70 results about "Energy forecasting" patented technology

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.

A wind energy forecasting method with extreme wind speed prediction function cooperated with a central computer, comprising the steps of: inputting a weather data which contains a numerical weather prediction data; implementing a modification with a first model output statistics; implementing a modification with a physical model in accordance with the output of the first model output statistics that can iteratively calculate the results by varying the angles of wind direction; implementing a modification with a second model output statistics; and implementing a prediction of extreme wind speed caused by typhoon, which comprises the following sub-steps of: using a wind and typhoon database to find track data of plural historical typhoons within a certain distance from a target typhoon; using an extreme wind and wind energy prediction tool to calculate at least one extreme wind speed in the future of the target typhoon and calculate the probability of occurring the extreme wind speed; and modifying the extreme wind speed with the physical model to the extreme wind speed at the position or height of a wind turbine.

A computer-executable method is executed by a CPU as the following steps of: obtaining an interested range in relation to a target typhoon and obtaining historical typhoons within the interested range from a wind and typhoon database; obtaining shortest distances from the respective historical typhoons to the target typhoon within the interested range; choosing a target ground grid point and obtaining normalized extreme wind speeds of the respective historical typhoons corresponding to the target ground grid point; obtaining extreme wind speeds probable for the target ground grid point by calculation according to the normalized extreme wind speeds and the highest wind speed of the center of the target typhoon; and arranging the extreme wind speeds in descending order, arranging the shortest distances corresponding to the respective extreme wind speeds, and obtaining the occurrence probability of the extreme wind speeds at the target ground grid point according to a formula.

A wind energy forecasting system processes data from one or more numerical weather prediction models with power output data from a wind energy facility using artificial intelligence. This artificial intelligence is applied in one or more neural networks that produce specific power output forecasts for each numerical weather prediction model. A statistical ensembling approach is then applied to the resulting numerical weather prediction model forecasts and integrated with a persistence power output forecast to arrive at a consensus, overall forecasted power output for the wind energy facility.

The invention provides a method for improved building energy usage reduction by computer automation of optimized plant operation times and sub-hourly building energy forecasting to determine plant faults. The invention provides a computer system to derive the NTL, mechanical heat-up (MHL) and mechanical cool-down (MCL) lags and in conjunction with a readily available interval weather forecast, the system can output various signals to indicate optimized start and stop times for heating and cooling equipment. The algorithm to calculate the 15-minute energy forecast is used to indicate out-of-control conditions in the operation of the plant.

The invention provides steel production planning-based energy forecasting system and forecasting method. The forecasting system consists of a data acquisition network, an industrial ring network and a management network, wherein field real-time data of a measuring instrument and a programmable logic controller (PLC) is acquired through the data acquisition network, and output and consumption forecasting of an energy consumption unit in the future is realized by the energy forecasting module according to data of production plan, maintenance plan and equipment state acquired from enterprise resource planning (ERP) and manufacturing executive system (MES). The system can accurately forecast the energy output and consumption of a single unit or the whole enterprise according to the production plan, the maintenance plant and equipment state and other real time data, and provides basis for reasonable dispatching of energy of steel enterprises, thereby effectively reducing energy waste of the steel enterprises.

An on-line energy forecast system based on a product ARIMA module and a method thereof belong to the field of steel industry energy forecast technology. The system comprises a local PLC, a PCS layer consisting of DCSs, a MES layer, an ERP management layer and a network system. The network system comprises an SCADA system arranged on a spot, a real time database server, a database server, an application server, a client workstation, an anti-virus database and a network which is connected with a computer, a controller and a sensor. The invention has the advantages that an applicable module grade is configured by a prediction algorithm parameter configuration module, which can realize that real time on-line forecast can be carried out on multiple data types comprising steady, non-stationary, seasonal fluctuation data.

The invention provides a system for dynamically predicating the power load of an iron and steel enterprise in a short period and belongs to the technical field of energy predication of iron and steel enterprises. According to hardware, the system comprises an application server, a relational data base server, a client side PC and a network device connecting all computers. The network device comprises a switch, network cables, a firewall and a router device. The application server and the relational data base server are connected to the switch through the network cables. The external client side PC is connected to a router. The router is connected with the switch through the firewall, so that communication between a client side and a server side is achieved. A software system comprises a heterogeneous data platform and a load predicating system. The load predicating system is composed of a load analyzing module, a predication configuration module and a load predicating module. The system for dynamically predicating the power load of the iron and steel enterprise in the short period has the advantages that the power utilization characteristics of each power utilization link, the technological feature, a production plan, a repair schedule and production working condition information are comprehensively considered, classified modeling is conducted, a predication value of the total load is obtained according to superposition of predication results, the predication value is in line with the reality of the iron and steel enterprise, information, technological rhythms and dynamic working condition information are fully considered in the process of dynamic predication, and models are better in adaptability.

