We consider multi-task regression models where observations are assumed to be a linear combination of several latent node and weight functions, all drawn from Gaussian process priors that allow nonzero covariance between grouped latent functions. Motivated by the problem of developing scalable methods for distributed solar forecasting, we exploit sparse covariance structures where latent functions are assumed to be conditionally independent given a group-pivot latent function. We exploit properties of multivariate Gaussians to construct sparse Cholesky factors directly, rather than obtaining them through iterative routines, and by doing so achieve significantly improved time and memory complexity including prediction complexity that is linear in the number of grouped functions. We test our approach on large multi-task datasets and find that sparse specifications achieve the same or better accuracy than non-sparse counterparts in less time, and improve on benchmark model accuracy.

Modern cyber-physical systems (e.g., robotics systems) are typically composed of physical and software components, the characteristics of which are likely to change over time. Assumptions about parts of the system made at design time may not hold at run time, especially when a system is deployed for long periods (e.g., over decades). Self-adaptation is designed to find reconfigurations of systems to handle such run-time inconsistencies. Planners can be used to find and enact optimal reconfigurations in such an evolving context. However, for systems that are highly configurable, such planning becomes intractable due to the size of the adaptation space. To overcome this challenge, in this paper we explore an approach that (a) uses machine learning to find Pareto-optimal configurations without needing to explore every configuration and (b) restricts the search space to such configurations to make planning tractable. We explore this in the context of robot missions that need to consider task timeliness and energy consumption. An independent evaluation shows that our approach results in high-quality adaptation plans in uncertain and adversarial environments.

This paper formulates dynamic density functions, based upon skewed-t and similar representations, to model and forecast electricity price spreads between different hours of the day. This supports an optimal day ahead storage and discharge schedule, and thereby facilitates a bidding strategy for a merchant arbitrage facility into the day-ahead auctions for wholesale electricity. The four latent moments of the density functions are dynamic and conditional upon exogenous drivers, thereby permitting the mean, variance, skewness and kurtosis of the densities to respond hourly to such factors as weather and demand forecasts. The best specification for each spread is selected based on the Pinball Loss function, following the closed form analytical solutions of the cumulative density functions. Those analytical properties also allow the calculation of risk associated with the spread arbitrages. From these spread densities, the optimal daily operation of a battery storage facility is determined.

This paper presents a spatiotemporal unsupervised feature learning method for cause identification of electromagnetic transient events (EMTE) in power grids. The proposed method is formulated based on the availability of time-synchronized high-frequency measurement, and using the convolutional neural network (CNN) as the spatiotemporal feature representation along with softmax function. Despite the existing threshold-based, or energy-based events analysis methods, such as support vector machine (SVM), autoencoder, and tapered multi-layer perception (t-MLP) neural network, the proposed feature learning is carried out with respect to both time and space. The effectiveness of the proposed feature learning and the subsequent cause identification is validated through the EMTP simulation of different events such as line energization, capacitor bank energization, lightning, fault, and high-impedance fault in the IEEE 30-bus, and the real-time digital simulation (RTDS) of the WSCC 9-bus system.

We present a machine learning approach to the solution of chance constrained optimizations in the context of voltage regulation problems in power system operation. The novelty of our approach resides in approximating the feasible region of uncertainty with an ellipsoid. We formulate this problem using a learning model similar to Support Vector Machines (SVM) and propose a sampling algorithm that efficiently trains the model. We demonstrate our approach on a voltage regulation problem using standard IEEE distribution test feeders.

Robots have a tough job making their way in the world. Life throws up obstacles, and it takes a lot of computing power to avoid them. At the IEEE International Solid-State Circuits Conference last month in San Francisco, engineers presented some ideas for lightening that computational burden. That's a particularly good thing if you're a compact robot, with a small battery pack and a big job to do. Engineers at Intel are experimenting with robot-specific accelerators as part of a collaborative multirobot system.

Capacitors, given their high energy output and recharging speed, could play a major role in powering the machines of the future, from electric cars to cell phones. But the biggest hurdle for these energy storage devices is that they store much less energy than a battery of similar size. Researchers at Georgia Institute of Technology are tackling that problem in a novel way, using machine learning to ultimately find ways to build more capable capacitors. The method, which was described in February 18 in the journal npj Computational Materials and sponsored by the U.S. Office of Naval Research, involves teaching a computer to analyze at an atomic level two materials that make up some capacitors: aluminum and polyethylene. The researchers focused on finding a way to more quickly analyze the electronic structure of those materials, looking for features that could affect performance.

AI, in the coming years, is expected to make a lot of progress in the solar and wind energy sector by updating manual processes into an automated one. AI with the help of other groundbreaking technologies like machine learning, advanced neural networks, and deep learning have shown their ability to make a big revolution in the utility and energy sectors. The increasing modal share of renewable energy sources have caused insufficiency in demand and supply of energy, and now, many companies are implementing AI with various other new technologies to allow utilities to manage the imbalance. AI, in the future, is expected to improve the efficiency of the renewable energy industry by changing traditional manual operations of the industry into automated processes. Also, the other transforming technologies such as IoT and big data are expected to contribute a lot to AI processes to help improve the process to overcome the energy insufficiency.

Many large scale problems in computational fluid dynamics such as uncertainty quantification, Bayesian inversion, data assimilation and PDE constrained optimization are considered very challenging computationally as they require a large number of expensive (forward) numerical solutions of the corresponding PDEs. We propose a machine learning algorithm, based on deep artificial neural networks, that learns the underlying input parameters to observable map from a few training samples (computed realizations of this map). By a judicious combination of theoretical arguments and empirical observations, we find suitable network architectures and training hyperparameters that result in robust and efficient neural network approximations of the parameters to observable map. Numerical experiments for realistic high dimensional test problems, demonstrate that even with approximately 100 training samples, the resulting neural networks have a prediction error of less than one to two percent, at a computational cost which is several orders of magnitude lower than the cost of the underlying PDE solver. Moreover, we combine the proposed deep learning algorithm with Monte Carlo (MC) and Quasi-Monte Carlo (QMC) methods to efficiently compute uncertainty propagation for nonlinear PDEs. Under the assumption that the underlying neural networks generalize well, we prove that the deep learning MC and QMC algorithms are guaranteed to be faster than the baseline (quasi-) Monte Carlo methods. Numerical experiments demonstrating one to two orders of magnitude speed up over baseline QMC and MC algorithms, for the intricate problem of computing probability distributions of the observable, are also presented.

Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting compact approximations to the best-response function, which maps hyperparameters to optimal weights and biases. We show how to construct scalable best-response approximations for neural networks by modeling the best-response as a single network whose hidden units are gated conditionally on the regularizer. We justify this approximation by showing the exact best-response for a shallow linear network with L2-regularized Jacobian can be represented by a similar gating mechanism. We fit this model using a gradient-based hyperparameter optimization algorithm which alternates between approximating the best-response around the current hyperparameters and optimizing the hyperparameters using the approximate best-response function. Unlike other gradient-based approaches, we do not require differentiating the training loss with respect to the hyperparameters, allowing us to tune discrete hyperparameters, data augmentation hyperparameters, and dropout probabilities. Because the hyperparameters are adapted online, our approach discovers hyperparameter schedules that can outperform fixed hyperparameter values. Empirically, our approach outperforms competing hyperparameter optimization methods on large-scale deep learning problems. We call our networks, which update their own hyperparameters online during training, Self-Tuning Networks (STNs).