53 results about "Electricity demand forecasting" patented technology

The invention discloses a power demand evaluation method, system and device based on deep learning, and a storage medium, and belongs to the technical field of power system intelligence and energy management, and the method comprises the steps: collecting data of multiple modes, and carrying out the preprocessing of the data; designing an adaptive weighting strategy according to the preprocessed data, weighting different modal data, constructing a deep learning model through weighted fusion data, and training the model; and outputting a prediction result of the power demand, and correcting the output result. According to the method, the dynamic weighting strategy of multi-modal data and a time window correction mechanism are fused, so that the adaptability of power demand prediction to complex environment changes is remarkably improved, and the load fluctuation characteristics of extreme weather can be accurately captured; and in combination with the time sequence modeling capability of the long-short-term memory network, the long-term dependency relationship and the multi-factor coupling rule are effectively learned, and the problem that a traditional model is insufficient in expression of periodic and sudden demand modes is solved.

The invention relates to the technical field of data analysis, and discloses a power demand prediction method based on a complex network and a graph neural network, and the method comprises the steps: recognizing a coupling relation between multi-source time sequence feature data sets, and constructing a power demand complex network through the multi-source time sequence feature data sets and the coupling relation, the method comprises the following steps: performing feature learning on a power demand complex network through a graph neural network, generating a power demand prediction model, pruning the power demand prediction model to obtain a lightweight prediction model, and performing demand analysis on power data to be analyzed by using the lightweight prediction model to obtain a target prediction demand. And performing feature attribution analysis on the target prediction demand to obtain a feature contribution degree, generating a demand prediction reason according to the feature contribution degree, and generating a power demand prediction result according to the target prediction demand and the demand prediction reason. According to the method, the requirements of high precision, real-time performance and credibility on power demand prediction under the new-quality productivity development background are effectively met.

The invention discloses a monthly load prediction method fusing time-of-use electricity price elements and long and short term time sequence characteristics, and relates to the field of load prediction, and the method comprises the steps: building a monthly load prediction model through employing a knowledge migration algorithm based on a dual-channel time sequence neural network and a long and short term time sequence routing module; the dual-channel time sequence neural network comprises a multi-scale partitioning module, a Mamba module and a local window converter; key characteristic parameters of monthly loads are obtained; and inputting the key characteristic parameters into a monthly load prediction model, and predicting the monthly load. According to the invention, a scientific and reliable quantitative basis can be provided for power demand prediction and system planning decision.

The invention provides a deep learning-fused power demand multi-algorithm collaborative demand prediction method and system, and the system comprises a short-term power demand prediction platform, a medium and long term power demand prediction platform, a collection management platform, and a display analysis platform. According to the whale optimization algorithm, the generalization ability is improved by introducing chaotic mapping and a nonlinear convergence factor, the weight is optimized in combination with a multi-scale graph convolutional network, the number of nodes, the learning rate and the number of iterations of a model are optimized in combination with a simulated annealing algorithm, the model is constructed, and by setting a medium-and-long-term power demand prediction platform, the power demand prediction efficiency is improved. Based on the Tent chaotic mapping and the dynamic step length factor optimization standard sparrow search algorithm, the prediction result is accurate and reliable by optimizing the key parameters of the composite model combining the convolutional neural network and the bidirectional long and short term memory network with the attention mechanism, and the power demand prediction cost is reduced.

The invention relates to an orderly power utilization management method based on user behavior analysis, and belongs to the technical field of power utilization behavior analysis. The method comprises the steps of data acquisition, data analysis and prediction, calculation of a personalized power utilization strategy, dynamic excitation of the strategy and establishment of a user feedback platform. Through the method, the accuracy of power demand prediction can be improved, power resources are reasonably scheduled, and the participation degree and satisfaction degree of users are improved. Through refined load prediction and orderly power utilization guidance, the power utilization peak can be effectively stabilized, the peak load can be reduced, the safe and stable operation capability of the power grid can be improved, and powerful support is provided for power dispatching and emergency management.

