27 results about "Electricity price forecasting" patented technology

This application discloses a method, apparatus, equipment, and medium for day-ahead nodal electricity price forecasting and correction based on price state grouping and gating correction, relating to the field of electricity price forecasting technology. The method includes: constructing a training sample window using historical market operation characteristic data; classifying price states according to historical clearing prices to generate price state labels; training a model within the training sample window to obtain a global forecasting model and a price state sub-forecasting model; performing offline initial forecasting of day-ahead nodal electricity prices using the global forecasting model, and correcting the initial price forecasting result by calling the corresponding sub-forecasting model according to the corresponding price state; if a forecast value meets a preset gating condition, further determining whether it meets a preset zero-price condition; if so, performing gating correction to obtain the final electricity price forecasting result. This application can improve the targeting and accuracy of day-ahead nodal electricity price forecasting under different price states, and enhance the ability to identify and correct special price states such as zero-price.

Embodiments of the present application provide a power price prediction method, device, equipment, storage medium and program product. The power price prediction method comprises the following steps: obtaining power grid transaction data, a first power price corresponding to N time points in a first time period, and a second power price corresponding to a second time period; performing data integration processing on the power grid transaction data, the first power price, and the second power price according to the N time points to obtain a time series data set, wherein the time series data set comprises the power grid transaction data, the first power price, and the second power price corresponding to each time point; and predicting the power price corresponding to the N time points in the second time period based on the time series data set and a power price prediction model to obtain a predicted power price corresponding to each time point in the second time period. The method integrates power grid data according to time sequence characteristics to obtain a time series data set, and improves the accuracy of power price prediction and the prediction ability of long-period power prices based on the dependence relationship between historical power prices and current power prices in the time series data set.

The application provides a kind of integrated demand response method and system based on user behavior coupling modeling, it is related to energy management technical field.The application obtains and pre-processes the historical data of city integrated energy system;Through the historical data after pre-processing and long short-term memory neural network, obtain UIES demand prediction model, predict multiple load prediction data and electricity price prediction data through UIES demand prediction model;Based on historical data, predicted multiple load prediction data and electricity price prediction data determine model parameters, build IB-IDR income model;Based on IB-IDR overall income model, according to multi-agent theory, adopt adaptive method to solve optimal IB-IDR strategy for each energy subsystem.The application can overcome the uncertainty of UIES demand side, realize more accurate, integrated IB-IDR incentive strategy for each consumer to obtain more demand response resources, promote UEIS supply and demand balance.

This invention discloses a control method and system for an electric thermal energy storage system based on multi-timescale rolling time-domain optimization and price confidence, comprising the following steps: based on the electricity spot market forecast data, outputting the expected value of electricity price forecast for each discrete time period and the upper and lower boundaries of the electricity price confidence interval through a price forecast model; establishing a coupled model of the electric thermal system including a heat source, a thermal storage device, and a heat load; constructing a conservative equivalent electricity price for optimized scheduling, and establishing an optimization problem with the goal of minimizing the total operating cost of the system; generating and executing control commands using a two-timescale hierarchical rolling time-domain optimization: solving for a benchmark heat production and thermal storage plan covering a preset daily cycle at the first time scale, updating the electricity price forecast and the actual state of the thermal storage device at the second time scale, and resolving the optimization problem within a rolling window, and executing control commands only for the current time period control step.

This disclosure relates to the field of power system technology, and discloses a method and apparatus for joint prediction of electricity price, source, and load for integrated energy systems. The method involves processing heterogeneous load-side data and operating condition information to obtain dynamic conversion coefficients corresponding to various load types; constructing an energy layer representation based on heterogeneous source-side data, dynamic conversion coefficients for various load types, heterogeneous load-side data, and operating condition information over a specified time period; constructing a market layer representation based on electricity price information and operating condition information over a specified time period; processing the energy layer and market layer representations using a bidirectional coupling unit to obtain a cross-layer coupled representation; and using a multi-task sequence prediction decoder to perform prediction processing on the cross-layer coupled representation and combining it with real-time rolling cycle information for correction to obtain a prediction set, which includes predicted electricity price information, predicted source output information, and predicted equivalent load information. This significantly improves the accuracy of electricity price prediction, energy output prediction, and energy consumption prediction.

