1771 results about "Power load" patented technology

Disclosed in the present invention are a fuzzy-logic-control-based coordination method and system for a power grid requirement response and an energy storage system, the method comprising: S1, collecting real-time power grid data and prediction data, and constructing a corresponding real-time power grid data set and a corresponding prediction data set; S2, using a fuzzy algorithm to convert the real-time power grid data set, the prediction data set and multi-dimensional renewable energy information into a fuzzy set; S3, customizing a power grid requirement response measure and an operation strategy of an energy storage system; S4, executing the strategy customized in step S3; S5, monitoring in real time the execution effect of the strategy and collecting operation data such as a power grid load matching degree, energy storage device response speed and efficiency, and a requirement response participation degree; and S6, periodically updating a decision model of a fuzzy logic controller. In the present invention, the fuzzy logic controller is used to process and analyze power grid data in real time, such that the uncertainty and ambiguity during power grid operation can be effectively handled, especially for the production capacity fluctuation of renewable energy and the rapid changes of power loads.

The invention relates to an electrical load prediction and optimization regulation and control method and system for high-energy-consumption equipment, and solves the problems of inaccurate load prediction, single regulation and control means and difficulty in dynamic adaptation of the high-energy-consumption equipment, and the method comprises the steps: collecting multi-source data of the high-energy-consumption equipment in real time, constructing a dynamic equipment collaborative causal graph after preprocessing, and extracting key constraints; inputting the data and the constraints into the dynamic digital sample model to obtain a system state simulation result; based on the result, a multi-objective optimization regulation and control strategy is generated and executed by using a meta-learning + reinforcement learning decision framework; and collecting actual data comparison deviation, starting hierarchical federated learning when a threshold value is exceeded, grouping and aggregating similar experiences according to a causal graph topology, and dynamically calibrating model parameters and a decision framework. The method has the following effects that accurate load prediction and multi-target cooperative regulation and control of the high-energy-consumption equipment are achieved, working condition changes are dynamically adapted, the cost is reduced, and continuous production and the service life of the equipment are guaranteed.

The invention relates to the technical field of power data processing, in particular to an energy storage configuration optimization method, which comprises the following steps: acquiring new energy output time sequence data and computing power load characteristic data; generating a space-time correlation coupling evaluation result of the new energy output volatility and the computing power load volatility; inputting a result into a hybrid power supply double-layer optimization model, recursively correcting parameters through a two-stage collaborative solution algorithm, and outputting a Pareto optimal solution set; a computing power task elastic regulation and control mechanism is embedded, and the task priority is dynamically adjusted according to the energy storage charge state and the new energy output level to generate a scheduling strategy; finally, an energy storage configuration scheme and a dynamic scheduling strategy are output, and collaborative optimization of cost effectiveness and power supply reliability is achieved. The method breaks through the coupling conflict of the economic target and the robust constraint in the traditional bilevel planning, remarkably reduces the energy storage configuration cost, and improves the system stability.

The invention discloses a power grid power load intelligent prediction method, system and device and a medium, and relates to the technical field of power distribution network transmission optimization. Power load data is decomposed into a trend component, a periodic component and a random fluctuation component, and then the importance of different components is evaluated by using a feature channel attention layer; the time sequence attention layer captures key moments in each component time sequence and extracts features at the key moments, and then the features extracted based on the importance and the features extracted at the key moments are fused, so that the multi-scale features of the power load are captured; and then inputting the fused features into the dynamic gating residual connection LSTM network for prediction, and in the prediction process, improving the attention degrees of long-term sequences, short-term sequences and fluctuation sequences in different features through a residual modulation function, thereby more accurately capturing the multi-scale features of the power load and obtaining a prediction value of the power load.

