83 results about "Online decision making" patented technology

Techniques are provided for use in accordance with such systems as web sites operating electronic commerce (e-commerce) applications, interactive voice response (IVR) systems and workflow systems for providing automated monitoring of user activity and personalized action taking based on such activity, in accordance with an on-line decision support mechanism which combines formal and heuristic reasoning. In a web-based system, for example, the on-line decision support provided in accordance with the invention can be used in a wide variety of e-commerce applications requiring automated, real-time, intelligent interventions, including targeted promotions and discounts, assisting with navigation through self-help material, supporting dynamic price negotiations, and even selecting large portions of page content.

A computerized system and method of constructing and expanding search queries for conducting searches through information sources. The system enables retrieving a category options tree, allowing a user to define a category route by selecting a category-node, which defines a search-category. The system may further enable retrieving a query scenario tree, having a hierarchal structure comprising query nodes, where the retrieved query scenario tree is associated with an initial input query, inputted by a user. Each query node defines a query route enabling to construct the content and structure of an expanded search query. The system enables selecting a query node of the retrieved query scenario tree, according to an online decision making process, which analyses the search-category in relation to available query routes in to allow selecting a query node from the retrieved scenario tree that is most compatible with the search-category.

The invention belongs to the field of maintenance decision-making of hydraulic equipment, and relates to a method for the optimal maintenance decision-making of hydraulic equipment with risk control. The method mainly comprises three steps: 1) judging whether a system is in a status of defect by using a variable-weight association rule algorithm, if so, calculating the probability values of occurrences of latent faults of the system; 2) calculating the comprehensive evaluation value for the consequence of each latent fault by using a BP neural network; and 3) multiplying the probability values obtained in step 1 by the comprehensive evaluation values obtained in step 2 so as to obtain the VaRs (values-at-risk) of the latent faults, judging whether the VaRs are more than a specified threshold, if so, ranking the VaRs in descending order so as to determine the maintenance sequence; otherwise, returning to the step of monitoring. The method can judge whether a device is in a status of defect, judge the type of the latent fault and calculate the probability values of occurrences of latent faults only through a calculation; and compared with traditional risk maintenance methods, the method of the invention improves the accuracy of fault diagnosis, speeds up the diagnosis speed, and provides a better reference for online decision-making.

A method for controlling coal grinder includes selecting measurement points on grinder and obtaining measured data, using artificial control platform to realize on line self optimizing for submitting out a set of optimum control policy on real time, applying said control information to control action of executing mechanism for coal grinder. A control system for realizing the method is also disclosed.

he invention discloses a method for comprehensive online prevention and control decision making, and the method meets the requirements for the constrains of the multiple types of safety and stability,and belongs to the prevention and control technical field of safety and stability in electric power systems. The method, directed to the features of large power grids, such as intertwining of multiple types of safety and stability problems and insufficient time for online decision making, proposes control performance indexes of adjustment measurements of electric generators, loads and capacitivereactance devices for a total of 11 types of safety and stability, such as transient safety and stability, dynamic safety and stability and static safety and stability, and independently lining up andselecting different types of measurements based on a comprehensive performance index of safety and stability, and enumerating and combining measurements selected by type, and applying a cluster computing platform to implement a quantitative estimation of the safety and stability of the measurements enumerated and combined; defining the calculation of the comprehensive decision-making of the transient safety and stability and the dynamic safety and stability as a phase, defining the calculation of the decision-making of the static safety and stability as an independent phase, optimizing the solution of the transient safety and stability and dynamic safety and stability problems, and adopting a cyclical iteration calculation scheme. The method can implement a method for fast and optimized online prevention and control decision making taking the constrains of multiple types of safety and stability into consideration.

A computerized system and method of constructing and expanding search queries for conducting searches through information sources. The system enables retrieving a category options tree, allowing a user to define a category route by selecting a category-node, which defines a search-category. The system may further enable retrieving a query scenario tree, having a hierarchal structure comprising query nodes, where the retrieved query scenario tree is associated with an initial input query, inputted by a user. Each query node defines a query route enabling to construct the content and structure of an expanded search query. The system enables selecting a query node of the retrieved query scenario tree, according to an online decision making process, which analyses the search-category in relation to available query routes in to allow selecting a query node from the retrieved scenario tree that is most compatible with the search-category.

