2411 results about "Load forecasting" patented technology

An Energy and Cost Savings Calculation System is provided that automates the determination of energy and cost savings due to energy conservation measures. The system provides Multi-Variant, Non-Linear (MVNL) load forecasting techniques, energy and cost savings calculations, and Weather Ranking. The load forecasting technique may accept numerous external parameters as input. The technique may use multiple Baselines. It may also use multiple Basic Reference Periods to reduce the load forecasting error. The load forecasting technique may utilize external parameters that are updated on a daily basis, such as dry bulb temperature, dew point temperature, solar condition, and interval meter data. The technique may use Baseline Extensions to perform forecasts and Reference Period Modifications to enhance accuracy. The system may calculate energy and cost savings using Complex Rates and time-of-use (TOU) energy data. The system may rank a plurality of sources providing weather data to identify the most accurate weather data.

The invention relates to a miniature power supplying system containing a plurality of distributed power supplies, and discloses an intelligent energy control system capable of controlling a microgrid by using forecast information. The intelligent control system for microgrid energy comprises a microgrid system and a control system, wherein the microgrid system comprises a power supply unit, an energy storage unit and a load unit, and the control system comprises an information collecting system and a central processing unit. The central processing unit comprises a load forecasting module, a microgrid online status estimating module, an energy forecasting module of an intermittent power supply energy forecasting and storing unit, a microgrid system analyzing module and a microgrid multiobjective optimization operation and comprehensive coordination control module. The intelligent control system for microgrid energy can control the microgrid according to the forecast information and accomplish the intelligent operation of the microgrid.

The invention relates to an intelligent heating network dispatching system. The system comprises a data monitoring and collecting unit, a load predicting unit, a heating network balancing unit and a dispatching unit. The data monitoring and collecting unit can carry out data collecting and monitoring on a heat source, a heat exchanging station, a heat user and a pipe network of a heat supplying system. According to data collected by the data monitoring and collecting unit and meteorological information, real-time user load predicting is carried out by the load predicting unit in a heating period, and an energy consumption predicted value is obtained. Comparing is carried out on actual running data of the heat supplying system and the energy consumption predicted value, and according to the compared result, correcting is carried out on the energy consumption predicted value. According to the real-time running data collected by the data monitoring and collecting unit, analyzing is carried out by the heating network balancing unit in the heating period, and a whole network dynamic balancing control scheme is confirmed. According to the energy consumption predicted value of the load predicting unit and the whole network dynamic balancing control scheme confirmed by the heating network balancing unit, intelligent heating network dispatching is achieved by the dispatching unit.

The invention discloses a short-term electric power load prediction method considering meteorological factors, and belongs to the technical field of electric power load prediction. The method includes: collecting historical load data and meteorological data, and detecting and correcting abnormal data; analyzing the relevance between the load data and the meteorological factors, and determining key meteorological factors; establishing comprehensive meteorological factors according to the relevance between the load and the key meteorological factors; summarizing change characteristics of a daily load curve of a regional power grid, and finding out typical similar days of a prediction day; establishing an Elman neural network short-term load prediction model by employing the selected load and the comprehensive meteorological factors, and training network parameters by employing a firefly algorithm; inputting the comprehensive meteorological factors of a to-be-predicted moment and the corresponding load data to the Elman neural network short-term load prediction model, and outputting a load prediction value of the to-be-predicted moment; and displaying the load prediction value. According to the method, the load data of weekdays, weekends, and official holidays can be accurately predicted, the prediction precision is high, the applicability is high, and reliable basis is provided for making of generation plans for operation personnel of the power grid.

The invention discloses a power load forecasting method based on a long short term memory (LSTM) neuron network. The power load forecasting method comprises inputting power load data and a region feature factor at a historic moment through an input unit; carrying out training and modeling on the power load data and the region feature factor at the historic moment by means of an LSTM network in order to generate a deep neural network load forecasting model which is a single-layer multi-task deep neural network model or a double-layer multi-task deep neural network model used for power supply load forecasting; forecasting the power load in an area needing to be forecasted by means of the deep neural network load forecasting model, and generating a forecasting result of the power load in the area; and outputting the forecasting result of the power load in the area through an output unit. According to the invention, a multi-task learning power load forecasting model is constructed based on the LSTM network in the deep learning field, power consumption loads in multiple areas can be forecasted accurately, and the forecasting effect is improved.

