10results about How to "Improve Load Forecasting Accuracy" patented technology

The invention discloses a motion data management method and system based on AI body measurement, and relates to the technical field of artificial intelligence and machine learning, and the method comprises the steps: collecting motion data of each user, and carrying out the preprocessing; dividing user intervals by using a K-means clustering algorithm, constructing a load prediction model by using a fuzzy BP neural network, and obtaining a final load prediction value by using an improved adaptive genetic algorithm; and constructing a regression model by using a QHD reinforcement learning algorithm, dynamically adjusting a discount factor, outputting a training load adjustment strategy, and adjusting the discount factor according to feedback. User training load intervals are accurately divided through a K-means clustering algorithm, distribution of personalized training loads is ensured, the load prediction precision is improved by using a fuzzy BP neural network and an IAGABP algorithm, the weight and bias of the network are optimized, a local optimal solution is avoided, the prediction accuracy is improved, a QHD reinforcement learning algorithm and a dynamic discount factor are combined, and the prediction accuracy is improved. And a strategy of dynamically adjusting the training load is realized.

The invention relates to a virtual power plant bidding strategy optimization method based on a chaotic game optimization algorithm. The method comprises the following steps: generating an initial bidding strategy of a virtual power plant through chaotic mapping; each virtual power plant receives feedback information of the market, games by considering factors of cost, income, fluctuation of photovoltaic power generation, scheduling cost and attenuation of an energy storage battery and service life of equipment, and adjusts a bidding strategy of the virtual power plant; punishment income is applied to bidding behaviors violating market ethics or benefit distribution constraints; calculating the income of the power plant according to the adjusted strategy, and updating the bidding strategy of each virtual power plant; and repeating the game process until a convergence condition is reached, and outputting a virtual power plant bidding strategy. Compared with the prior art, the bidding strategy of the virtual power plant is more flexible and adaptive by using the randomness and unpredictability of the chaotic system, and meanwhile, the fairness, sustainability and healthy market development of the system are ensured by introducing ethical constraint and equipment life management.

The invention discloses a power distribution network load prediction method and device based on multistage information interaction transmission and a storage medium, and relates to the technical field of power systems. According to the load type historical power data of the plurality of power distribution network areas, dividing the power distribution network area to be measured to obtain a sub-area division result; constructing a multi-level graph structure system according to a sub-region division result, calculating a node association relationship of each level, and forming a corresponding level adjacent matrix according to the node association relationship of each level; and taking the adjacent matrix of the corresponding hierarchy and the load type historical power data of the to-be-tested power distribution network region as input, and outputting through the hierarchical graph convolutional neural network prediction model to obtain a target prediction result. According to the method, on the basis of distribution network area load division, the space-time relevance of each level is mined, distribution network load prediction is realized, and the prediction precision is effectively improved.

The invention relates to the technical field of energy management and intelligent control, and provides a ground source heat pump system end load prediction and adaptive correction method and system.The method comprises the steps that a day-ahead load prediction model is built, and a day-ahead load prediction value is obtained through calculation; constructing a day-ahead load prediction deviation correction model to obtain a day-ahead load prediction deviation correction value; obtaining a day-ahead load prediction value vector based on the day-ahead load prediction deviation correction value; constructing an intra-day load prediction model, and calculating to obtain an intra-day load prediction value; and respectively calculating the credibility of the intra-day load predicted value, the predicted value at the corresponding moment in the day-ahead load predicted value vector and the historical actually measured load data, and calculating to obtain a predicted load issuing value based on the intra-day load predicted value, the predicted value at the corresponding moment in the day-ahead load predicted value vector and the credibility. According to the invention, by constructing the double-layer load prediction model and combining the meteorological parameter correction model, the adaptability of the system to the dynamic change of the environment is improved, and the load prediction precision is improved.

The invention discloses an automobile charging station load intelligent prediction method and system, and relates to the technical field of new energy, and the method comprises the steps: collecting the charging state information of each automobile charging station in a target range, so as to construct a plurality of load intensity coefficients Xfh of the automobile charging stations, and carrying out the comparison of the load intensity coefficients Xfh, marking a number group of high-load automobile charging stations, and sending a load demand prediction instruction; according to the method, charging piles in a high-load automobile charging station number group are continuously monitored, a radio frequency identification technology is combined, a load demand index Zyc is obtained through fitting, after threshold comparison is carried out on the load demand index Zyc, whether the automobile charging stations in the high-load automobile charging station number group meet the automobile charging demand of the day or not is judged, and a corresponding grade regulation and control instruction is generated and executed; according to the method, through real-time monitoring, dynamic analysis and accurate regulation and control, the resource allocation of the automobile charging station is effectively optimized, and the charging user experience is improved.