A computerized system and method of constructing and expanding search queries for conducting searches through information sources. The system enables retrieving a category options tree, allowing a user to define a category route by selecting a category-node, which defines a search-category. The system may further enable retrieving a query scenario tree, having a hierarchal structure comprising query nodes, where the retrieved query scenario tree is associated with an initial input query, inputted by a user. Each query node defines a query route enabling to construct the content and structure of an expanded search query. The system enables selecting a query node of the retrieved query scenario tree, according to an online decision making process, which analyses the search-category in relation to available query routes in to allow selecting a query node from the retrieved scenario tree that is most compatible with the search-category.

The invention discloses an on-line decision support method for responding to a power quality early warning. The on-line decision support method for responding to the power quality early warning comprises the following steps of (1) establishing a power quality early warning index system, (2), collecting data, (3) analyzing the early warning, (4) extracting a data feature quantity, (5) classifying indexes, (6) establishing a rule system, (7) conducting forward reasoning to obtain a decision support result, (8) and ending the on-line decision support analysis process. The on-line decision support method for responding to the power quality early warning is based on the established rule system, on-line decision support is conducted on a power quality early warning analysis result, and therefore a reasonable and workable expert decision suggestion can be provided for various power quality problems happening to a power system.

The invention discloses an intelligent signal processing system of power grid equipment. A data layer is provided with a database module and a real-time information receiving module, an application layer is provided with an auxiliary decision making module, an abnormal signal association analysis and diagnosis module and a fault signal analysis and diagnosis module, and a user layer is provided with a human-machine interaction module and an online decision making module. The system comprises a real-time state and a research state, both of which can realize the association analysis and diagnosis of an equipment abnormal signal before the occurrence of an accident, a fault signal diagnosis function when the accident occurs, and timely assistance to the decision of the regulation and control personnel; and meanwhile, a historical signal analysis and diagnosis result can be inquired so as to provide historical data to the case analysis and training of the regulation and control personnel. The system has expandability and can be embedded with an SCADA / EMS system; and meanwhile, the system reserves partial interfaces to facilitate the compatibility with other systems. The intelligent signal processing system of the power grid equipment ensures the universality and independence of the system function.

The invention discloses an online emergency control decision-making method considering transient state and static state security and stability constraint, and belongs to the security and stability emergency control technical field of the electric power system. For overcoming the problems that multiple kinds of problems exiting in the security and stability of the large power grid are mingled, and the online decision-making time is short, different types of control measures are chosen specific to different kinds of problems exiting in security and stability; the control measures of each type are screened based on the control performance indexes separately; the screened measures of different controllable equipment are enumerated and combined; the enumerated and combined measures are screened through the power sensitivity based overload security verification and power frequency characteristic based transient state frequency security verification; and finally, the screened enumerated and combined measures are subjected to transient state and static state security and stability quantitative evaluation by adopting a cluster computing mode. The calculation strategies are classified and sequenced specific to the problems exiting in security and stability, so that the rapid and optimized decision making of the online emergency control considering the transient state and static state security and stability constraint is realized.

The invention provides an intelligentized charging system with a responding function for electricity demand and a method thereof. The system comprises a control module, an attribute storing module, an information obtaining module, a strategy storing module, an on-line decision-making module, an off-line decision-making module and a power regulating module. The charging system has an intelligent control function for demand response, and automatic control for the demand response can be realized. Because the novel intelligentized charging system with the function of demand response can perform automatic charging regulation according to the peak valley conditions of current load of a power grid, electricity price adjustment conditions and other power grid state, the maximization of the utilization of electrical energy is realized, and the charging system has a promoting action for improving a charging mode and an electricity using mode no matter from a practical perspective or an environment protection perspective.