The invention discloses a dispatching method and a dispatching system based on load online forecasting of a thermoelectric power system. The dispatching method has the main objects of a boiler and a vapor generating set which are the core equipment of a thermoelectric power generation system. The dispatching process comprises the following steps: a. acquiring data; b. creating a real-time database and a historical database; c. analyzing data and making a dispatching decision, creating a decision dispatching knowledge base to obtain a corresponding operation decision in the current optimal state to be reached and in the recent optimal dispatching state, comparing the expectation effect of the dispatching decision with an actual effect, taking the result as the condition of load forecasting, and finally obtaining the optimal dispatching decision through human-computer interaction. The dispatching system comprises a field data acquiring terminal, a field production layer DCS, a management layer ERP, a center data server and a manufacture execution and management layer MES. The invention overcomes the defects existing in the prior art; and based on the production capacity and the distribution forecast of a thermoelectric plant, the dispatching method and the dispatching system facilitate improving the production operation efficiency of enterprises, lowering the source consumption and reducing the pollution discharge.

The invention discloses a method for establishing virtual reality excavation dynamic smart load prediction models. The method includes the steps that the knowledge excavation technology is adopted so that a virtual reality analysis environment can be formed, the influence relation between fixed quantities is explored, and an input variable candidate set is determined; smart load prediction models of a support vector machine of a self-adaptive structure and an Elman neural network and the like are established, wherein input variables are determined by the support vector machine through the attribute screening technology and parameters are optimized by the support vector machine through a flora tendency differential evolutionary algorithm; a region load smart load prediction model based on data slice excavation is established; a load curve prediction model combined with dynamic electrovalence factors, user characteristics and the user response electric quantity is established, so that linked correcting prediction of loads, electrovalence and the response electric quantity is achieved. According to the method, the prediction models suitable for the actual condition of a smart power grid of China are established, the scale of construction of renewable energy sources is reasonably planned, more efficient power utilization of users is facilitated, and reasonable arrangement of power supply resources of power enterprises is facilitated.

The present invention discloses a short-term operation optimization method for a power system including large-scale wind power, comprising modeling the randomness of wind power output, modeling the randomness of the load of electric power system and modeling net load of electric power system. Net load refers that for probability distribution of net load that is too discretized, probability distribution curve of net load is divided into N intervals, the probabilities for each interval are obtained and probability distribution curve of net load is obtained through calculating and weighing each interval. Through calculating randomness of power wind output and standard deviation of load prediction error of the electric power system, net load prediction error of the electric power system is obtained and reasonable coordination is made on the electric power system according to prediction error and prediction amount to better regulate the correlations between randomness, volatility, regionalism, double-circuit peak shaving and load of wind power generation, so as to realize optimization operation of the electric power system.

The invention discloses an optimized operation control method and system of a distributed energy system. The method include: S1, collecting environmental information and actual operation data of a unit so as to acquire a change rule of cold and hot load of a distributed energy station user with season and moment, and establishing a cold, hot and electric load prediction model; S2, optimizing the cold, hot and electric load prediction model on line by introducing real-time calibration factors and the actual operation data of the unit; S3, on the premise that the energy utilization efficiency is met, establishing a dynamic optimized load distribution model according to the dynamic requirements of the predicated cold, hot and electric load by taking a whole-plant economic benefit optimization as an objective, and outputting dynamic optimized load distribution results; S4, based on the whole-plant economic benefit optimization, establishing an optimal combination model according to the dynamic optimized load distribution results, and outputting a unit operation optimization command. High-precision load prediction information can be acquired, a corresponding optimization command is formed, and online optimization control is performed on the load dynamics and unit operation.

The present invention relates to system and method for providing near real-time DR events and price signals to the customer end-points to optimally manage the available DR resources. The system utilizes bottom up load forecasting for accurate individualized forecasts for customer loads in the presence of dynamic pricing signals. For better efficiency and reliability of grid operation the system utilizes advanced machine learning and robust optimization techniques for real-time and “personalized” DR-offer dispatch.

