of an energy storage power station, a photovoltaic power station and a wind power station are collected, a data set is constructed, and an energy prediction model is established; predicting energy prediction data in a future time period by using the trained energy prediction model; obtaining real-time price and supply and demand data of the electricity market; performing time period division on the data through an extreme random tree model ERT, and distributing real-time electricity price interval labels; combining the data subjected to time period division and label distribution into a scheduling data set; according to the scheduling data set, defining an optimization target, and constructing a virtual power plant multi-energy collaborative scheduling model; energy scheduling constraint conditions are constructed, a scheduling scheme is obtained, control instructions are sent to an energy storage power station, a photovoltaic power station and a wind power station, and real-time control over all energy main bodies is achieved. The power market fluctuation can be responded in real time, the multi-energy collaborative scheduling of the virtual power plant is optimized, the energy configuration efficiency is improved, and the operation cost is reduced.

This invention discloses an energy regulation method and system for virtual power plants based on a predictive model, relating to the field of virtual power plant operation control. The method includes the following steps: collecting energy data from the virtual power plant; integrating wind power data and load data, and extracting features from the integrated data; constructing a preliminary energy dynamic balance prediction model based on predicted generation data of distributed energy sources and predicted demand data of load-side resources; using the preliminary energy dynamic balance prediction model to predict day-ahead load demand and distributed energy; adjusting the operating status of each distributed energy source and load-side resource in real time using the niche gray wolf optimization algorithm according to the preliminary dispatch strategy; dynamically adjusting and optimizing the energy dynamic balance prediction model; and re-predicting load demand and distributed energy using the optimized energy dynamic balance prediction model. This invention can respond to changes in the power system in advance, achieving more efficient energy dispatch.

The invention discloses a factory integrated energy system optimization operation method considering a production network and an energy network. The method comprises the following steps: establishing a carbon emission knowledge graph of each link of the production network and a carbon emission knowledge graph of each device of the energy network through an energy-saving and carbon-reducing intelligent agent fused with a large language model, generating an energy-saving and carbon-reducing diagnosis report, and formulating an energy-saving and carbon-reducing reconstruction scheme; in a current system operation stage, carrying out analogue simulation on the optimal energy-saving and carbon-reducing reconstruction scheme, and respectively establishing energy prediction models of a production network and an energy network; the method comprises the following steps of: sensing energy consumption predicted values, carbon emission intensity predicted values and carbon emission predicted values of a production network and an energy network in each time period in the future through a decision-making agent, and judging whether a high-carbon low-efficiency link / equipment exists or not through an energy demand and a production scheduling plan of the production network in each time period in the future and an energy supply plan and a global carbon emission index of the energy network in each time period in the future; if yes, a system strategy adjustment mechanism is triggered, and a low-carbon economic optimization operation model of the dynamic alliance of the production network and the energy network is established.

This invention relates to the field of energy forecasting technology, and in particular to a method and system for short-term energy load forecasting based on an improved Transformer using SE-Block. The method includes reversible normalization preprocessing of acquired multivariate load sequence data; feature extraction and fusion of the preprocessed data using improved cross-scale interactive patching, including multi-scale feature extraction, cross-scale interactive alignment, residual correction, and dynamic fusion; and feature filtering of the fused features based on a channel attention mechanism, including feature response based on improved SE-Block and nonlinear interaction of context vectors. This invention addresses the non-stationarity of actual load caused by meteorological conditions and user behavior. By automatically eliminating noise interference among multiple variables, the model accurately depicts the fluctuation details of the load curve, demonstrating its robustness in multivariate load forecasting for integrated energy systems.

This invention belongs to the field of energy simulation technology and relates to an energy flow network simulation system and method for steel enterprises. It includes: a system configuration module for configuring parameters based on user-inputted information and forming a structured configuration data package; a front-end operation module for configuring a visual interactive interface based on the configuration data package; generating a Gantt chart based on pre-set production and maintenance plans; and drawing a dynamic energy flow diagram based on user-defined equipment and energy nodes; and a back-end service module for calculating energy prediction results based on the Gantt chart, dynamic energy flow diagram, and configuration data package using a pre-set production and consumption model, and performing scheduling optimization when energy prediction results are unbalanced to obtain an energy scheduling balance result. This invention achieves collaborative simulation of production and energy, more intuitively displays the energy balance process, provides a more comprehensive simulation platform for the steel industry, and facilitates systematic management by enterprises.