This invention discloses a method and system for controlling air-cooled units driven by dynamic peak-shaving additional energy consumption, belonging to the technical fields of thermal power flexibility regulation and electricity market. The method includes: real-time acquisition of operating parameters of the air-cooled extraction steam unit to form a basic parameter set; decomposition of the real-time thermoelectric decoupling load into steady-state thermoelectric decoupling loss, back-pressure extraction steam coupling loss, and pure back-pressure loss, and calculation of dynamic peak-shaving additional energy consumption indicators based on the decomposition results; generation of unit load regulation targets by combining coal price and electricity price forecast information; real-time monitoring of unit safety parameters and calculation of safety deviations; correction of the air-cooled back-pressure change rate based on the safety deviations; and output of air-cooled louver opening and circulating water distribution regulation commands based on the corrected air-cooled back-pressure change rate. This invention can integrate the dynamic impact of air-cooling flexibility on the marginal cost of peak shaving, providing relatively real-time and reasonable data support for unit regulation under the electricity spot market, and has certain engineering applicability.

A method and system for constructing a time-series attention model for electricity prices that integrates grid congestion information is disclosed. The method includes: collecting grid state, market state, and electricity price data, and constructing a dataset using window partitioning; building a grid congestion detection and vector fusion module to determine grid congestion status and generate congestion state feature vectors, fusing these feature vectors with grid state vectors and market state vectors to form exogenous variables; constructing a time-series attention network to perform feature mapping on exogenous variables, embedding vectors into endogenous and exogenous variables, and obtaining electricity price prediction results after fusion using a dual attention mechanism; training and validating the grid congestion detection and vector fusion module and the time-series attention network; and testing the grid congestion detection and vector fusion module and the time-series attention network validated in step 4 using a test set. This invention can improve the accuracy and stability of electricity price prediction under complex operating scenarios.

This invention discloses a structured decomposition loss function design method for electricity spot market price forecasting, comprising the following steps: S1: Obtaining a training sample set; S2: Constructing an electricity price forecasting model to be optimized based on the training sample set; S3: Obtaining trend components, periodic components, and peak impact components; S4: Calculating the supervised loss terms for the corresponding components obtained in S3; S5: Constructing the total loss function for model training; S6: Iteratively training the electricity price forecasting model based on the total loss function; S7: Outputting the forecast date price, the forecast real-time price, and their price difference for the operating day. The advantages of this invention compared to existing technologies are: providing a structured decomposition loss function design method for electricity spot market price forecasting that effectively improves the fitting ability of the electricity price forecasting model to medium- and long-term trends, peak-valley structures, and sudden peak events, thereby improving the stability and robustness of the forecast results.

This invention relates to the field of power system data analysis and energy management technology, specifically to a system and method for real-time data acquisition and forecasting of electricity user energy consumption. It collects multi-source heterogeneous data from the user side in real time, and after standardization, cleaning, and time-series alignment, fuses the data based on a unified data model to construct a correlated data cube. This allows for the construction and dynamic updating of digital twin models for electricity users, simulating their electricity consumption characteristics and market behavior. A multi-timescale collaborative forecasting mechanism is activated to generate short-term, medium-term, and long-term electricity demand and electricity market price forecasts, and to formulate trading strategies accordingly. By feeding back actual transaction and market data, the model parameters and forecasting strategies are continuously optimized. This effectively solves the problem of limited accuracy in energy consumption and market forecasting caused by insufficient fusion of multi-source heterogeneous data and lack of collaborative analysis, significantly improving the accuracy of load and electricity price forecasts.

This application discloses an electricity price prediction method, apparatus, non-volatile storage medium, and electronic device. The method includes: acquiring an input dataset, which includes historical electricity price data, meteorological data, boundary condition data of the target power system, and time-series feature data; preprocessing the data in the input dataset; and processing the preprocessed input dataset using a prediction model to obtain the predicted electricity price for the target time period. The prediction model includes multiple mixing layers, each including a time mixing module and a feature mixing module. The time mixing module determines the temporal dependencies of the data input into the prediction model, and the feature mixing module determines the relationships between the data input into the prediction model. This application solves the technical problems of low prediction efficiency and slow result updates caused by the large amount of computational resources and long prediction training time required by existing prediction techniques.