The invention discloses a short period load prediction method based on kernel principle component analysis and a random forest. The a short period load prediction method comprises the following steps of: (1) analyzing and selecting data influencing load prediction precision of a day to be predicted in an operational electric power system, and preliminarily constructing training and prediction sample sets; (2) utilizing kernel principle component analysis to carry out dimensionality reduction on training sample data; (3) utilizing a random forest model to train the training sample data after the dimensionality reduction, and obtaining the random forest model after the training; and (4) inputting prediction sample data into the random forest model after the training, and carrying out short period load prediction of the day to be predicted. The short period load prediction method has the advantages that the kernel principle component analysis and the random forest model are combined for carrying out short period load prediction on the electric power system, the prediction precision, efficiency and data rationality are improved.

The invention relates to a wind-power adsorption connected large-power-grid scheduling rolling planning method, comprising the following steps: obtaining ahead planned output data of all conventional units from an ahead power-generation planning system; building an intraday rolling model of a wind-power adsorption connected power grid based on the ahead plan; obtaining a current system load predicted value and a total wind-power output predicted value through intraday rolling expansion short-term prediction and refreshing the output data of residual time intervals of all the conventional units in an online manner according to the system loading predicted value and the total wind-power output predicted value; and updating processing data of a single machine in optimization problems in a unit output plan. The method can well solve the effect of wind-power connection on the operation of the power grid, and the safety and economic property for power grid operation are improved while cleanenergy sources are fully utilized.

The invention discloses a short-term and medium- and long-term electric power load prediction method based on machine learning model. Firstly, preprocessing is conducted on data, including smootheningabnormal data and filling missing data. Factors of affecting load changes will be analyzed, including historical data, time periodicity, and weather variable characteristics. Domestication will be conducted on all input variables for accelerating learning speed and raising prediction precision. The invention is advantageous in that linear regression is compared, and the performance of the vectorregression and gradient lifting regression in the short-term and medium- and long-term electric power load prediction is supported; with the prolongation of the prediction time, the performance of thegradient lifting regression model is better that that of the other two models; the AdaBoost algorithm which uses the gradient lifting tree as a basic classifier is brought forward, and load prediction is conducted, and the precision of electric power load prediction can be effectively raised.

The invention discloses a power load forecasting method based on customer segmentation in power industry. The power load forecasting method comprises: step 1, extracting customer load data and obtaining load sample data; step 2, pre-processing the load sample data; step 3, performing cluster grouping to customer to obtain a plurality of customer groups; step 4, summarizing the load data of the customer groups; step 5, performing load timing sequence forecasting to a single customer group; step 6, summarizing and calculating load forecasting results of the plurality of customer groups; and step 7, evaluating the load forecasting results obtained in the step 6. The power load forecasting method can accurately forecast power load of the customer groups and provides a basis for development and operation of a power system.

The invention discloses a dynamic climate compensation method for centralized heating. Firstly, the outdoor temperature is predicted, water supply and return temperatures are adjusted some time ahead according to the predicted value of the outdoor temperature, and the hysteresis of pipe network adjustment in the manner that adjustment is performed while sampling is overcome. The outdoor temperature of the next day is predicted according to local historical meteorological data and weather forecast of the meteorological department, and the value is used as basic data for prediction of a thermal load; and then the thermal load is predicted, that is, the thermal load curve of the next day is calculated according to the outdoor temperature. With the method, the outdoor temperature is reasonably predicted so as to realize advanced dynamic adjustment of a climate compensator; heating medium parameters of a heating system are adjusted by the aid of an adjusting model according to the thermal load value set in advance, a heat source is changed from original wide passive heating into active heating, on the premise that the indoor temperature for the user is stable, the operation adjusting indictor of the heating system within the specified time are given in advance, the heating efficiency is improved, and the heating energy consumption is reduced.

The invention relates to the field of elastic computing of cloud computing, and discloses an agile elastic telescoping method in a cloud environment. The agile elastic telescoping method includes the specific steps: forecasting the load of a next time slice according to historical load data of a data center through an ARIMA (autoregressive integrated moving average) model and an ARMA (autoregressive moving average) model by taking the time slice as a cycle; performing saving operation and restoring operation on a virtual machine, saving the memory state of the virtual machine by the saving operation to hang up the virtual machine, and then restoring the memory state of the virtual machine by the restoring operation to restore use of the virtual machine; hanging up one or a plurality of application-ready virtual machines or rapidly placing the virtual machines into service through the forecasted load of the data center obtained by the load forecasting step and by the aid of the rapid supply step of the virtual machines to dynamically adjust resources of application clusters of the data center. The agile elastic telescoping method has the advantages that the sizes of the clusters are adjusted in real time according to current conditions of the application clusters, and energy consumption of the data center is reduced.