The invention relates to the technical field of industrial equipment temperature control, and discloses a temperature control system, which comprises a multi-source state sensing module for acquiring a power load, temperature, humidity and feedback temperature; the feed-forward prediction and analysis module is used for generating a feed-forward signal based on the load and the temperature; the closed-loop feedback and safety guarantee module is used for calculating a feedback signal according to the temperature deviation; the cooperative control decision module combines the feed-forward signal and the feedback signal to generate a fan instruction, and generates a baffle instruction for balancing heat dissipation and regeneration according to the feed-forward signal and humidity; the self-adaptive heat dissipation execution module is used for executing a fan instruction to generate cooling airflow; and the dynamic energy regeneration module executes a baffle instruction to distribute the waste gas flow direction. According to the method, the power load is introduced to serve as a prospective index, correction is conducted in combination with the environment temperature, a predictive heat dissipation control model is constructed, the system can start heat dissipation adjustment before a large amount of heat is generated, and therefore smooth and stable control over the equipment temperature is achieved.

The invention discloses an electricity utilization information acquisition intelligent configuration method based on a pattern recognition algorithm, and relates to the technical field of intelligent power grids, and the method comprises the steps: collecting a directional data stream, inputting a federal map neural network to construct a power distribution network physical connection relation, and generating a spatio-temporal topological feature vector; extracting a current effective value component of the directional data flow as an electrical load sequence, extracting an equipment state code to identify a voltage sag event, injecting voltage sag event associated disturbance into the electrical load sequence in combination with an event propagation path weight of a spatio-temporal topological feature vector, and generating an anti-fact sample set; and compressing the new configuration strategy through a knowledge distillation engine, and outputting an event response logic and a parameter adjustment instruction to form an executable configuration strategy. According to the method, through anti-fact sample generation and reinforcement learning optimization under spatial-temporal topological feature vector constraint, a physical rule deep embedding decision is realized.

The invention relates to the technical field of power load decomposition, and discloses a non-intrusive power load decomposition method and system based on multi-modal feature learning. The method comprises the following steps: synchronously acquiring electric power parameter data of an intelligent electric meter, environmental parameter data of an environmental sensor and use behavior data of user equipment to obtain multi-modal load monitoring data; performing cross-modal feature extraction through a non-negative matrix factorization layer of the first equipment state recognition model to obtain a multi-modal fusion feature vector; carrying out load mode recognition through a first decomposition layer of the first equipment state recognition model to obtain a first decomposition load matrix; performing clustering optimization through a second decomposition layer of the first equipment state recognition model to obtain a second load decomposition matrix; and executing a dynamic fuzzy decision based on the second load decomposition matrix to obtain an equipment operation state identification result. According to the method, the limitation that a traditional method only depends on a single power signal is broken through, and high-precision and high-robustness non-intrusive power load decomposition is achieved.

The invention discloses an intelligent computing center automatic operation and maintenance management method based on computing power resource allocation, and relates to the technical field of resource management, and the method comprises the steps: obtaining real-time computing power load data and a to-be-processed task queue of an intelligent computing center; constructing a resource state matrix according to the real-time computing power load data, performing historical data backtracking analysis on the resource state matrix by using a sliding window algorithm, and calculating a resource load predicted value and a resource availability score of each computing node; based on the resource availability score, an improved genetic algorithm is adopted to carry out optimal allocation solution on the constructed task-resource matching matrix, and an optimal task allocation scheme is generated; and converting the optimal task allocation scheme into a resource allocation instruction set, sending the resource allocation instruction set to each target computing node to execute task scheduling, and updating the resource occupation state of the corresponding node in the task-resource matching matrix. According to the invention, the technical jump from passive response type management to active prediction type management is realized, and the resource configuration efficiency of an intelligent computing center is improved.