The invention discloses a renewable energy consumption capability evaluation method and device, terminal equipment and a storage medium, and belongs to the field of power systems, and the method comprises the steps: obtaining time sequence power grid operation data and time sequence feature description type text data; performing text segmentation on the time sequence feature description type text data to obtain a sub-word sequence; converting each sub-word of the sub-word sequence into a continuous dense vector; performing position coding on each sub-word; combining the continuous dense vectors and the position coding vectors of all the sub-words to obtain word embedding vectors; generating a multi-scale time sequence feature vector according to the time sequence power grid operation data; mapping the multi-scale time sequence feature vector to a space with the same dimension and distribution as the word embedding vector to obtain a numerical value embedding vector; and inputting the word embedding vector and the numerical value embedding vector into a trained renewable energy consumption capability evaluation model to generate a renewable energy prediction consumption amount. According to the invention, the problem of how to evaluate the renewable energy consumption capability can be solved.

The invention discloses a closed-loop optimization regulation and control method and system for an electric power integrated energy system, and the method comprises the steps: building an intelligent prediction-optimization model based on double-layer mixed integer programming, and enabling an upper-layer problem to optimize the parameters of a renewable energy prediction model; the total actual operation cost of the integrated energy system in one or more preset scenes is minimized; according to the predicted value provided by the upper-layer problem, the lower-layer problem solves the day-ahead unit commitment problem to minimize the expected operation cost, and feeds back the optimal unit commitment decision to the upper-layer problem; the method effectively solves the problem that prediction and decision-making targets are disjointed in a traditional'prediction-optimization-first 'framework, and improves the economical efficiency of regulation and control of the comprehensive energy system.

The embodiment of the invention provides an energy storage scheduling method, system and device for an energy storage power station and a storage medium. The method comprises the steps that multiple different types of new energy data are acquired; performing data preprocessing on the multiple different types of new energy data to obtain multiple different types of target new energy data respectively corresponding to the multiple different types; predicting the target new energy data through a predetermined energy prediction model, and determining an energy prediction result; and generating an energy storage scheduling sequence according to the energy prediction result to control switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence, the energy storage scheduling sequence including an input scheduling sequence and an output scheduling sequence. According to the scheme, optimization among different energy sources can be realized, and the stability of the power grid voltage is improved.

The application discloses an energy data management method, system and device of a movable intelligent building cabin, and relates to the technical field of data management. The method comprises the following steps: deploying a sensor network on the movable intelligent building cabin, collecting energy data, environmental data and user behavior data in real time, and performing correlation fusion to generate an energy real-time state vector; constructing an energy output prediction model and an energy demand prediction model; performing energy prediction on the energy real-time state vector in a preset time window to obtain energy output prediction parameters and energy demand prediction parameters; performing energy regulation analysis on the energy output prediction parameters and the energy demand prediction parameters to determine target energy regulation strategy parameters, and performing dynamic management on energy data. The technical problems that the prior art is difficult to dynamically adapt to changes in the energy demand of the movable building cabin, resulting in energy waste and supply-demand mismatch are solved, the technical effect of intelligently regulating the energy management strategy and improving the energy supply-demand matching degree is achieved.

The invention discloses a wind power prediction method, system, equipment and medium considering a prediction error weighting and gating output mechanism, and belongs to the technical field of power system new energy prediction, and the method comprises the steps: constructing a wind power prediction model, collecting wind power prediction data, and decomposing the wind power prediction data based on the wind power prediction model; performing weighted correction on a decomposition result according to a historical power prediction error sequence; performing feature extraction on the corrected decomposition results, and analyzing a mutual influence rule between the decomposition results; and constructing a multi-quantile prediction structure, predicting quantile values of all wind power probability distributions at the same time, and forming a time sequence prediction result of a wind power change interval. According to the method, more information is provided for the prediction model by comprehensively considering the correlation between the historical prediction error and the historical power, and the performance of the model is improved.

The invention discloses an active power and reactive power coordination method for an active power distribution network containing an intelligent soft switch and considering voltage stability constraint, relates to the field of power distribution networks, and constructs a flexible interconnected power grid containing the intelligent soft switch by comprehensively considering an active power distribution system structure and day-ahead load and renewable energy prediction information. And based on the flexible interconnected power grid model and the voltage stability constraint, establishing an active and reactive power coordination model of the active power distribution network containing the intelligent soft switch considering the voltage stability constraint, and based on a solving strategy of the active and reactive power coordination model of the active power distribution network containing the intelligent soft switch and an improved continuation power flow method, calculating the voltage stability margin of the system. The stable voltage constraint of the power distribution system in the regulation and control process is ensured, the optimal regulation and control strategy is obtained, and the safety of the optimized operation of the power distribution system containing the intelligent soft switch considering the voltage constraint can be effectively improved.