The invention discloses a data center joint optimization method and system, belongs to the technical field of data center management, and can solve the technical problems of inaccurate load prediction and low resource allocation efficiency of a data center. The method comprises the steps that the load condition of a data center in a historical period is obtained, a data center load data set is formed, a time sequence is obtained through the data center load data set, a GM model is established, the GM model comprises a GM model difference equation and a GM model prediction equation, the GM model difference equation is obtained through the time sequence through the GM model, and the GM model prediction equation is obtained through the GM model. The GM model difference equation comprises an adjustment parameter, a bird flock algorithm is used to obtain an optimal value of the adjustment parameter, the optimal value is substituted into the GM model prediction equation in the GM model, a prediction sequence is obtained, and a data center optimization strategy is executed according to the prediction sequence.

The invention relates to an electric power system operation optimization method and device based on a JSO-SVM model and dynamic adjustment, and belongs to the technical field of electric power systems, and the method comprises the following steps: collecting data related to the operation of an electric power system, carrying out the data processing, finding out the historical number of days similar to the target daily load characteristics through calculating the daily feature similarity, and carrying out the calculation of the target daily load characteristics. The related data comprises historical load data, meteorological conditions and user behavior modes of the power system; establishing a JSO-SVM load prediction model based on SVM and JSO algorithms, and performing parameter optimization through model training; setting a target function, and performing real-time load prediction by using a JSO-SVM load prediction model; and according to a load prediction result obtained in real time, applying a dynamic adjustment algorithm to optimize an operation strategy of the power system. According to the method, accurate prediction and real-time dynamic optimal scheduling of the power load are realized, and the stability and the economical efficiency of a power system are improved.

The invention discloses a multi-element load analysis and prediction method for an integrated energy system, and the method comprises the steps: data preprocessing: carrying out the preprocessing of original load data, and obtaining data which can better reflect a load change rule; determining influence factor correlation; feature factor extraction: firstly performing normalization processing on existing load data, adopting an RCNN model, setting related parameters, and extracting more representative influence factors, the input quantity of the RCNN model being influence factor values such as input factors determined in the previous step, and the output quantity being input of an SVR model; and load prediction: setting related parameters in the SVR model, taking an input quantity in the prediction model as an influence factor output value of the RCNN model, and outputting to obtain a predicted load value. According to the multi-element load analysis and prediction method for the integrated energy system, the accuracy of load prediction can be improved; the coupling characteristics among the multi-element loads of the integrated energy system are analyzed, so that the prediction tasks of the multi-element loads obtain redundant implicit information, and the prediction precision is improved.

The invention relates to the technical field of centralized heating, in particular to a heat supply pipe network dynamic balance adjusting system based on the Internet of Things, which comprises a sensing layer, a network layer, a control layer and an execution layer, and is characterized in that the sensing layer acquires parameters such as pipe network pressure, temperature and flow through a low-power-consumption sensor in a full-link manner, and transmits the parameters to the network layer through a LoRaWAN protocol; the network layer preprocesses data through an edge gateway and realizes encrypted transmission by means of 5G; the control layer integrates heat supply load prediction, particle swarm optimization and a self-learning algorithm, and accurately generates an adjustment instruction; the execution layer drives the electric adjusting ball valve to complete opening adjustment, and closed-loop control is formed. The flow deviation rate can be controlled within + / -4%, the indoor temperature fluctuation is smaller than or equal to 0.5 DEG C, energy consumption is reduced by 15%-20%, remote intelligent operation and maintenance are supported, the system is suitable for various scenes such as conventional residential quarters, large commercial complexes and old communities in cold regions, heat supply balance and energy saving performance are effectively improved, and application and popularization value is remarkable.

The application provides a kind of GAPSO algorithm-based power station load tracking method, including data acquisition and preprocessing, and related data of power grid and power station are collected and processed;A power grid load forecasting model based on GAPSO algorithm is constructed, variables are determined, and an optimized neural network is constructed;The charge-discharge strategy of energy storage power station is optimized, the objective function is established and solved;Real-time scheduling and response are carried out, data monitoring, decision-making and adjustment of power station state are carried out;Multi-objective optimization adjustment is carried out, function is constructed, solved and continuously improved.The application improves the load forecasting accuracy, optimizes the power station operation strategy, enhances the real-time scheduling and response capability, realizes the multi-objective comprehensive optimization, effectively improves the operation efficiency and adaptability of energy storage power station in power system.