The invention relates to a total energy demand and structure predicting system comprising a database module, an input module, an analysis prediction module, and an output module. The database module is used for storing relevant historical data of energy sources including coal, oil, natural gas and other renewable energy sources. The input module is used for invoking the relevant historical data ofenergy sources from the database module and extracting a historical energy prediction index. The analysis prediction module is used for predicting the total energy demand based on a gray prediction model, an energy Kuznets curve, and a multiple regression mathematical model according to the energy prediction index and predicting an energy demand structure based on a Markov chain. And the output module is used for outputting prediction results of the total energy demand and the energy demand structure. Compared with the prior art, the predicting system has advantages of high accuracy and adaptability.

A computer-executable method is executed by a CPU as the following steps of: obtaining an interested range in relation to a target typhoon and obtaining historical typhoons within the interested range from a wind and typhoon database; obtaining shortest distances from the respective historical typhoons to the target typhoon within the interested range; choosing a target ground grid point and obtaining normalized extreme wind speeds of the respective historical typhoons corresponding to the target ground grid point; obtaining extreme wind speeds probable for the target ground grid point by calculation according to the normalized extreme wind speeds and the highest wind speed of the center of the target typhoon; and arranging the extreme wind speeds in descending order, arranging the shortest distances corresponding to the respective extreme wind speeds, and obtaining the occurrence probability of the extreme wind speeds at the target ground grid point according to a formula.

The invention discloses a power optimization scheduling-based microgrid energy storage system state consistency control method, which belongs to the technical field of control of the microgrid energystorage system. The method adopts time-of-use price, new energy prediction output and energy storage unit battery pack state of energy SOE to determine an energy storage unit operation strategy on thebasis of considering energy storage charge and discharge efficiency and ensuring system active power balance, and considers an energy storage unit battery pack state of energy SOE imbalance problem and time-varying energy storage unit power charge and discharge bearing capability SOP, and a microgrid energy storage system power balance model is built; and besides, through a consistency protocol,energy storage units SOH and SOE are ensured to be consistent, the application performance of the energy storage unit in the energy storage system is improved, the overall charge and discharge times of the energy storage system is effectively reduced, and the service life is improved.

The invention belongs to the technical field of chaotic systems. The invention discloses a chaotic time sequence prediction method based on attention mechanism deep learning. The method comprises thefollowing steps: (1) constructing a chaotic time sequence data set; (2) carrying out phase space reconstruction on a chaotic time sequence; (3) training chaotic time sequence data by using an LSTM neural network model; (4) constructing a prediction-based attention mechanism model, (5) constructing an offline training model, and (6) carrying out online prediction. The chaotic time sequence prediction method based on attention mechanism deep learning is clear in model structure, has a reference value, and can be applied to the aspects of financial market prediction or energy prediction and the like of a chaotic system.

The invention relates to the technical field of energy management, and discloses a building energy management system, which solves the problems of single management means, weak comprehensive management ability and insufficient intelligence in the traditional energy consumption supervision of buildings. The building energy management system includes an energy consumption collection module, an energy consumption database, an energy consumption alarm module, an area energy consumption management module, an area energy consumption management module, an energy prediction management module, an energy report module, a visualization module, and a system management module. The building energy management system is applicable to building energy management.

The embodiment of the invention discloses a green base station shunting method and device in a hybrid energy network. Aiming at each green station, the method comprises the steps: employing a green energy prediction model at each time interval of each shutting time period; predicting green energy collected by each green base station at each time interval; obtaining the current residual energy of each green base station, thereby determining the first UE number shunted by each green base station at each time interval; and carrying out shunting of a conventional base station in the hybrid energy network. According to the embodiment of the invention, the green energy collected by each green base station at each time interval is determined according to the green energy prediction model, and the load numbers, which can be supported by the green base stations, are determined according to the current residual energy of the green base stations. The quality of services, which are provided for users, can be effectively guarantees while the energy consumption is reduced.