The invention belongs to the technical field of energy management of distributed generation energy supply systems of electric power systems. The control method comprises the following steps: before running a combined system on every workday, extracting history cooling load data and power load data of a terminal user from a historical data base and obtaining the delay variation curve of the coolingload and the power load of the terminal user during the whole workday by lone-term load predicting; according to load predicting results, working out the optimal generated output plan of the combinedsystem by adopting optimization control mathematical model; during the running of the combined system, carrying out optimization control calculation again by utilizing the terminal user real-time cooling and power load need obtained from the distributed control system, and modifying the generating capacity and the refrigerating capacity of the combined system. The invention utilizes a distributedmonitoring system to monitor the actual cooling and power load need of the terminal user and can modify the load forecasting result in real time and adjusting the respective controlled variable of the combined system.

The invention discloses a dispatching method for achieving robust operation of an electrical power system. The dispatching method comprises the steps that S1, original data information is obtained; S2, under a certain confidence coefficient level, an upper limit and a lower limit of a mean value of day-ahead, intra-day and real-time wind power generation forecast errors, an upper limit and a lower limit of day-ahead, intra-day and real-time photovoltaic power generation forecast errors, and an upper limit and a lower limit of day-ahead, intra-day and real-time load forecast errors are obtained; S3, a day-ahead dispatching plan, a robust safe operation range corresponding to the day-ahead dispatching plan, an intra-day dispatching plan, a robust safe operation range corresponding to the intra-day dispatching plan, a real-time dispatching plan and a robust safe operation range corresponding to the real-time dispatching plan are obtained. According to the method, the rolling coordination technologies of forecast information, current operation information and historical operation information are considered simultaneously, the robust safe operation ranges of the system are obtained, and therefore the dispatching plans are not limited to a unique preset value, and flexible dispatching in the robust ranges can be achieved. The obtained dispatching plans can be used for coping with stochastic volatility of new energy power generation better, and safety and economical efficiency are both considered.

A method for generating a net load forecast for a utility grid, the grid including intermittent distributed energy resources and loads, comprising: defining two or more load forecast zones, each zone being associated with a load profile type and a climate zone type; assigning each of the loads to one of the zones based on the load profile and climate zone types associated with the load; assigning each of the energy resources to at least one of the zones based on the climate zone type associated with the energy resource; for each zone, generating an electrical energy consumption forecast for loads, an electric power generation forecast for energy resources, and a net load forecast from the electrical energy consumption and electric power generation forecasts; combining the net load forecast for each zone to generate the net load forecast for the grid; and, presenting the net load forecast on a display.

The invention discloses a regional energy comprehensive coordination management and control system. The system comprises a regional operation monitoring subsystem, a distributed power forecasting subsystem, a load cluster prediction response analysis subsystem, a fault fast processing subsystem, an energy analysis and management subsystem, an electric vehicle optimal scheduling subsystem and a regional multi-level energy comprehensive coordination control subsystem. The regional energy comprehensive coordination management and control system achieves comprehensive operation monitoring of power sources, power grids and user loads in a region and forecasting, analysis and scheduling of a variety distributed energy resources on the basis of multi-source information integration, achieves rapid fault diagnosis and processing of the power grid, achieves load forecasting, energy consumption analysis, energy saving management and electric vehicle intelligent scheduling of users and achieves reasonable distribution and pluralistic complementary of regional energy through comprehensive coordination of energy interaction among the power sources, the power grids and the user loads, thereby greatly increasing the energy efficiency and enabling the power grids to be in economical and efficient operation.

The invention relates to a short-term load prediction method based on a clustering and sliding window. The method comprises the following steps of: preprocessing electric power load data; clustering historical data of a prediction user by utilizing a clustering algorithm, and adjusting clustering parameters; selecting k data from near to far of the prediction time in a category, containing most data, in clustering results to form a sliding window k; predicting the k selected data by utilizing a combination model based on the sliding window, and acquiring a primary prediction result; and correcting the primary prediction result of the combination model according to meteorological factors to obtain a final load prediction result. Compared with the prior art, the method has the advantages of high prediction precision, good adaptability and the like.