The invention provides a Web application adaptive resource allocation method based on machine learning, which comprises the following steps: step S1, the physical machine operating system is virtualized and divided into two virtual machines, and the two virtual machines run their respective operating systems respectively; step S2, two machine learning models are provided for the two virtual machines respectively; a response time prediction model based on machine learning is used to predict the response time of a given environment; step S3, based on the online decision-making mechanism based onthe genetic algorithm, the fitness function of the response is formulated according to the above model to search for the software and hardware resource allocation scheme with the optimal response time. The method can train the prediction model from the historical data and automatically allocate the software and hardware resources for the Web application service according to the genetic algorithm.

Example implementations described herein are directed to detection of anomalous events and locations on the transmission power system using phasor management unit (PMU) data, which provides information to grid operators for online decision support. From the high-resolution time synchronized PMU data, the transient abnormal events can be monitored and locations can be disclosed to operators for remedy actions. Utilization of PMU information for such decision support compliments operation practices relying on supervisory control and data acquisition (SCADA) measurements at much lower data resolution. Accurate identification of event locations can further advise grid operators the root cause of disturbances and illuminate possible cascading failures. Implementations of the proposed technology may improve the resilience and reliability of the transmission power systems.

The invention discloses a comprehensive optimization method for a power grid in a high-permeability region of a distributed power supply, and the method comprises the following steps: S1, building a mathematic model for the comprehensive optimization of a power transmission network according to the operation safety constraint of a system through taking the minimization of power generation cost asa target; S2, modeling a decision process of comprehensive optimization of the power transmission network by using a Markov process, and defining a corresponding state space, an action space and a reward function; S3, employing a neural network fitting value function, employing parameter freezing, experience playback and progressive greedy methods for training, and initializing neural network parameters and control parameters; S4, performing simulation training locally to obtain a trained evaluation value network; S5, performing online operation control by using the trained evaluation value network. Through an efficient deep reinforcement learning algorithm, the optimal control strategy is learned in interaction with the simulation model, the online decision time is shortened, and a powergrid comprehensive optimization scheme is quickly obtained.

This non-provisional patent application pertains to an embodiment of an online decision engine for applied research and statistics. Users will interact with a point-and-click interface that asks questions to guide researchers to the correct research methods and statistics to answer their research questions. A number of decision engines exist in the overall decision engine. These decision engines include: Research questions, research designs, statistical power, sample size, evidence-based medicine, epidemiology, diagnostic testing, variables, statistics, databases, surveys, psychometrics, and education. Users are presented a series of questions and based on their answers and clicking on buttons with the answers embedded in them, they are linked to webpages with the correct research method or statistical test based on their responses to the questions presented.

The invention introduces an on-line decision making method for load current de-icing of a transmission line. The method comprises the following steps: 1, acquiring data; 2, calculating; 3 calculating power flow; 4, calculating stability; 5, performing on-line decision making; simultaneously, calculating time required for de-icing the transmission line which can adopt load current de-icing; and displaying the information in a mode of conventional graphic or table. On the premise of ensuring that an electric network operates safely and stably, the method can give full play to the advantages of load current de-icing, reduce the labor intensity of dispatchers, automatically and make the decision on line that whether the load current de-icing can be used, reduce the safety risk to the electric network brought by the load current de-icing, and can generate great social benefit and economic benefit.

The invention provides a cloud intelligent production optimization scheduling online decision-making method based on case-based reasoning. The method comprises the steps of utilizing historical data of a cloud intelligent production scheduling process, constructing a scheduling process case library, constructing case description of a current to-be-decided cloud intelligent production scheduling problem by adopting online detected real-time data, carrying out case retrieval and case reuse to obtain a scheduling scheme of the current to-be-decided cloud intelligent production scheduling problem,and finally modifying and storing cases to complete updating of the case library. Thus, the online intelligent decision making of the cloud intelligent production optimization scheduling process is realized, the knowledge of the cloud intelligent production scheduling process is effectively reused, the resource sharing is finally realized, the enterprise is helped to save resources, and the production efficiency is improved.