The invention relates to the field of power customer demand prediction based on data mining, in particular to a power customer demand prediction method and system based on data mining, and the method comprises the steps: collecting multi-source data of a target customer group; carrying out power consumption behavior clustering on the clients based on pattern mining, and generating user behavior tags; extracting a multi-dimensional feature vector of the customer based on the behavior tag; a prediction model is constructed according to the multi-dimensional feature vectors, and accurate prediction and optimal management of power customer demands are realized by combining a data mining technology and power demand prediction. Firstly, a multi-source data acquisition technology is adopted, rich input data is provided for a prediction model, and power consumption behaviors of various clients can be reflected more accurately. And secondly, through mode mining and power consumption behavior clustering, the clients are divided into different power consumption groups, personalized features of the clients are generated based on behavior tags, accurate input feature vectors are provided for a subsequent prediction model, and the prediction accuracy is improved.

The invention discloses a power demand prediction system and method based on a deep fusion network, and the method comprises the steps: carrying out the standardization preprocessing of multi-source data, introducing a self-adaptive weighting mechanism based on relation complexity, and dynamically fusing a plurality of statistical correlation coefficients to precisely recognize significant influence factors, the technical problem that traditional fixed weight screening is difficult to consider linear and nonlinear relationships is solved. Then, an Almong polynomial distribution lag model and coupling coordination degree analysis are utilized to quantify time lag contribution of influence factors and process feature interaction, and a final feature set including a dynamic conduction mechanism is constructed. And finally, through a deep fusion model integrating the convolutional neural network and the bidirectional long-short-term memory network, multi-scale local features and bidirectional long time sequence dependence are extracted in parallel, so that high-precision prediction of the power demand is realized, and the defects that an existing model is weak in generalization ability and difficult to capture a complex time sequence rule are overcome.

This invention discloses an energy-saving and safe prefabricated substation, relating to the field of power systems. It includes: a power demand forecasting module: predicting future power demand and adjusting transformer operating parameters based on this demand; a quantum communication configuration module: selecting a quantum key distribution protocol based on the transformer operating parameters, deploying quantum communication equipment, connecting smart sensors installed at various nodes, establishing an energy management panel, and collecting operational intelligent data through the smart sensors; an intelligent sensor network deployment module: receiving and preprocessing the operational intelligent data collected by the sensors through the energy management panel, deploying smart nodes within the substation to form a distributed sensing network; and a local data analysis and decision-making module: completing the operational intelligent data analysis and decision-making process locally through the distributed sensing network. This invention, through its power demand forecasting module, achieves accurate prediction of future power demand.

The invention discloses an iron and steel industry power demand prediction method and system based on multi-source factors, and relates to the technical field of data processing and big data analysis, and the method comprises the steps: collecting the historical environment, port throughput, logistics, power demand and iron and steel industry chain associated data of a target region; obtaining multi-source factor standard subdata through space-time alignment, preprocessing and monthly granularity division; through correlation analysis and trend chart construction, screening a first electricity consumption correlation factor, and determining an electricity consumption correlation coupling factor pair and short-term accidental and long-term stable correlation dynamic factors; a prediction model is constructed based on fitting of a time function and a periodic function, data are collected in real time, correction is carried out in combination with sudden factors such as extreme weather and policy adjustment, and a steel industry power demand prediction value is output. The method has the advantages that deep fusion of multi-source factors is achieved, prediction is accurate and reliable, and effective support can be provided for power grid load management and production planning of the iron and steel industry.

The invention belongs to the technical field of electric power, and discloses a method for establishing a diversified power consumption prediction model for a micro-grid unit. The method comprises a step of constructing a power distribution system source network load storage layering and partitioning structure, a step of constructing a diversified power utilization demand model facing a micro-grid unit, a step of predicting distributed photovoltaic output based on space-time fusion, a step of predicting an electric vehicle charging load, and a step of predicting a demand side response load. The method has the main beneficial technical effects that the prediction precision under the new energy uncertainty condition is improved, and the intra-day short-term prediction accuracy reaches 90% or above; an aggregation calculation method of the charging load of the electric vehicle is established; a stripping method and a prediction model based on a daily reference load curve are provided, the correlation between the stripping method and the temperature is analyzed, and the accuracy of intraday short-term load prediction reaches 95% or above.