The present application relates to the technical field of power system operation control, and discloses a wind-solar combined electricity price prediction method, device, equipment and medium, the present application divides the weather state type into extreme weather type and non-extreme weather type, and inputs the classification result into a mixed prediction model together with wind-solar weather data, so that the model can adaptively adjust its parameters according to the weather state type, thereby automatically switching the most suitable prediction strategy when extreme weather and normal weather appear alternately, avoiding the problem of uneven prediction ability of fixed model architecture under different weather scenes, improving the accuracy and stability of electricity price prediction under complex weather conditions, and providing a more reliable decision basis for power system operation control.

This invention belongs to the field of power system operation and market transaction technology, specifically relating to a method and system for electricity price prediction based on clustering and hybrid modeling. It involves acquiring historical electricity price data, initially classifying it into weekdays, weekends, etc., and labeling it according to public calendar rules; constructing a daily electricity price pattern sample set by filtering the data for the dates to be predicted, and generating labels through K-means clustering; training a clustering predictor using the initial classification and weekday features; constructing a separate hybrid model based on the clustering labels, matching the corresponding model according to the attributes of the dates to be predicted, extracting features, and outputting predicted values.

The application discloses an enhanced model day-ahead electricity price prediction method based on dynamic feature selection, which extracts features from the original data set through a multi-head attention mechanism for multidimensional correlation analysis, generates a feature weight vector in real time to realize dynamic screening of the optimal feature subset, thereby suppressing redundant information and nonlinear noise features at the source; then, an enhanced XGBoost model is used to deeply mine the structured relationship of power market data, simultaneously combined with a Transformer model to capture the long-range time series dependence characteristics of the electricity price sequence, and through a gating mechanism to perform dynamic weighted fusion, to realize the complementary integration of spatial features and time series features; finally, a multi-objective Bayesian optimization algorithm is introduced to obtain a trained enhanced model through multi-objective collaborative optimization, and then prediction is performed. The application significantly improves the prediction accuracy and robustness, effectively solves the deployment problem of the model in a resource-limited environment, and has high engineering application value and power market prediction practicality.

The application discloses a kind of based on dynamic electricity price prediction energy storage system optimization scheduling method and system, it is related to energy storage system optimization scheduling technical field.The application is by constructing multi-resolution electricity price prediction model, and collects electric power market historical price data, utilizes the model to predict the electricity price of future time and identifies price peak;The charge-discharge scheduling process of post-listing energy storage system is modeled, and the optimization scheduling function with the maximum operation income as target is constructed and solved using rolling time domain method;According to the optimal charge-discharge strategy obtained by solving, the energy storage system is scheduled.The application improves the prediction accuracy of electricity price, especially price peak, through multi-resolution prediction model, and combined with rolling time domain optimization, constructs the scheduling strategy with the maximum economic benefit as target, obtains the optimal charge-discharge strategy of future time, significantly improves the profit of energy storage system, reduces the economic loss caused by wrong decision.

This invention belongs to the field of load forecasting, and specifically relates to an automatic optimization method and system for electricity spot trading strategies. It includes: a data acquisition and processing module for acquiring and preprocessing multi-source time-series data; an electricity price forecasting module for inputting high-dimensional feature vectors into an electricity price forecasting model and outputting high-dimensional electricity price forecast vectors for future scheduling cycles; a strategy generation module for inputting high-dimensional electricity price forecast vectors into a strategy generation model and outputting a trading strategy parameter set; and an adaptive calibration module for online calibration of the electricity price forecasting model according to a preset calibration strategy. The preset calibration strategy involves real-time monitoring of the moving average of the high-dimensional electricity price forecasting error and the statistical drift index of the data distribution. When the error threshold is exceeded or the drift exceeds a preset confidence interval, an incremental parameter update mechanism is triggered. This invention solves the problem in existing technologies where static forecasting models cannot adapt to the non-stationary environment of the power system, leading to a decrease in forecast accuracy and consequently, strategy failure.