The invention discloses a morning orbit computing power satellite, and belongs to the field of aerospace technology and space infrastructure. The satellite comprises a satellite platform and a computing force load arranged on the satellite platform. The satellite platform is provided with a condensation type energy system and a space pump drive fluid loop system. The condensation type energy system adopts an expandable condensation type solar cell array to generate power, switches a power supply mode according to an illumination period and an earth shadow period of a morning and night orbit, and supplies power to computing force loads and platform equipment. The space pump drive fluid loop system adopts an expandable flexible radiation cooling plate for heat dissipation, heat dissipation is conducted on computing force loads through a fluid loop, and a heating assembly is arranged to prevent a working medium from being frozen under the low-temperature working condition. Through the expandable structure and the orbit environment adaptability design, continuous energy supply and effective heat management are provided for the computing power load in the morning and night orbit environment, and high-power-consumption computing power load in-orbit stable operation is supported.

The invention provides a power load prediction method and device, and belongs to the technical field of power load prediction.The method comprises the steps that current waveform data are obtained, and fundamental wave and harmonic components in the current waveform data are extracted; carrying out waveform spatial form geometric analysis to obtain a real-time load characteristic sequence, and then carrying out segmentation processing; the current effective value sequence of each time window is converted into a time-frequency domain energy distribution vector, and then a three-level feature library is constructed; constructing a three-dimensional tensor model through equipment start-stop event identification, inputting the three-dimensional tensor model into a multi-target optimizer to evolve feature weights, and filtering abnormal samples to obtain a feature cluster; performing random masking processing on the time sequence data of the feature cluster to generate a mask sequence, inputting the mask sequence into an encoder to reconstruct masking data, comparing, learning and judging abnormal output correction data, and inputting the corrected data into a prediction network to generate a feedback signal flow; and analyzing the feedback signal flow to update the prediction network weight. Based on the method, the invention also provides power load prediction equipment. According to the invention, the precision of power load prediction is obviously improved.

The invention provides an energy storage power station optimization operation mode decision-making method and system, and relates to the technical field of energy storage power station optimizing.A hybrid prediction model is constructed to realize high-precision decomposition prediction of power load, and meanwhile, the internal resistance of a battery is estimated in real time by adopting a recursive least square method; and the battery capacity and internal resistance parameters are dynamically corrected in combination with a temperature compensation mechanism. Through health state multi-index fusion evaluation, self-adaptive distribution of charging and discharging power is achieved, and compared with the prior art, the problem that a traditional static model cannot adapt to complex environment changes is solved. The battery capacity fading risk can be predicted in advance by introducing a double-compensation mechanism of an environmental influence index and an electric power influence index. According to the scheme, the response speed and economical efficiency of energy storage in a high fluctuation load scene are remarkably improved, and a reliable dynamic optimization decision support system is provided.

The invention belongs to the technical field of intelligent energy and power system automatic control, and particularly relates to a cross-level collaborative regulation and control system integrating meteorological prediction, power market and equipment state, which comprises a central collaborative controller, a data acquisition unit, a communication network and an execution terminal, the data acquisition unit is used for acquiring meteorological data, power load data, electric energy consumption cost data and equipment operation state data in real time; the execution terminal at least comprises a photovoltaic inverter, an energy storage converter and a charging pile controller; the central cooperative controller is configured to execute three cooperative optimization closed loops, namely, a data fusion and prediction closed loop, a multi-target dynamic optimization closed loop and a multi-time scale control closed loop. According to the system and the method provided by the invention, the problems of real-time performance and accuracy of multi-source heterogeneous data fusion are solved; the balance optimization bottleneck of multiple targets such as economy, stability and environmental protection in the dynamic process is broken through; full-time-scale seamless cooperative control from second-level emergency response to hour-level economic dispatching is realized; and the self-adaptive capability and the overall performance of the system in different application scenes are improved.