The application discloses a kind of electric power demand prediction method, device, medium and equipment.The application is by comprehensive historical electric power data and to be predicted day information, using mutual information method and cosine similarity principle to carry out depth optimization to historical data, constructs accurate electric power demand prediction index system.Further, the relative error method of first structure model is filtered out with the initial sample set related to the to-be-predicted day, and then the numerical similarity and shape similarity analysis of the second structure model are analyzed, and the electric power data that meet the short-term electric power demand prediction are refined.Finally, in combination with the to-be-predicted day and the index system, the first index system is selected, and these selected data are input into the well-trained long short-term memory model, and the powerful time series analysis capability of the model accurately outputs the electric power demand result of each period of the to-be-predicted day.The application improves the accuracy of short-term electric power demand prediction to solve the problem that the short-term electric power demand cannot be accurately predicted in the prior art.

The application discloses a power demand prediction method and a terminal during the Spring Festival, which comprises the following steps: inputting prediction data of a Spring Festival influence period of a prediction year into a power demand prediction model which does not consider the influence of the Spring Festival and only considers the influence of air temperature, outputting power consumption of the Spring Festival influence period of the prediction year without considering the influence of the Spring Festival, and then calculating predicted power consumption of the Spring Festival influence period of the prediction year based on power consumption of the Spring Festival influence period of historical years considering the influence of the Spring Festival and the power consumption of the Spring Festival influence period of the prediction year without considering the influence of the Spring Festival, so as to step by step predict the power consumption considering only the influence of air temperature and the power consumption influenced by the Spring Festival, and combine power consumption of the Spring Festival influence period of historical years, so as to more accurately predict power demand during the Spring Festival, and help power supply enterprises to better plan and dispatch power during the influence period of the Spring Festival.

The application discloses a power demand prediction method and system based on big data analysis, relates to the technical field of power systems, and mainly aims to solve the problems of poor prediction accuracy and effectiveness of existing power demand, and save power transmission effectiveness. The method comprises the following steps: determining load information to be demanded and time period average use data corresponding to the load information, wherein the time period average use data comprises average values of power scheduling use in multiple time periods; based on the load information, a corresponding demand prediction model is called, and the time period average use data is processed based on the demand prediction model to determine power demand reference data of a target time period, wherein the demand prediction model is obtained by training a deep learning network based on multi-time period use sample data; a reference time period of the target time period is determined, and the power demand reference data is adjusted based on the power demand extreme value and the power demand average value of the reference time period to obtain a power demand prediction result.

The invention discloses a big data measurement asset use portrait and demand prediction allocation method, and belongs to the technical field of electric power big data and asset optimization management, and the method comprises the steps: S10, constructing a database related to a target region, the database comprising a high-demand power data group and a low-demand power data group, acquiring power consumption data of the user from the high-demand power consumption data group; and S20, distinguishing the high-demand power consumption data group into a regular power consumption user group and an irregular power consumption user group, and calculating the proportion of the regular power consumption user group and the irregular power consumption user group in the high-demand power consumption data group. According to the method, the accuracy and the response speed of power demand prediction are improved and the dynamic change of a complex power system is effectively dealt with by constructing the database, distinguishing the power consumption behavior modes of the users, dynamically monitoring the power demand change, extracting key power consumption characteristics, quantifying the load fluctuation ratio and implementing hierarchical load management.

The application relates to the technical field of central air conditioning system management, and discloses a dynamic power management system based on central air conditioning load characteristics, which mainly comprises a load characteristic analysis module, a power demand prediction module, an energy distribution optimization module and a control execution module. The load characteristic analysis module classifies load characteristics by analyzing historical operation data of the central air conditioning system; the power demand prediction module predicts future power demand in combination with load characteristic classification results and weather forecast data; the energy distribution optimization module generates an optimal energy distribution scheme according to predicted power demand and current power supply conditions by using a genetic algorithm; and the control execution module adjusts the operation of the central air conditioning system according to the optimization results. The system accurately analyzes load characteristics, predicts power demand and optimizes energy distribution, effectively reduces power cost, meets the power demand of the central air conditioning system, improves energy utilization efficiency, and has remarkable economic and environmental protection benefits.