The application belongs to the technical field of electricity price prediction, and discloses a method for electricity price sequence reconstruction and prediction based on a large language model, which comprises the following steps: obtaining and preprocessing the electricity price time sequence of a target electricity market, constructing a missing identification matrix and a missing pattern coding matrix; extracting dynamic prior features; constructing joint input features, extracting forward time features and backward time features through a pre-trained large language model, performing confidence assessment, generating bidirectional fusion features, and obtaining a complete electricity price time sequence after missing value filling; dividing the complete electricity price time sequence into multiple patches according to a preset time window and performing patch reprogramming; constructing a prompt prefix to form a unified sequence representation; inputting the unified sequence representation into the pre-trained large language model to perform forward reasoning, linear projection and inverse normalization processing, and obtaining electricity price prediction results at multiple future time points. The application can effectively fill in missing values and accurately predict electricity prices.

The application belongs to the technical field of prediction, and provides an energy storage transaction auxiliary decision-making method and system for planning-year-scale electricity price prediction, generates a full-year meteorological resource sequence; based on multi-dimensional data of power transaction, adopts a long short-term memory neural network to respectively construct a day-ahead / real-time electricity price prediction model, and performs confidence evaluation; identifies abnormal samples from a historical electricity price sequence and extracts corresponding features, realizes abnormal electricity price prediction by using a Transformer model, and performs weighted fusion on prediction results of the long short-term memory neural network and the Transformer model in an abnormal period to generate a corrected electricity price prediction value; establishes an optimization decision-making model with maximization of daily revenue of independent energy storage operation as a target, embeds multiple constraints, and obtains an optimal day-ahead market charging and discharging output price curve to assist independent energy storage transaction. The application can realize generation of an optimal transaction auxiliary strategy of independent energy storage under a planning-year scale.

The present invention relates to the technical field of hydrogen-blended gas unit control. Specifically disclosed are a hydrogen-blended gas unit control system and method based on spot market trading. The system comprises: a demand calculation module, which is used for acquiring historical unit operation data, and determining a unit load demand value of the current gas unit on the basis of the historical unit operation data; a supply calculation module, which is used for acquiring wind and solar condition data, and determining a wind and solar supply value on the basis of the wind and solar condition data; and a hydrogen-blending control module, which is used for predicting a unit electricity price on the basis of the unit load demand value of the current gas unit and the wind and solar supply value, determining a hydrogen-blending ratio of the gas unit on the basis of the obtained predicted electricity price, and performing hydrogen-blending control on the gas unit on the basis of the hydrogen-blending ratio of the gas unit. By means of the present invention, a unit electricity price is predicted in view of wind and solar condition data, and hydrogen-blending control is performed on a gas unit on the basis of an electricity price prediction result, thereby effectively improving the operation economy of the gas unit.

This invention provides a method and system for optimizing multi-source coordinated charging and discharging strategies for energy storage systems. The method includes: predicting electricity prices based on acquired multi-source historical data to obtain predicted electricity prices; outputting an optimized load curve with the objective of minimizing the weighted sum of maximum demand power and electricity cost within a scheduling cycle; using the optimized load curve as a consumption benchmark, determining the existence of curtailment risk and identifying a dynamic operating range when the predicted photovoltaic power generation exceeds the sum of the consumption benchmark and the current rechargeable capacity of the energy storage system; constructing a scheduling curve model based on the predicted electricity prices to maximize net revenue; constructing constraints for the scheduling curve model based on the optimized load curve and the dynamic operating range; and solving the scheduling curve model based on the constraints to obtain a charging and discharging scheduling curve and control the operation of the energy storage system. This invention improves energy utilization efficiency and reduces electricity costs.