The invention discloses a DQN and MCTS-based inter-container multi-field bridge dynamic scheduling method. The method comprises the steps: training a multi-field bridge dynamic scheduling model through a DQN to obtain a deep Q network which can make an optimal decision-making capability under random interference, guiding the MCTS through the deep Q network to carry out online decision-making of an inter-container multi-field bridge of a storage yard, and giving a next scheduling decision of the field bridge. According to the method, a multi-field-bridge dynamic scheduling model autonomously explores the yard environment through a reinforcement learning method, a large number of learning samples are generated, the problem that real field-bridge scheduling samples are lacked and difficult to obtain is solved, meanwhile, the MCTS and the DQN are combined to solve the multi-field-bridge dynamic scheduling problem between box intervals, the optimal scheduling decision of each step is given online, and the robustness of the decision scheme under uncertain interference is improved.

The invention belongs to the field of distributed power supply optimal scheduling, and discloses a distributed power supply optimal scheduling method, system and device and a storage medium, and the method comprises the steps: obtaining renewable energy power generation prediction, load prediction and state information of each device in a region collected by an intelligent agent in each region; based on the renewable energy power generation prediction, the load prediction and the state information of each device, utilizing a pre-trained distributed power supply optimization scheduling model to carry out optimization scheduling decision, and obtaining the optimal output of the controllable device; and issuing a scheduling instruction to the controllable equipment in the region based on the optimal output of the controllable equipment. The method can adapt to the uncertainty of the output and load of the distributed power supply, does not depend on the accurate prediction of the source load, gives an optimal scheduling result in real time according to the random change of the source load, and greatly improves the online decision-making speed compared with a centralized optimization method.

The invention relates to an online virtual resource allocation method based on virtual machine pre-deployment, and belongs to the field of cloud computing and data center resource management. An online virtual resource allocation framework based on virtual machine pre-deployment is constructed, and the framework realizes organic combination of virtual machine deployment offline optimization and virtual machine deployment online decision making through a virtual machine pre-deployment mode; secondly, designing an online virtual resource allocation process based on the framework so as to realizerapid virtual resource allocation, and meanwhile, improving the physical resource utilization rate of the data center after resource allocation by preferentially using a pre-deployed virtual machineto complete resource allocation; quick response to a virtual machine request can be realized through virtual machine online deployment, and offline resource optimization can be performed on virtual machine deployment, so that the physical resource utilization rate of the cloud data center is improved.

The invention provides a fault response decision making device in a flight control system, which comprises an onboard device and an off-board device. The hardware components of the onboard device comprise a decision making-used computer, a human-machine interaction touch panel and a data communication link, wherein the decision making-used computer and the human-machine interaction panel are connected with an aircraft cockpit through a data communication link; the decision making-used computer and the human-machine interaction panel are connected through a data communication link; and the human-machine interaction touch panel can interact with a pilot. In the fault response decision making device and the method, the whole online decision making process of the onboard device has effects ofquickness, correctness and scheme optimization, the optimal fault processing scheme can be quickly provided for the pilot in a complicated environment and a high-pressure and high-load scene, and theflight safety and the reliability are improved.

The invention relates to an Android computing migration online decision-making method based on code analysis. The method comprises the following steps of firstly, modeling the classes, methods, objects and calling relations of the applications based on a code analysis technology; secondly, on the basis of dynamic analysis, modeling an application model of the method execution time and the data transmission of the applications; and finally, based on the application model, proposing a context model help decision, and carrying out decision scheme evaluation and optimal scheme selection through afitness function. According to the method, the response time of each migration decision scheme is calculated based on an object call graph, the method execution time and the data transmission quantityobtained by the code analysis technology, and the optimal deployment scheme is obtained, so that the execution time and the energy consumption can be reduced.

The invention discloses an online decision-making method and an online decision-making device for inhibiting new energy linkage off-grid based on an off-grid time sequence. The method is characterizedby, for an anticipated fault set of which the new energy linkage off-grid amount does not meet the requirement, identifying a key new energy unit of linkage off-grid according to the new energy off-grid time sequence characteristics; calculating control performance indexes of new energy unit, capacitive reactance device, direct current and the conventional unit measures for inhibiting the new energy off-grid according to the off-grid reasons of the key new energy unit; screening out effective control measures, carrying out sorting according to measure priorities and the control performance indexes, and carrying out enumerating and combining to generate a decision scheme; and solving an auxiliary decision scheme which is minimum in control cost and meets the requirements of safety, stability and new energy off-grid margin through cluster parallel check. On the premise of ensuring safe and stable operation of the power grid, decision support is provided for improving the grid-connectedreliability and the absorptive capacity of new energy.