The invention discloses a power grid photovoltaic output and load sequence modeling method, system and device and a storage medium, and the method comprises the steps: comprehensively utilizing the multi-scale feature extraction capability of a time-frequency decomposition technology, the time sequence dependence modeling capability of a long and short-term memory network, and the global hyper-parameter optimization capability of a Bayesian optimization algorithm; and carrying out collaborative modeling and prediction on the photovoltaic output and the power load under a unified framework. By introducing a source load time-delay correlation analysis and probability interval construction mechanism, point prediction results and uncertainty intervals of photovoltaic, load and net load can be output at the same time, and a set of source load integrated prediction system with high prediction precision, strong robustness and reliable interval characterization capability is constructed. The method can improve the precision and reliability of photovoltaic power and load prediction, also can reduce the risk in power system scheduling, optimizes the energy storage configuration strategy, and especially has wide popularization potential and application prospects in the scenes of new energy grid-connected operation, intelligent micro-grid and virtual power plant management and the like.

The invention discloses a server energy-saving system and method based on a lag compensation type dynamic thermal impedance model, and relates to the field of server energy saving.By collecting operation data of a server hardware bottom layer in real time, a multi-dimensional thermal-computing force coupling time sequence atlas is constructed, and based on the multi-dimensional thermal-computing force coupling time sequence atlas, a dynamic thermal impedance model is established. Calculating a heat conduction time constant of hardware in a current environment; establishing a lag compensation type dynamic thermal impedance model based on the heat conduction time constant; constructing a thermodynamic phase space according to operation data; analyzing a noise reduction evolution trajectory in combination with the lag compensation type dynamic thermal impedance model; the method comprises the steps of generating a weighted thermal resonance state vector, activating an adaptive gain MPC predictive damping scheduling strategy based on the weighted thermal resonance state vector, constructing and solving a dynamic weighted multi-objective optimization function, generating an optimal damping scheduling instruction, and thoroughly solving the fan asthma phenomenon that the fan PWM duty ratio fluctuates substantially in a sine mode under the constant computing power load.

The invention discloses a multi-dimensional data collaborative analysis early warning method based on intelligent operation and maintenance of a power transmission network, and relates to the technical field of power transmission network early warning, and the method comprises the steps: collecting target data of target equipment, and obtaining sudden change data of a power load in a system; performing correlation analysis on the instant characteristics of the electrical quantity and the dynamic change of the power grid structure in combination with the sudden change data of the power load to obtain correlation factors capable of predicting a fault; according to the power transmission network intelligent operation and maintenance early warning method, the problem that fault early warning is inaccurate and not timely due to insufficient data collaboration and early warning response lag in power transmission network operation and maintenance is solved, and the effect of improving the early warning precision and response speed of power transmission network intelligent operation and maintenance is achieved.

The invention discloses a short-term power load prediction method, system and device based on multi-intelligent-model fusion and a medium, and belongs to the technical field of short-term power load prediction, and the method comprises the steps: obtaining regional historical load data and meteorological data; performing data cleaning on the obtained load data and meteorological data; measuring linear and nonlinear correlation between the power load and the meteorological factors, and screening meteorological data with high load correlation; decomposing the load data into a time sequence by using an empirical mode decomposition method based on combination of multi-scale permutation entropy to obtain a multi-scale sub-data sequence; respectively predicting the multi-scale sub-data sequences to obtain prediction results; carrying out weighted fusion on the prediction result through a long short-term memory network model to obtain a load prediction result, and optimizing model parameters to obtain a trained multi-model prediction model; and predicting the test set data by using the trained model to obtain a final load prediction result. According to the invention, the precision and adaptability of load prediction are effectively improved.

The invention discloses a command and control system resource trend prediction method based on fusion of long and short time sequence characteristics. The method comprises the following steps: acquiring a public power load or similar time sequence monitoring data set, and preprocessing the data in the data set; a deep learning network model based on a TCN-Transformer hybrid model is constructed, a TCN model and a Transformer model are adopted for parallel computing to achieve feature extraction, the TCN model extracts short-term information, the Transformer model extracts long-term features, then fusion features are obtained through a cross attention mechanism and multi-layer perceptron (MLP) weighting, and finally prediction output is generated through full connection layer mapping. Taking data in the training set as input, training the constructed TCN-Transform hybrid model, and continuously optimizing the model until convergence meets a set requirement; and performing prediction by using the trained network model. According to the method, the TCN-Transform hybrid model is constructed, so that local fine-grained features are reserved, the global time trend is effectively captured, and the accuracy of command decision making is improved.