The invention relates to the technical field of energy consumption, in particular to an integrated energy predicting method, namely a consumed energy predicting method. The method includes selecting regional factor historical data and energy consumption requirement actual value as data samples according to particular years; combining with the acquired data, excavating relationships of different years and types, and searching for sample weights of regional factor samples corresponding to an energy consumption requirement actual value so as to determine the affecting level of regional factors of different years on energy consumption requirements; adopting the prediction algorithm based on linear mapping to predict a total annual consumption requirement value of one region of one year. The relationships of factors and prediction results can be represented objectively, the efficiency of the algorithm is improved, the energy consumption predicting process is more effective and rapid, the energy prediction accuracy can be improved on the economic development fresh normalcy and energy environment strong constraint conditions, the regional energy balance is calculated, and the reasonable and feasible energy development and safety guarantee policy can be determined finally.

The invention provides an automatic heating optimization system for a coke oven. The automatic heating optimization system comprises a feedforward control system and a feedback control system, whereinthe feedforward control system is used for acquiring real-time production data of the coke oven, calculating a set value of a control parameter through an energy forecasting model, and sending the set value to a coke oven control system to realize feedforward rough adjustment; the feedback system comprises a fire fall monitoring system, a mean flue temperature detection system and a waste gas oxygen content detection system, calculates a set value of a control parameter through a fuzzy control model, and sends the set value to the coke oven control system to realize feedback fine adjustment.The automatic heating optimization system for the coke oven calculates a set value of heated coal gas flow of the coke oven by acquiring and analyzing various condition factor variables generated by coking, and instructs heating control of the coke oven and optimizes the heating control, thereby realizing automatic control of uniform heating of the coke oven.

The invention discloses a greenhouse energy forecasting method based on a hybrid optimization algorithm. The greenhouse forecasting method based on the hybrid optimization algorithm comprises the following steps that (1), a differential equation of temperature inside a greenhouse is set; (2), parameters are initialized; (3), a population is initialized, and the initial values of the parameters needing recognizing are generated randomly; (4), gen is made to be 1; (5), if gen is smaller than or equal to gens_max, the step (6) is carried out, and if gen is greater than gens_max, the step (15) is carried out; (6), k is made to be 1; (7), if k is smaller than or equal to max_k, the step (8) is carried out, or the step (10) is carried out; (8), a current optimal solution and a globally optimal solution are obtained; (9), k is made to be k+1, and the step (7) is carried out again; (10), pop_size grains are selected by utilization of a preferred function; (11), information of reserved M grains is used for regenerating a population of the GA; (12), the grains obtained in the step (11) are used for intersection and variation of the GA; (13), the pop_size-M grains obtained by the GA and the reserved M grains of the PSO are combined to be pop_size new populations; (14), gen is made to be gen+1, and then the step (5) is carried out; (15), the minimum fitness function value and the parameters are output finally, and the forecast energy value of the greenhouse is output.

The invention discloses a photovoltaic power prediction method in combination with a photovoltaic power physical model and data driving, belonging to the field of new energy prediction technology of power systems. The method comprises the following steps: determining key weather features that affect the photovoltaic power by using a photovoltaic power physical model, and establishing key weather feature matrices of a historical period and a prediction period; and then separately establishing weather data matrices of the historical period and the prediction period to obtain input matrices of the historical period and the prediction period; performing feature extraction for the input matrices to obtain principal component feature matrices of the historical period and the prediction period; and selecting K historical periods with the nearest Manhattan distance from the principal component features of any prediction period, fitting to obtain a mapping relationship between the principal component features of the K historical periods and the photovoltaic power of the corresponding historical periods, and inputting the principal component features of the selected prediction period into the mapping relationship to obtain the photovoltaic power of the prediction period. According to the photovoltaic power prediction method disclosed by the invention, the photovoltaic power can be accurately predicted by using the photovoltaic power physical model, and stronger industrial application values can be achieved.

The invention belongs to the technical field of electric power system dispatching operation, and discloses an intra-day rolling optimization scheduling method considering electric quantity coordination. By introducing a goal planning method, maximum new energy consumption, tracking of a day-ahead output plan, tracking of a day-ahead electric quantity plan including contract decomposition electric quantity and minimum electric quantity plan completion rate deviation are taken as multiple targets, and power grid and unit state information, new energy prediction output information and daily plan electric quantity completion conditions which are acquired in real time are comprehensively considered. A dynamic rolling intra-day optimization scheduling model enables the power generation plan after rolling correction to improve the absorption of new energy, achieves the balance control of the completion progress of the unit daily electric quantity plan, solves the problems that the unit daily electric quantity control is difficult to adapt to the change of a power grid operation environment and is highly dependent on manual intervention, and ensures effective and fair execution of the daily electric quantity plan of the power plant.