This invention discloses a power dispatching method, system, equipment, and medium based on daily planning and simulated operation, belonging to the field of power dispatching technology. The specific steps are as follows: First, acquire real-time and historical power grid data to establish a power demand dataset. Second, establish a power demand forecasting model, perform time series analysis on historical and real-time power grid data, and forecast future power demand. Third, establish a multi-objective optimization function, and use an improved genetic algorithm to solve the multi-objective optimization function to obtain the optimal power dispatching scheme. Fourth, input the optimal power dispatching scheme into the simulation model for verification, and then issue the verified optimal power dispatching scheme for execution. This invention, through the closed-loop fusion of data-driven prediction, multi-objective intelligent optimization, and high-fidelity simulated operation, transforms the traditional static dispatching mode relying on human experience into a dynamic optimization and proactive defense intelligent decision-making mode. This improves the automated generation capability of dispatching plans and the level of safety pre-control.

The invention relates to a digital data processing technology of a power management system, in particular to a power demand analysis method and system under multi-source data fusion. The analysis method comprises the following steps: collecting and converging multi-source heterogeneous data; performing data fusion and standardization processing; carrying out multi-dimensional scene load characteristic modeling and trend analysis; performing layered and classified electricity demand prediction; and outputting a hierarchical classification prediction report. The analysis system comprises a multi-source data acquisition module, a data fusion processing module, a feature modeling and analysis module, a hierarchical prediction and optimization module and a visual display module. Compared with the prior art, the method has the advantages that a complete power utilization analysis data panorama is constructed, and the load feature recognition integrity is improved by more than 40%; the average absolute percentage error MAPE of short-term load prediction can be reduced to be within 3% and is improved by about 35% compared with a general modeling analysis method; and the efficiency of converting the prediction result into the action can be improved by 50%.

The invention belongs to the technical field of power demand prediction, and particularly relates to a power demand prediction method based on deep learning, which comprises the following specific steps: S1, acquiring a power demand prediction original data set; s2, preprocessing the power demand prediction original data set to obtain a power demand prediction image data set; s3, constructing a power demand prediction model for predicting power demand data; s4, dividing a power demand prediction image data set, and training and verifying a power demand prediction model; and S5, applying the power demand prediction model to obtain a predicted value of the hour-by-hour power demand of the target region in the future time period. According to the method, when power demand prediction is carried out, image spatial-temporal features can be extracted and fused more comprehensively and accurately, and the prediction precision and efficiency in a complex power data scene are remarkably improved.

The present invention comprises: a communication unit that communicates with a host system that creates a regional energy plan; a target setting unit that sets a target value for creating balancing power for a target consumer site; a prediction unit that predicts future electric power demand; a boundary-condition-setting unit that sets a boundary condition for demand control from load facility specifications; an operation plan creation unit that creates a demand control plan for the load facilities from the target value for balancing power, the future electric power demand prediction, and the boundary condition for demand control; and an input / output unit. The regional energy plan is created or corrected by the host system on the basis of whether the demand control plan can be executed.

This invention discloses a method and system for electricity demand forecasting based on big data analysis, belonging to the field of power big data analysis and load forecasting technology. It addresses the problems of multi-step rolling error accumulation and large peak-valley load forecasting deviations in traditional electricity demand forecasting. This invention collects and standardizes multi-source data on historical load, meteorological, date characteristics, and electricity consumption structure, jointly identifying and correcting abnormal data. Through error propagation characteristic analysis, a comprehensive error propagation index is constructed. Based on wavelet decomposition, hierarchical forecasting of trend, periodic, and fluctuation components is performed, and a dynamic weight allocation strategy is designed in conjunction with the error propagation index. An error compensation and confidence decay mechanism is introduced, and rolling updates and segmented verification corrections are performed, significantly improving the stability and accuracy of electricity load forecasting.