The embodiment of the invention provides an energy prediction method and device, and the method comprises the steps: obtaining an energy consumption feature corresponding to a current level in a plurality of levels; inputting the input data corresponding to the current hierarchy into the intelligent agent of the current hierarchy to obtain an energy consumption prediction result corresponding to the current hierarchy, the input data corresponding to the current hierarchy being an energy consumption feature corresponding to the current hierarchy under the condition that the current hierarchy is the lowest hierarchy in the plurality of hierarchy, and the energy consumption feature corresponding to the current hierarchy being an energy consumption feature corresponding to the current hierarchy; under the condition that the current hierarchy is not the lowest hierarchy in the plurality of hierarchies, the input data of the current hierarchy comprises an energy consumption prediction feature corresponding to the current hierarchy and an energy consumption feature corresponding to the current hierarchy, the energy consumption prediction result corresponding to the highest level is used for adjusting the energy use strategy of the energy consumption area corresponding to the highest level. According to the invention, the problem of low energy prediction precision in the prior art is solved.

The present application relates to the technical field of energy security, and more particularly to a power distribution network elasticity improvement and joint optimization scheduling of repair personnel scheduling method and system, comprising: obtaining active power distribution network topology parameters, diesel generator and energy storage device parameters, renewable energy predicted output and load curve and numerical value; the post-disaster recovery model of active power distribution network is constructed in the guidance of elasticity, the adjustment strategy of distributed power generation resources is determined based on the topology reconstruction and island segmentation strategy method; the optimization scheduling model of repair personnel and network reconstruction coordination is constructed in the guidance of elasticity, and the second order cone relaxation method is used for relaxation processing to determine the fault repair strategy; through the active power distribution network topology parameters, the adjustable resource parameters and the renewable energy predicted output, the optimization problem is reconstructed based on the active power distribution network fault scene under the disaster; the optimization problem is solved with the minimum fault economic loss as the target, and the active power distribution network topology structure and the fault repair strategy are obtained.

The invention discloses a hydrogen production and energy supply simulation method and system, and relates to the technical field of hydrogen production, and the method comprises the steps: generating energy input information in an energy supply simulation system; calibrating the future energy prediction information according to the real-time energy output information to obtain calibrated energy prediction information; acquiring operation state information and hydrogen demand information of hydrogen production equipment in the energy supply simulation system; determining power distribution of the hydrogen production equipment; operating parameters of the hydrogen production equipment are adjusted according to the power distribution, the hydrogen production target and the hydrogen storage state; the operation state information of the energy supply simulation system is presented, and the operation process information of the energy supply simulation system is recorded. Optimized operation of the hydrogen production and energy supply system can be achieved, the efficiency, stability and reliability of the system are remarkably improved, and the actual operation risk is reduced.

In one example, a system can receive an input from a user indicating a target variable to be forecasted over a future time window. The system can then determine independent variables that influence the target variable and generate a set of candidate variables, including combinations of the independent variables. The system can then execute a random forest classifier to identify a subset of candidate variables having a threshold level of influence on the target variable. The system can then construct a machine-learning model configured to receive the identified subset of candidate variables as inputs and generate a forecast of the target variable. After constructing the machine-learning model, the system can train the machine-learning model using historical data and then execute the machine-learning model to generate the forecast.

The invention discloses a digital native model energy prediction method and system of a physically-driven computing power center. The method comprises the steps of obtaining time sequence mass flow, temperature data and geometric physical parameters required by operation of the cold storage tank, and setting prior information such as an initial to-be-identified parameter set and a flow direction to obtain input data and parameters; on the basis of energy conservation, constructing a layered ordinary differential equation model for describing the temperature change of each layer by using the input data and the parameters; using an adaptive step ODE solver to predict temperature distribution of each layer at each time point based on the hierarchical ordinary differential equation model according to input data and parameters so as to obtain predicted temperature; constructing a loss function by comparing the predicted temperature with an actual measurement value; a gradient is calculated based on the loss function, and parameters are adjusted by an optimization algorithm to minimize the loss function. By implementing the method provided by the invention, the model dimension can be reduced and the calculation can be simplified while the main physical mechanism is reserved.