The invention relates to an energy prediction method for optimizing gray model key parameters based on a king butterfly algorithm, and the method is technically characterized in that a gray GM (1, 1) prediction model is established for initial energy demand data; aiming at a development coefficient a and a grey action quantity u of the grey GM (1, 1) model, establishing an objective function of an average relative error between an initial energy demand value and a simulation value output by the grey prediction model; solving an optimal solution of the target function through a king butterfly algorithm, and determining a development coefficient a and a grey action quantity u of a grey GM (1, 1) model; and substituting the development coefficient a and the grey action quantity u into a grey GM (1, 1) model to predict the energy demand. The method is reasonable in design, the empire butterfly algorithm is applied to the gray GM (1, 1) prediction model, the applicability of the single gray GM (1, 1) prediction model to irregular fluctuation data caused by uncontrollable accidental factors is improved, the prediction precision of the gray algorithm is also improved, the method is relatively simple, and the prediction effect is better.

The invention discloses an intelligent household energy monitoring management system and a carbon asset management method. The intelligent household energy monitoring management system comprises an intelligent platform comprising a central control host, which is respectively connected with a display device and an operation device; an intelligent device system, which comprises a solar energy device system and an intelligent household electrical appliance system; a carbon asset statistical and management system, which comprises an energy evaluation unit, an energy data acquisition unit, an energy learning management unit, an energy prediction management unit, an energy carbon asset analysis unit, an energy management database unit, and an energy consumption and demand control unit. The central control host of the intelligent platform is respectively connected with the carbon asset statistical and management system and the intelligent device system, and is used to control the carbon asset statistical and management system and the intelligent device system. The operation device is connected with an input unit, and the display device is connected with a display unit. The resource management of the intelligent household is realized, and the carbon asset is accurately quantified, and therefore carbon footprint management and carbon trading management service are realized.

The invention provides a new energy cross-regional consumption method based on scene analysis. The method comprises the steps: respectively bringing new energy historical prediction error data of a two-region power grid, a new energy prediction power generation curve and a new energy load curve into a pre-constructed extra-high voltage DC cross-regional consumption model, obtaining a start-stop and direct-current line transmission optimization plan of each regional unit meeting the maximum expected value of the cross-regional new energy consumption electric quantity; executing the two-region unit start-stop and direct-current line transmission optimization plan to realize two-region new energy consumption. According to the technical scheme provided by the invention, the extra-high voltagedirect current cross-regional consumption model is established; the extra-high voltage direct current line, the sending end region and the receiving end region are used as research objects; the new energy consumption spaces of the two regions are fully coordinated, and the new energy consumption of the two regions is promoted.

The invention belongs to the technical field of energy prediction, in particular to an energy consumption prediction method. The method comprises the following steps: collecting sample data includinghistorical energy consumption, population, GDP, industrial structure, energy consumption structure, energy intensity, carbon emission intensity and total import and export amount; the sample data being subjected to dimensionless processing, and the grey relational degree of each sample data and energy consumption structure being calculated, and the input factors of the model being selected according to the order of grey relational degree; multiple IMF components being obtained by integrated empirical mode decomposition (EMD) based sequence denoising; the parameters of LS-SVM being optimized byusing the improved hybrid frog leapfrog algorithm, and the forecasting model being established to reconstruct the forecasting results, and the final energy consumption forecasting results being obtained. Experiments proved the EMD-ISFLA-LSSVM model predicts the energy consumption, and the predicting effect is remarkable.

Systems and methods for improving load energy forecasting in the presence of distributed energy resources in which a revised load forecast is calculated based on forecasted meteorological conditions data, forecasted wind and solar energy, forecasted load data, time data and time-series variables determined based on an analysis of the historical data. In exemplary embodiments, the revised load forecast is provided to energy management computer systems to enable appropriate levels of generation of conventional and renewable energy generation within the electric power grid.

The invention discloses an intelligent power grid prediction method based on cloud computing, and the method comprises the following steps: transmitting the real-time power supply and demand information of a microgrid to a cloud, and predicting the real-time state of each microgrid in a cloud computing environment; wherein the cost of energy prediction is composed of uploading, downloading and calculating costs of data, and the micro-grid optimization target based on cloud computing is to minimize the calculation cost. Energy waste and carbon dioxide emission in the working process of the microgrid are reduced to the maximum extent, and the green power grid communication is achieved. The method has remarkable effectiveness in the aspects of reducing energy consumption and reducing carbon dioxide emission, and meanwhile, the communication transmission in the energy prediction process is minimized.

