专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2007087537A2 SYSTEM AND METHOD FOR GRADING ELECTRICITY DISTRIBUTION NETWORK FEEDERS SUSCEPTIBLE TO IMPENDING FAILURE 审中-公开
标题翻译：电力分配网络供应商的分级系统和方法不利于发生故障
公开(公告)号：WO2007087537A2
公开(公告)日：2007-08-02
申请号：PCT/US2007060926
申请日：2007-01-23
申请人： UNIV COLUMBIA , CONEDISON INC , ANDERSON ROGER N , BOULANGER ALBERT , WALTZ DAVID L , LONG PHIL
发明人： ANDERSON ROGER N , BOULANGER ALBERT , WALTZ DAVID L , LONG PHIL
IPC分类号： H04N7/173
CPC分类号： G06N99/005
摘要： A machine learning system creates failure-susceptibility rankings for feeder cables in a utility's electrical distribution system. The machine learning system employs martingale boosting algorithms and Support Vector Machine (SVM) algorithms to generate a feeder failure prediction model, which is trained on static and dynamic feeder attribute data. Feeders are dynamically ranked by failure susceptibility and the rankings displayed to utility operators and engineers so that they can proactively service the distribution system to prevent local power outages. The feeder rankings may be used to redirect power flows and to prioritize repairs. A feedback loop is established to evaluate the responses of the electrical distribution system to field actions taken to optimize preventive maintenance programs.
摘要翻译：机器学习系统为公用事业的配电系统中的馈线电缆创建故障敏感性排名。机器学习系统采用mart升级算法和支持向量机（SVM）算法生成馈线故障预测模型，对静态和动态馈线属性数据进行了培训。馈线由故障敏感性和对公用事业运营商和工程师的排名进行动态排名，以便他们可以主动为服务分配系统，以防止局部停电。馈线排名可用于重定向电力流量并优先进行维修。建立了一个反馈回路，以评估配电系统对优化预防性维护计划所采取的现场行动的响应。

2. 发明申请

WO2005020044A9 INNERVATED STOCHASTIC CONTROLLER FOR REAL TIME BUSINESS DECISION-MAKING SUPPORT 审中-公开
标题翻译：用于实时业务决策支持的无保留随机控制器
公开(公告)号：WO2005020044A9
公开(公告)日：2005-05-06
申请号：PCT/US2004028185
申请日：2004-08-26
申请人： UNIV COLUMBIA , ANDERSON ROGER , BOULANGER ALBERT
发明人： ANDERSON ROGER , BOULANGER ALBERT
IPC分类号： G06F1/00 , G06F3/00 , G06F3/02 , G06F7/00 , G06F15/18 , G06Q10/00
CPC分类号： G06Q10/04 , G06N5/022 , G06N99/005 , G06Q10/10
摘要： An Innervated Stochastic Controller (100, 102, 104, 106)) optimizes business decision-making under uncertainty through time. The Innervated Stochastic Controller (100) uses a unified reinforcement learning algorithm to treat multiple interconnected operational levels of a business process in a unified manner. The Innervated Stochastic Controller (100) generates actions that are optimized with respect to both financial profitability and engineering efficiency at all levels of the business process (110). The Innervated Stochastic Controller can be configured to evaluate real options. In one embodiment of the invention, the Innervated Stochastic Controller (100) is configured to generate actions that are martingales. In another embodiment of the invention, the Innervated Stochastic Controller (100) is configured as a computer-based learning system for training power grid operators to respond to grid exigencies.
摘要翻译：一个受控制的随机控制器（100,102,104,106））通过时间不确定性优化业务决策。神经网络随机控制器（100）使用统一的强化学习算法统一处理业务流程的多个互连操作级别。神经网络随机控制器（100）产生关于业务过程（110）的所有级别的财务盈利能力和工程效率优化的动作。神经网络随机控制器可以配置为评估实际选项。在本发明的一个实施例中，神经网络随机控制器（100）被配置为生成鞅的动作。在本发明的另一个实施例中，神经网络随机控制器（100）被配置为用于训练电网运营商响应电网紧急情况的基于计算机的学习系统。

3. 发明申请

WO2015013677A3 TOTAL PROPERTY OPTIMIZATION SYSTEM FOR ENERGY EFFICIENCY AND SMART BUILDINGS 审中-公开
标题翻译：用于能源效率和智能建筑的总物业优化系统
公开(公告)号：WO2015013677A3
公开(公告)日：2015-11-26
申请号：PCT/US2014048296
申请日：2014-07-25
申请人： UNIV COLUMBIA
发明人： ANDERSON ROGER N , BOULANGER ALBERT , BHANDARI VAIBHAV , BONIBERGER EUGENE , GAGNEJA ASHISH , GILBERT JOHN , KRESSNER ARTHUR , RAJAN ASHWATH , SOLOMON DAVID , FORDE JESSICA , WU LEON L , RATHOD VIVEK , MORENSKI KEVIN , SHOKRI HOOSHMAND
IPC分类号： H03F1/26
CPC分类号： G06Q50/16 , G06Q50/06
摘要： Techniques for managing one or more buildings, including collecting historical building data, real-time building data, historical exogenous data, and real-time exogenous data and receiving the collected data at an adaptive stochastic controller. The adaptive stochastic controller can generate at least one predicted condition with a predictive model. The adaptive stochastic controller can generate one or more executable recommendations based on at least the predicted conditions and one or more performance measurements corresponding to the executable recommendations.
摘要翻译：用于管理一个或多个建筑物的技术，包括收集历史建筑数据，实时构建数据，历史外生数据和实时外部数据，以及在自适应随机控制器处接收收集的数据。自适应随机控制器可以用预测模型生成至少一个预测条件。所述自适应随机控制器可以至少基于所述预测条件和对应于所述可执行建议的一个或多个性能测量来生成一个或多个可执行建议。

4. 发明申请

WO2014075108A3 FORECASTING SYSTEM USING MACHINE LEARNING AND ENSEMBLE METHODS 审中-公开
标题翻译：使用机器学习和ENSEMBLE方法预测系统
公开(公告)号：WO2014075108A3
公开(公告)日：2015-08-20
申请号：PCT/US2013069762
申请日：2013-11-12
申请人： UNIV COLUMBIA
发明人： ANDERSON ROGER N , BOULANGER ALBERT , WU LEON L , BHANDARI VIABHAV , SARKER SOMNATH , GAGNEJA ASHISH
IPC分类号： G06N5/02
CPC分类号： G06Q10/06315 , G06N5/04 , G06N7/005 , G06N99/005 , G06Q10/0631 , G06Q10/067 , G06Q10/08
摘要： Techniques for determining forecast information for a resource using learning algorithms are disclosed. The techniques can include an ensemble of machine learning algorithms. The techniques can also use latent states to generate training data. The techniques can identify actions for managing the resource based on the forecast information. The resource can include energy usage in buildings, distribution facilities, and resources such as Electric Delivery Vehicles. The resource can also include forecasting package volume for businesses.
摘要翻译：公开了使用学习算法确定资源的预测信息的技术。这些技术可以包括机器学习算法的集合。这些技术还可以使用潜在的状态来生成训练数据。这些技术可以根据预测信息识别用于管理资源的动作。该资源可以包括建筑物的能源使用，配电设施以及电动车辆等资源。该资源还可以包括为企业预测包量。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式