The invention relates to the technical field of data processing, and discloses a power sample data acquisition and classification method and system. The method comprises the following steps: synchronously acquiring active power, reactive power fluctuation and voltage harmonic data through a multi-point terminal, and constructing six types of characteristic index vector groups; a power load genetic optimization algorithm is used to optimize a classification threshold under power flow constraint; based on the optimal threshold value, clustering analysis is carried out through an EFC-KMeans algorithm in combination with impedance matrix characteristics; and inputting the clustering center into a multi-head power topology attention mechanism modeling node coupling relationship to realize power sample data classification and identification. The physical constraint conditions of the power system are effectively fused in the power sample data acquisition and classification process, so that the physical feasibility and engineering practicability of the classification result are improved.

The invention relates to the technical field of power loads, in particular to a power load dynamic optimization prediction method based on reinforcement learning, which comprises the following steps: acquiring real-time voltage frequency power of nodes, tracking frequency difference direction change of adjacent nodes, marking reverse disturbance to generate a distribution map, and identifying a frequent disturbance area according to the distribution map; clustering node groups with consistent fluctuation trends to determine a target area; monitoring power fluctuation inversion to lock energy steering nodes; constructing a prediction input set; comparing prediction and actual trends to extract a deviation interval, adjusting stride and rate of a reinforcement learning model, updating a decision and smoothing a curve, and outputting a power load dynamic prediction curve. According to the method, disturbance space-time dynamic identification is realized through multi-layer correlation analysis, judgment precision is improved through frequency power joint calibration, load path consistency and area extension are reflected through node clustering, power transmission tracking is enhanced through energy node identification, a feedback closed loop is constructed through offset monitoring, and curve continuity and response rate are improved. Stable convergence is predicted to be consistent with the trend under multiple disturbances.

The invention provides a photovoltaic access power distribution network voltage stability evaluation method, which comprises the following steps: acquiring ship docking time, staying duration and crane working frequency in a port area in real time, fusing obtained meteorological information, identifying a photovoltaic power generation output power change trend, and obtaining a daily power load peak-valley time period and a load fluctuation amplitude; according to the adjusted voltage value of each node, generating a switch operation instruction and a power adjustment instruction of the shore power supply equipment, identifying load abrupt change by executing the instructions, and determining a real-time power dispatching scheme by combining the power adjustment instruction and the ship arrival time; and according to the target voltage control value, determining the power utilization safety state of the port power distribution network, and evaluating the voltage stability of the photovoltaic access power distribution network through the operation data of the photovoltaic power generation access point.

The invention provides a power load prediction method based on feature decoupling and time-space diagram modeling, and particularly relates to the technical field of power load prediction, and the method comprises the steps: preprocessing the historical data of a power load, obtaining a normalized multivariable load sequence, and decomposing the normalized multivariable load sequence into a trend term and a season term through a learnable convolution kernel decomposition algorithm; a dominant period is extracted from seasonal term spectrum analysis, and multi-scale down-sampling is carried out according to the dominant period to generate a multi-scale sequence. Based on a multi-scale sequence, an adaptive mixed hop message aggregation mechanism is adopted, cross-scale time dependence and inter-variable high-order association are dynamically fused, and aggregation features are obtained. And performing combined prediction on the trend term and the aggregation feature, and outputting a load prediction result after inverse normalization. According to the method, the technical problem that an existing graph neural network model is difficult to accurately model a time-space dependency relationship of dynamic change under multiple scales in power load prediction is solved, so that the power load prediction precision and the model generalization ability are remarkably improved.

