交替的电流(AC)偶然受限的最佳功率流(CC-OPF)问题解决了发电不确定性下发电和交付的经济效率。由于可再生能源量大量,后者是现代电网的内在固有的。尽管取得了学术上的成功,但AC CC-OPF问题是高度非线性和计算要求的,这限制了其实际影响。为了改善AC-OPF问题的复杂性/准确性权衡,本文提出了一种快速数据驱动的设置,该设置使用稀疏和混合的高斯流程(GP)框架,以模拟具有输入不确定性的功率流程方程。我们提倡通过数值研究对拟议方法的效率,而与最新方法相比,多个IEEE测试用例的效率快两倍,更准确。
translated by 谷歌翻译
从数据中揭示馈线拓扑对于提高情境意识和适当利用智能资源在电源分配网格中至关重要。该教程总结,对比和建立了对拓扑识别的最新作品与检测方案之间针对电源分配网格提出的有用联系。%在不同的测量类型,可观察性和采样方面。主要重点是突出使用分配网格中测量设备有限的方法,同时使用电源流体物理和馈线的结构特性来增强拓扑估算。可以从传统的方式或积极地收集相量测量单元或智能电表的网格数据,或者在执行网格资源并测量馈线的电压响应时积极收集。在不同的仪表放置方案下,对馈线可识别性和可检测性的分析主张进行了审查。可以通过具有各种计算复杂性的算法解决方案来确切或大致获得此类拓扑学习主张,从最小二乘拟合到凸优化问题,从图形上的多项式时间搜索到综合计划。该教程渴望为研究人员和工程师提供有关当前可行分配网格学习和对未来工作方向的见解的了解。
translated by 谷歌翻译
由于负载和可再生能源的不确定性日益增长,对现代电网的安全和最佳运行产生了突出的挑战。随机最佳功率流(SOPF)制剂提供了一种通过计算在不确定性下保持可行性的派遣决策和控制政策来处理这些不确定性的机制。大多数SOPF配方考虑了简单的控制策略,例如数学上简单的仿射策略,类似于当前实践中使用的许多策略。通过机器学习(ML)算法的功效和一般控制政策的潜在好处的效果,我们提出了一个深度神经网络(DNN)基础的政策,该政策是实时预测发电机调度决策的不确定。使用解决SOPF的随机原始双重更新来学习DNN的权重,而无需先前一代训练标签,并且可以明确地解释SOPF中的可行性约束。 DNN政策对更简单的政策和它们在执行安全限制和产生附近的近最佳解决方案中的功效的优点在于机会在许多测试用例上受到限制的制定的情况下。
translated by 谷歌翻译
We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\varphi(X)$ of data $X$ to estimate a target $Y$, while being conditionally independent of a distractor $Z$ given $Y$. Both $Z$ and $Y$ are assumed to be continuous-valued but relatively low dimensional, whereas $X$ and its features may be complex and high dimensional. Relevant settings include domain-invariant learning, fairness, and causal learning. The procedure requires just a single ridge regression from $Y$ to kernelized features of $Z$, which can be done in advance. It is then only necessary to enforce independence of $\varphi(X)$ from residuals of this regression, which is possible with attractive estimation properties and consistency guarantees. By contrast, earlier measures of conditional feature dependence require multiple regressions for each step of feature learning, resulting in more severe bias and variance, and greater computational cost. When sufficiently rich features are used, we establish that CIRCE is zero if and only if $\varphi(X) \perp \!\!\! \perp Z \mid Y$. In experiments, we show superior performance to previous methods on challenging benchmarks, including learning conditionally invariant image features.
translated by 谷歌翻译
气候变化增加了损害电力系统可靠性并导致多次设备故障的极端天气事件(风暴,大雨,野火)的数量。实时和准确检测潜在线路故障是减轻极端天气影响并激活紧急控制的第一步。功率平衡方程非线性,极端事件中的发电不确定性增加,缺乏电网可观察性会损害传统数据驱动的失败检测方法的效率。同时,基于神经网络的现代化的机器学习方法需要大量数据来检测事故,尤其是在改变时间的环境中。本文提出了一个具有物理信息的线路故障检测器(字段),该探测器利用网格拓扑信息来减少样本和时间复杂性并提高定位准确性。最后,我们说明了与最先进的方法相比,与各种测试用例相比,我们的方法的优越性实证性能。
translated by 谷歌翻译
近年来,电力发电已导致美国超过四分之一的温室气体排放。将大量的可再生能源整合到电网中可能是减少电网中碳排放并减缓气候变化的最易于使用的方法。不幸的是,风和太阳能等最容易获得的可再生能源是高度波动的,因此给电网操作带来了很多不确定性,并挑战了现有的优化和控制政策。偶然受限的交流电(AC)最佳功率流(OPF)框架找到了最低成本生成的调度,以保持较低的概率将电网操作保持在安全限制之内。不幸的是,AC-OPF问题的偶然性约束扩展是非登记,计算挑战性的,需要了解系统参数以及有关可再生分布行为的其他假设。已知的线性和凸近似于上述问题,尽管可以进行操作,但对于操作实践来说太保守了,并且不考虑系统参数的不确定性。本文提出了一种基于高斯流程(GP)回归以缩小此差距的替代数据驱动方法。 GP方法学习了一个简单但非凸的数据驱动的近似值,可以包含不确定性输入的交流功率流程。然后,通过考虑输入和参数不确定性,将后者用于有效地确定CC-OPF的解。在众多IEEE测试案例中,说明了使用不同近似值的GP不确定性传播的拟议方法的实际效率。
translated by 谷歌翻译
Adversarial Imitation Learning (AIL) is a class of popular state-of-the-art Imitation Learning algorithms commonly used in robotics. In AIL, an artificial adversary's misclassification is used as a reward signal that is optimized by any standard Reinforcement Learning (RL) algorithm. Unlike most RL settings, the reward in AIL is $differentiable$ but current model-free RL algorithms do not make use of this property to train a policy. The reward is AIL is also shaped since it comes from an adversary. We leverage the differentiability property of the shaped AIL reward function and formulate a class of Actor Residual Critic (ARC) RL algorithms. ARC algorithms draw a parallel to the standard Actor-Critic (AC) algorithms in RL literature and uses a residual critic, $C$ function (instead of the standard $Q$ function) to approximate only the discounted future return (excluding the immediate reward). ARC algorithms have similar convergence properties as the standard AC algorithms with the additional advantage that the gradient through the immediate reward is exact. For the discrete (tabular) case with finite states, actions, and known dynamics, we prove that policy iteration with $C$ function converges to an optimal policy. In the continuous case with function approximation and unknown dynamics, we experimentally show that ARC aided AIL outperforms standard AIL in simulated continuous-control and real robotic manipulation tasks. ARC algorithms are simple to implement and can be incorporated into any existing AIL implementation with an AC algorithm. Video and link to code are available at: https://sites.google.com/view/actor-residual-critic.
translated by 谷歌翻译