The invention discloses a hybrid prediction-based power carrier energy-carbon linkage control method and system, and the method comprises the steps: obtaining power utilization data, weather data, policy data and economic data, inputting the data into a hybrid prediction model, and predicting a power demand prediction value in a future time period; a multi-target constraint optimization model is constructed, and an energy-carbon linkage distribution strategy in the future time period is solved and obtained, including the electric quantity purchase amount, the clean energy power supply amount, the energy storage charge and discharge amount and the energy storage charge state in the future time period; and according to an energy-carbon linkage distribution strategy in a future time period, correspondingly generating an electric power purchase instruction, an electric power generation instruction and an electric power storage instruction, and correspondingly sending the electric power purchase instruction, the electric power generation instruction and the electric power storage instruction to an electric power purchase client, an electric power generation device and an electric power storage device in an electric power carrier communication mode to control electric power purchase, generation and storage. According to the invention, the method can achieve the precise prediction of the power demand in a complex environment, dynamically adjusts the energy supply according to the prediction result, and effectively controls the carbon emission.

According to the present invention, building information (104) includes: basic building-information (101) that includes information on the size of a building; maximum annual power that indicates power consumption at a time. within one year. when the power consumption of the building is at a maximum level; and a power consumption amount of the building during a predetermined period within the one year. A processing device (21) extracts, from past power data (103), power data of a similar building for which the basic building-information (101) is similar to that of a target building. The processing device (21) generates power data of the target building by correcting the power data of the similar building so that, for the power data of the similar building and the power data of the target building, there is a match between the maximum annual power consumption amounts and also between the power consumption amounts during the predetermined period.

The invention discloses a method and system for participating in electric power spot transaction through centralized energy storage, and relates to the technical field of electric power spot transaction energy storage optimization, and the method comprises the steps: employing an LSTM network and a random forest model, and carrying out the real-time prediction of an electric power demand value and a real-time prediction of an electricity price fluctuation value; based on the Actor-Critic architecture, the historical power demand predicted value and the electricity price fluctuation predicted value, constructing a power spot transaction charging and discharging decision model, and outputting a real-time charging and discharging strategy; based on the real-time power demand prediction value and the real-time electricity price fluctuation prediction value, multi-scene simulation is carried out through Monte Carlo simulation, earnings and risks of a multi-scene real-time charging and discharging strategy are calculated, and a simulation score report is output; and through Monte Carlo simulation, charge and discharge strategy operation conditions in different scenes are simulated, income and risk indexes are calculated, and the robustness and stability of the charge and discharge strategy are comprehensively evaluated.

The application discloses a power resource scheduling and load balancing optimization method and system combined with big data, and comprises the following steps: constructing a power demand prediction model, and obtaining a variety of power demand prediction result sets of each target area in a future time period; inputting real-time collection data into the power demand prediction model, and obtaining a prediction result with the highest matching degree; calculating the power load coefficient of each target area; constructing a regional load difference matrix, and obtaining a power resource dispatching-out area set and a dispatching-in area set; dividing a scheduling period into multiple time periods, and scheduling power resources through incremental power transfer; inputting the real-time collection data after scheduling into the power demand prediction model to repeat the above steps until the median value in the obtained regional load difference matrix is less than a scheduling threshold value. The application has the advantages that: accurate power demand prediction is realized through real-time data dynamic matching, and the power distribution between regions is optimized based on the load difference matrix and incremental scheduling, so that the power grid operation efficiency and stability are significantly improved.

The application discloses a power user service demand prediction method based on big data analysis, comprising the following steps: collecting power user data, and pre-processing the power user data; analyzing the pre-processed data by using a wavelet transform clustering algorithm to divide power user categories; combining the power user categories and historical power consumption data to establish a power demand prediction model; predicting the power user service demand by using the power demand prediction model, and visualizing the prediction result; by combining the clustering algorithm and the neural network, the application can process massive data, accurately predict the power user service demand, visualize the prediction result, and realize fine management of the power user.