The invention relates to the technical field of power load prediction, in particular to a long-term power system load prediction method and system based on multi-scale decomposition fusion. The method comprises the steps of performing data preprocessing based on time sequence data; performing multi-scale decomposition and feature embedding on the preprocessed data to obtain a multi-scale load feature vector set; performing gating adaptive filtering and attention double-path fusion under the multi-scale load characteristics based on the multi-scale load characteristic vector set; performing independent prediction and prediction fusion on a fusion result based on a space-time attention gating mechanism; and evaluating a result after prediction fusion. According to the multi-scale prediction result space-time attention fusion mechanism provided by the invention, prediction information on different scales can be adaptively integrated, deviation caused by a single scale is avoided, the comprehensive performance of long-term prediction is further improved, and the method is suitable for various power system planning and operation scenes.

The invention provides a power load prediction method based on a space-time diagram convolutional network in extreme weather. Comprising the following steps: collecting historical load data and regional meteorological element data of a plurality of load nodes in a power system, and screening key meteorological characteristics which have obvious influence on loads through a mode of combining model interpretation and regression analysis to construct a meteorological characteristic vector; multivariable empirical mode decomposition and singular value decomposition are adopted to carry out multi-scale reconstruction on load data, and smooth and effective load feature tensors are extracted. On the basis, a graph network structure is constructed in combination with a node physical connection relationship, and load and meteorological characteristics are fused in a time dimension to form node time sequence characteristics. And predicting the load by using the space-time diagram convolutional network model. According to the method, the space-time dependency relationship of the load data can be effectively modeled, the prediction accuracy of the load change under the extreme weather condition is enhanced, and the method has good robustness and generalization ability.

The invention belongs to the technical field of power load prediction and artificial intelligence, and provides a microgrid short-term load prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of historical operation data, and obtaining training data; embedding the electric power feature as a physical prior feature vector into an LSTM neural network to obtain a physical embedded vector, and fusing the training data with the physical embedded vector; pre-training the fusion sequence by using an LSTM neural network to obtain a first physical constraint LSTM model; a Wasserstein GAN is used to generate a confrontation framework for joint training, and a second physical constraint LSTM model is obtained; freezing a discriminator of the second physical constraint LSTM model and performing joint training to obtain a micro-grid short-term load prediction model and predict the real-time operation data to obtain a short-term load prediction result. The short-term load prediction accuracy of the micro-grid can be improved.

The invention discloses a power distribution control method and device for an optical storage DC flexible power distribution system, and relates to the technical field of power distribution control methods, and the method comprises the steps: determining a power consumption path of each power distribution region based on a power load and a photovoltaic power generation path of each power distribution region, and an energy storage path corresponding to the optical storage DC flexible power distribution system; and the power distribution balance event of each power distribution area is determined according to each power consumption path, the power distribution level of each power distribution area and the power distribution control relationship among the power distribution areas, so that the accuracy of the power distribution balance event of each power distribution area is improved. Therefore, the dynamic restoration event of the power distribution area is determined based on the autonomous management and control system and the abnormal power distribution position of the power distribution area, and the flexible regulation and control event of the optical storage direct-current flexible power distribution system is determined based on each dynamic restoration event, the working process of the optical storage direct-current flexible power distribution system and the flexible management and control path. And the autonomous flexible regulation and control effect of the optical storage direct-current flexible power distribution system is ensured.

The invention relates to the field of power load prediction, and particularly provides a multi-model dynamic fusion load prediction method and system, a terminal and a medium, and the method comprises the steps: constructing a plurality of different types of load prediction models, carrying out the independent training of each load prediction model through a training set, and carrying out the verification of a verification set on a verification set; calculating a dynamic weight corresponding to each load prediction model by adopting a Monte Carlo algorithm on the basis of similar day data similar to the prediction target day in the test set in feature; acquiring historical load data in a preset time period before the current moment, and meteorological data and time characteristic data at the corresponding moment to form a model input data set; preprocessing the input data set, and inputting the preprocessed input data set into each trained load prediction model to obtain an initial load prediction value corresponding to each load prediction model; and according to the dynamic weight, performing weighted fusion on each initial load prediction value, and outputting a final load prediction value. The accuracy of load prediction is improved.