The application discloses a kind of virtual power plant multi-agent collaborative regulation method and system, belong to electric power regulation technical field.The method includes: S1.carries out multi-scale load prediction and exports prediction result;S2.carries out chaos-depth learning coupling electricity price prediction and exports prediction result;S3.based on the prediction result of S1 and S2 carries out resource optimization scheduling;Subscale model includes LSTM submodel, GRU submodel and entropy weight dynamic fusion model, respectively carries out long-term prediction, short-term prediction and long-short term prediction result fusion;The content of S2 includes: S21.chaotic characteristic identification;S22.phase space reconstruction;S23.LSTM model prediction;The content of S3 includes: S31.regional level-station level-equipment level three-level agent architecture is built;S32.objective function and constraint setting;S33.closed-loop collaborative scheduling.The application can realize global optimization and guarantee the collaborative regulation of local autonomy.

The application relates to the technical field of data center energy management and power dispatching, and discloses a double-layer dispatching method, system, equipment and medium for data center load and energy storage collaborative optimization. The method comprises the following steps: collecting data center operation data and preprocessing, constructing a prediction model to obtain load and electricity price prediction data; formulating a day-ahead dispatching scheme based on the prediction data, solving a first optimization model, and generating a first dispatching instruction; executing the first dispatching instruction and monitoring the actual deviation, and if the actual deviation exceeds a threshold value, starting a second optimization model for real-time correction to obtain a second dispatching instruction; performing safety inspection on the charging and discharging power of the energy storage, and feeding back the safety state to the optimization model to form a closed-loop control; and based on the safety inspection result, starting and stopping the dispatching server and allocating the calculation tasks. The double-layer dispatching architecture combining day-ahead optimization and real-time correction is adopted, the electric-computing-storage collaborative optimization is realized, the operation cost is reduced, the renewable energy consumption capacity is improved, and the real-time response and safety operation level of the system are enhanced.

This application relates to a method, device, and storage medium for generating an electricity consumption control strategy. The method includes acquiring historical electricity price data and electricity price factor data of the electricity user, wherein the electricity price factor data represents factors affecting electricity price fluctuations; using the historical electricity price data and electricity price factor data as sample data to train an electricity price prediction model, wherein the electricity price prediction model is obtained through iterative training of multiple sub-models; predicting a target electricity price within a predetermined time period using the electricity price prediction model; and generating an electricity consumption control strategy based on the target electricity price. This application can sense future electricity price data or electricity price trends, and then generate corresponding electricity consumption control strategies based on the target electricity price. The electricity user can select the corresponding electricity consumption control strategy according to the electricity price fluctuations, thereby achieving the goal of saving electricity costs.

This invention discloses a pricing method for computing power services based on resource stress prediction and electricity price prediction, belonging to the field of cloud computing and data center operation and management technology. The method includes the following steps: Step S1. Establishing a multi-timescale computing power resource stress prediction model; Step S2. Constructing an opportunity cost mapping and comprehensive cost calculation model based on resource stress; Step S3. Constructing a differentiated pricing model and outputting the computing power service price. This method integrates long-term basic load, medium-term planned load, and short-term elastic load into a tiered occupancy ratio model, and corrects them respectively through planned execution correction coefficients, seasonal factors, special event factors, industry characteristic factors, and acceptable delay correction coefficients. Compared with existing technologies, it can more accurately reflect the actual occupancy status and dynamic changes of computing power resources. This invention can also improve the rationality and stability of the pricing mechanism, and is more conducive to the market-oriented trading and packaged delivery of computing power services.

This invention discloses a method, equipment, and storage medium for long-term electricity price forecasting in the electricity spot market. The method includes: extracting and preprocessing features from multi-source basic data to construct a generator set result set; calculating the relative output depth operator of the generator sets based on the generator set result set, and then calculating the weighted average output depth of the entire system; calculating the nonlinear price mapping operator based on the weighted average output depth of the entire system and the system supply and demand factors calculated from the generator set result set, and obtaining a preliminary predicted electricity price based on the nonlinear price mapping operator; and obtaining a full-year electricity price forecast sequence based on the preliminary predicted electricity price. By defining and applying the relative output depth operator, it is possible to reverse-engineer the bidding game psychology and strategy shift characteristics of power generation entities at different operating depths without accessing commercial privacy data such as competitors' bid prices, by utilizing publicly available generator physical characteristics.