The invention relates to an industry prosperity index-based power demand prediction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a preset industry index corresponding to a to-be-analyzed industry; performing index screening processing on the preset industry index to obtain a target industry index corresponding to the to-be-analyzed industry; obtaining current index data of the to-be-analyzed industry under the target industry index; inputting the current index data into the trained index data prediction model to obtain prediction index data of the to-be-analyzed industry under the target industry index; according to the prediction index data, determining a prosperity index corresponding to the to-be-analyzed industry; and according to the business index, determining predicted power demand information corresponding to the to-be-analyzed industry. By adopting the method, the prediction accuracy of the power demand can be improved.

This application discloses a method, device, and medium for forecasting electricity demand to adapt to the new electricity price reform. The method includes: determining information on changes in electricity price factors and economic factors in the target analysis area; acquiring historical electricity consumption data and factors influencing electricity demand for different electricity users in the target analysis area; generating electricity consumption curves for each electricity user and clustering them; analyzing the degree of influence of each electricity demand influencing factor based on the historical electricity consumption data of each electricity user in the electricity user class, and selecting key electricity demand influencing factors; updating the electricity users in each electricity user class based on the key electricity demand influencing factors; obtaining an electricity user class including electricity price factors and economic factors as the target electricity user class; training an electricity demand model based on the target electricity user class, and forecasting the electricity demand of each electricity user in the future forecast period.

The invention discloses a new energy bearing capacity assessment method, device and equipment suitable for a provincial power grid, and the method comprises the steps: firstly collecting power demand prediction, new energy and conventional power supply installed capacity and section limit power transmission capacity data, and constructing a year-round 8760-hour time sequence production simulation model; carrying out production simulation based on a load curve and section constraints, and iteratively adjusting the installed capacity of the new energy until a power abandoning rate threshold value (such as 10%) is met and the power transmission margins of all sections are non-negative; and further screening the minimum starting mode of the synchronous unit, which is most strict to the frequency stability and the multi-station short-circuit ratio, verifying the frequency stability and the multi-station short-circuit ratio (a threshold value 2) of the system by using electromechanical transient simulation, and returning to adjust the installed capacity if the verification is not passed. According to the method, four types of constraints including system regulation capability, frequency stability, section power transmission capability and multi-station short-circuit ratio are fused for the first time, accurate quantification of the provincial power grid new energy bearing capacity is realized, and a scientific basis is provided for power grid planning under high-proportion new energy access.

The application discloses a method and a terminal for generating a power supply guarantee scheme, obtains power demand prediction data and calculates power supply data, and obtains power profit and loss data by subtracting the power demand prediction data from the power supply data; the power profit and loss data can be used to obtain the profit and loss of power, if the power is in loss, a demand side response power supply guarantee scheme is generated when the loss power is less than a first preset load, and a power supply guarantee scheme combining the demand side response and power exchange is generated when the loss power is greater than or equal to the first preset load. Therefore, the power supply guarantee scheme considering the demand side response and the power exchange can fully tap the internal adjustable load and external power supply capacity on the basis of the original power supply and demand balance, and guarantee the safe and reliable power supply under extreme conditions.

The invention discloses an electrolytic bath start-stop planning and scheduling method and system, and the method comprises the steps: constructing an electrolytic bath environment model, and obtaining the operation state, power input, hydrogen output and future power demand prediction of an electrolytic bath; based on the deep Q network, the intelligent agent decides start-stop operation of the electrolytic cell and optimizes the power regulation rate according to the current state and future power demand prediction; defining a state space and an action space, designing a reward function, updating a Q value through Q learning, and optimizing an agent decision strategy; the start-stop priority is dynamically adjusted according to the running state, historical data and power adjusting rate of the electrolytic cell; calculating the starting and stopping time of the electrolytic cell according to the starting and stopping decision and the power regulation rate; outputting the state plan of each electrolytic cell, the total load adjustable upper and lower limits and the power adjusting plan; the problems of power regulation rate limitation, long start-stop time and coordinated control of multiple groups of electrolytic cells are solved, and the start-stop response speed, the economic benefit and the stability of the electrolytic cells are improved.