A power system splitting decision space screening method belongs to the technical field of power safety. The existing power system splitting decision-making methods are limited by the scale of the power grid, or the number of regions of the simplified power grid, and cannot be applied to large-scale power grid online applications. On the premise of not losing the solution feasible solution, the present invention utilizes the physical characteristic that the spatial distribution of the solution feasible solution of the power system has regularity, and does not divide the system area and then aggregate it into nodes, but directly screens the original network The subgraph method to reasonably reduce the size of the decision space. The method will make the existing conventional decoupling strategy search methods applicable to large-scale systems that have not been sufficiently simplified, so that the online decision-making of decoupling strategies in large-scale power grids is really possible. The invention does not rely on human experience, and develops the coherent recognition method that only groups a small number of generator nodes into a large-scale topology recognition method including load nodes, which satisfies the topology analysis of large-scale power grids.

Methods and systems are presented for configuring an online decision making engine based on performing simulations of one or more decision making algorithms using online data. A decision making system may obtain first programming codes that implement a decision making algorithm in a first programming language corresponding to the online decision making engine. Without any human interference, the decision making system may automatically generate second programming codes that implement the decision making algorithm in a second programming language corresponding to database system. The decision making system may then simulate the decision making algorithm using the second programming codes to generate simulation results. Based on the simulation results, the decision making system may configure (or re-configure) the online decision making engine.

The invention relates to a microgrid controller based on an artificial intelligence control method. According to the invention, a historical sample database is used to form an observation set of a deep deterministic policy gradient network to perform action exploration; training is performed according to continuous interactions between the microgrid controller and a microgrid system environment; mapping relationships between microgrid operation conditions and coordination control results are directly constructed; the microgrid controller directly uses a microgrid controller model which is trained offline to carry out rapid online decision making, so that the calculation and response speed is very high; and an offline training sample library is periodically updated to realize rolling optimization of the model and continuous improvement of policies. Therefore, real-time coordination control of the microgrid controller on a power supply, a grid, loads and storage in a system is realized, and the high efficiency and the robustness of the microgrid controller are effectively improved.

The invention discloses a power enterprise financial data management system based on big data. The overall architecture of the system is divided into five layers: a data source layer, a data storage layer, a big data parallel processing layer, a big data parallel analysis layer and a data visualization layer. The data source layer provides internal data and external data; wherein the data storagelayer stores the data, the big data parallel processing layer classifies the data, the big data parallel analysis layer analyzes the processed data and performs behavior prediction, and the data visualization layer performs data visualization after analyzing the obtained data in the form of graphs and network graphs. Big data storage management based on NoSQL, financial big data preprocessing based on Hadoop and a financial big data analysis mining algorithm provide theoretical basis and basic technical support for online decision analysis, and the management efficiency and accuracy of financial data of power enterprises are greatly improved.

The invention discloses an autonomous avoidance maneuvering method for multiple interceptors by a spacecraft based on reinforcement learning, and belongs to the technical field of anti-interception. According to the method, the problem of low success rate of avoiding multiple interceptors by existing spacecraft programmed maneuver is solved. The invention provides an autonomous avoidance maneuvering method based on a deep neural network, which is not limited by the quality and material of a spacecraft, consists of two parts, namely an offline training system and an online decision-making network, uses less computing resources of the spacecraft, has real-time decision-making capability, and improves the avoidance success rate of the spacecraft for multiple interceptors. When the autonomousmaneuver avoidance method is adopted for the spacecraft, the average maneuver avoidance success rate is 49%, and the avoidance success rate is increased by 29%. According to the method, the engine switching time in the avoiding process can be effectively shortened, and more energy is saved. The method can be applied to autonomous avoidance of multiple interceptors by a spacecraft.