The invention relates to the technical field of power load prediction, and particularly provides a power load prediction method and device, a medium and a computer program product, and the method comprises the steps: carrying out the channel separation of historical time series data related to a power load based on a physical quantity type, and obtaining a plurality of single-channel time series data; according to the single-channel time sequence data, generating a multi-scale weight of a corresponding channel and time sequence fragment embedding under a corresponding scale; embedding the time sequence fragments of different scales and respectively inputting the time sequence fragments into a pre-trained hybrid expert prediction model to obtain a plurality of expert prediction results; based on the multi-scale weight, fusing the plurality of expert prediction results into a single-channel prediction result; and fusing the single-channel prediction results of the plurality of channels to obtain a power load prediction result. According to the method, a power load prediction model with channel perception, adaptive scale selection and expert dynamic combination is constructed, and prediction precision and calculation overhead can be effectively balanced.

The invention discloses a power load curve clustering method, system and equipment based on an improved density peak value clustering algorithm and a storage medium, and belongs to the field of intelligent power distribution networks, and the method comprises the steps: carrying out the sampling segmentation of power load data, constructing a daily load curve set, carrying out the standardization processing of each daily load curve, and generating a standardized sample set; based on the standardized sample set, calculating a sample distance relation of the daily load curve set, and constructing a corresponding distance matrix; establishing a local density estimation model according to the distance matrix, and calculating a density estimation value of each sample curve; according to the local density estimation value of each sample curve and the relative distance between each sample curve and other samples in the distance matrix, constructing a clustering decision value set, and selecting a plurality of sample curves with clustering decision values higher than a threshold value as clustering centers; and by taking the clustering center as a reference, sequentially distributing the residual sample curves to the class cluster to which the corresponding clustering center belongs according to the density estimation value and the distance relationship between the residual sample curves and each clustering center, and completing sample clustering division. According to the method, the problem of misclassification when the density difference of the power load curve set is too large is solved, the sample density difference when the data density difference is too large is accurately represented, the clustering precision of the load curve is effectively improved, reliable power consumer social attribute identification is provided for a power supply side, and an energy planning strategy is better implemented.

The invention relates to the technical field of short-term power load prediction, in particular to a short-term power load prediction method combining improved empirical mode decomposition and a bidirectional long short-term memory network, which comprises the following steps: preprocessing historical load data; decomposing the load data into a plurality of intrinsic mode functions by adopting a complete adaptive noise integrated empirical mode decomposition algorithm, and adaptively adding Gaussian white noise to suppress a mode aliasing problem; constructing a prediction model based on a bidirectional long-short-term memory network and a self-attention mechanism for each component; extracting features by an input layer through a sliding window; the training layer adopts a bidirectional long short-term memory network to extract time sequence hidden features, and a key time point is focused through weighting of a self-attention mechanism; the output layer generates a component prediction value; and superposing all component prediction results, and reconstructing to obtain an accurate load prediction value of the to-be-predicted day. According to the method, the prediction precision and stability are effectively improved by improving signal decomposition and deep learning model fusion.

The invention discloses a user load prediction method and device based on secondary clustering, and relates to the field of power load prediction, and the method comprises the steps: dividing the historical user load data of a to-be-predicted power system into a plurality of groups of first classification data based on a first clustering algorithm; based on a second clustering algorithm, performing secondary division on the multiple groups of first classification data to obtain multiple groups of second classification data; performing iterative training on the initial prediction model according to the multiple groups of second classification data, optimizing model parameters of the initial prediction model during iteration, and completing training until the model parameters meet a preset model parameter threshold value to obtain a load prediction model; wherein the initial prediction model is constructed based on a stacked bidirectional neural network; and inputting current user load data of a to-be-predicted power system into the load prediction model to obtain a load prediction result. According to the invention, the user load prediction accuracy of the power system can be improved.