The invention provides an iron and steel enterprise energy optimization scheduling system. The iron and steel enterprise energy optimization scheduling system comprises an energy monitoring subsystem,a production plan input subsystem, an energy prediction subsystem and an energy optimization scheduling subsystem. The energy monitoring subsystem is connected with the production plan input subsystem and the energy prediction subsystem, and comprises a coal gas monitoring module, a steam monitoring module and an electric power monitoring module. The energy monitoring subsystem is used for monitoring and storing energy output and consumption data in different production plans. The production plan input subsystem is used for inputting production plans in different time periods. The energy prediction subsystem is used for acquiring production plans and performing energy prediction according to the output and consumption data of energy in different production plans. The energy optimization scheduling subsystem is used for displaying a scheduling plan according to a prediction result of the energy prediction subsystem, receiving an external selection signal and selecting and executing thescheduling plan. The iron and steel enterprise energy optimization scheduling system can perform intelligent scheduling according to the production plan of the enterprise.

The invention provides a low-energy-consumption smart home system capable of predicting energy regeneration. The system comprises an intelligent control module, an energy prediction module, a sensor network module, a video monitoring module, an execution module, an energy module and a monitoring module. The intelligent control module is used for controlling and managing energy, a lighting system,a home theater, a security alarm and doors and windows. The energy prediction module is used for predicting the production capacity of renewable energy sources. The sensor network module is used for environmental data monitoring, the video monitoring module is used for environmental image acquisition. The execution module comprises household appliances, audios and videos, doors and windows and thelike. The energy module comprises an energy storage unit, a household wind turbine and a photovoltaic array, and the monitoring module comprises a mobile phone, a local display screen and a householdnetwork server. The system is characterized in that the energy production capacity is predicted through the energy prediction module, the corresponding energy working mode is selected, and thereforemaximization of energy benefits is achieved.

The invention relates to the technical field of energy consumption, in particular to an integrated energy predicting method, namely a consumed energy predicting method. The method includes selecting regional factor historical data and energy consumption requirement actual value as data samples according to particular years; combining with the acquired data, excavating relationships of different years and types, and searching for sample weights of regional factor samples corresponding to an energy consumption requirement actual value so as to determine the affecting level of regional factors of different years on energy consumption requirements; adopting the prediction algorithm based on linear mapping to predict a total annual consumption requirement value of one region of one year. The relationships of factors and prediction results can be represented objectively, the efficiency of the algorithm is improved, the energy consumption predicting process is more effective and rapid, the energy prediction accuracy can be improved on the economic development fresh normalcy and energy environment strong constraint conditions, the regional energy balance is calculated, and the reasonable and feasible energy development and safety guarantee policy can be determined finally.

The invention provides a method for improved building energy usage reduction by computer automation of optimized plant operation times and sub-hourly building energy forecasting to determine plant faults. The invention provides a computer system to derive the NTL, mechanical heat-up (MHL) and mechanical cool-down (MCL) lags and in conjunction with a readily available interval weather forecast, the system can output various signals to indicate optimized start and stop times for heating and cooling equipment. The algorithm to calculate the 15-minute energy forecast is used to indicate out-of-control conditions in the operation of the plant.

The invention belongs to the field of electric power automation, and discloses a day-ahead robust joint optimization method and system for an electric energy and auxiliary service market, and the method comprises the steps: receiving an electricity market clearing request, and requesting the clearing of the electricity market; calling the constraint condition to solve a pre-established day-ahead robust joint optimization model of the electric energy and the auxiliary service considering the new energy prediction error, and obtaining an electricity market clearing result; and outputting theelectricity market clearing result. The invention provides the day-ahead robust joint optimization method and system for the electric energy and auxiliary service market, aiming at the problems that the current new energy prediction error is relatively large and the phenomenon of wind and light abandoning is serious, and by providing the day-ahead robust joint optimization method and system for the electric energy and auxiliary service market considering the new energy prediction error, new energy fluctuation errors are considered, the robustness is high, and the model can adapt to large new energy fluctuation errors; the new energy consumption capability of the power grid is effectively provided; and effective reference can be provided for power market operation under large-scale new energy access.