Sunshine has given way to wind and rain, as the motorboat chugs through a fjord in the Faroe Islands. "Its a bit windy here," says Olavur Gregarsen. "We'll see how far we can get to the harvesting boat." We soon reach a sheltered spot where steep mountains are looking down on hundreds of buoys bobbing in the sea. "They are holding up a horizontal line," explains Mr Gregarsen, the managing director of Ocean Rainforest, a seaweed producer.

For more than four decades, UC San Diego Professor of Physics Patrick H. Diamond and his research group have been advancing fundamental concepts in plasma physics, which is an important aspect of furthering advancements in fusion energy. Most recently, Diamond worked with graduate student Robin Heinonen on a model reduction study that used the Comet supercomputer at the San Diego Supercomputer Center at the University of California San Diego to showcase how machine learning produced a novel model for plasma turbulence. Diamond and Heinonen say that advances in machine learning, such as new deep learning techniques, have provided them with new tools to better understand the self-organization process that emerges from what the researchers term as a seemingly chaotic process. "Turbulence and its transport is chaotic in a sense, but this chaos is ordered and constrained," said Heinonen, who co-authored Turbulence Model Reduction by Deep Learning with Diamond in the academic journal entitled Physical Review E. "Moreover, in certain turbulent systems, the chaos conspires to spontaneously form large, long-lived coherent structures and in many cases, we only have a tenuous understanding of why and now. There are definitely aspects of structure formation and self-organization which we do understand, but it's still an active area of research."

A research team at Argonne National Laboratory developed a novel approach to helping system operators understand how to better control power systems with the help of artificial intelligence. Scientists at the U.S. Department of Energy's Argonne National Laboratory (ANL) have created a new artificial intelligence (AI) technique to help operators understand how to better handle power systems. Their single decision-making neural network model manages both static and dynamic processes with a relatively high level of accuracy, and could augment the resilience of the U.S. power grid. ANL's Yichen Zhang said, "A neural network can create a map between a specific input and a specific output. If I know the conditions we start with and those we end with, I can use neural networks to figure out how those conditions map to each other."

Windows power users have always envied their friends running UNIX machines for the ease of automation that they enjoy. The traditional Windows command-line shell, cmd.exe, has never been up to par with shells like bash or tcsh, especially when it comes to text processing and process automation. This next-generation shell is also a full-blown scripting environment with a real programming language that allows users to access every part of their operating system. Files, registry entries, and COM and .NET objects are all supported by PowerShell, which makes manipulating them a breeze.

We develop a second order primal-dual method for optimization problems in which the objective function is given by the sum of a strongly convex twice differentiable term and a possibly nondifferentiable convex regularizer. After introducing an auxiliary variable, we utilize the proximal operator of the nonsmooth regularizer to transform the associated augmented Lagrangian into a function that is once, but not twice, continuously differentiable. The saddle point of this function corresponds to the solution of the original optimization problem. We employ a generalization of the Hessian to define second order updates on this function and prove global exponential stability of the corresponding differential inclusion. Furthermore, we develop a globally convergent customized algorithm that utilizes the primal-dual augmented Lagrangian as a merit function. We show that the search direction can be computed efficiently and prove quadratic/superlinear asymptotic convergence. We use the $\ell_1$-regularized model predictive control problem and the problem of designing a distributed controller for a spatially-invariant system to demonstrate the merits and the effectiveness of our method.

Predicting a customer's propensity-to-pay at an early point in the revenue cycle can provide organisations many opportunities to improve the customer experience, reduce hardship and reduce the risk of impaired cash flow and occurrence of bad debt. With the advancements in data science; machine learning techniques can be used to build models to accurately predict a customer's propensity-to-pay. Creating effective machine learning models without access to large and detailed datasets presents some significant challenges. This paper presents a case-study, conducted on a dataset from an energy organisation, to explore the uncertainty around the creation of machine learning models that are able to predict residential customers entering financial hardship which then reduces their ability to pay energy bills. Incorrect predictions can result in inefficient resource allocation and vulnerable customers not being proactively identified. This study investigates machine learning models' ability to consider different contexts and estimate the uncertainty in the prediction. Seven models from four families of machine learning algorithms are investigated for their novel utilisation. A novel concept of utilising a Baysian Neural Network to the binary classification problem of propensity-to-pay energy bills is proposed and explored for deployment.

The transition to a new low emission energy future results in a changing mix of generation and load types due to significant growth in renewable energy penetration and reduction in system inertia due to the exit of ageing fossil fuel power plants. This increases technical challenges for electrical grid planning and operation. This study introduces a new decomposition approach to account for the system security for short term planning using conventional machine learning tools. The immediate value of this work is that it provides extendable and computationally efficient guidelines for using supervised learning tools to assess first swing transient stability status. To provide an unbiased evaluation of the final model fit on the training dataset, the proposed approach was examined on a previously unseen test set. It distinguished stable and unstable cases in the test set accurately, with only 0.57% error, and showed a high precision in predicting the time of instability, with 6.8% error and mean absolute error as small as 0.0145.

An emerging number of modern applications involve forecasting time series data that exhibit both short-time dynamics and long-time seasonality. Specifically, time series with multiple seasonality is a difficult task with comparatively fewer discussions. In this paper, we propose a two-stage method for time series with multiple seasonality, which does not require pre-determined seasonality periods. In the first stage, we generalize the classical seasonal autoregressive moving average (ARMA) model in multiple seasonality regime. In the second stage, we utilize an appropriate criterion for lag order selection. Simulation and empirical studies show the excellent predictive performance of our method, especially compared to a recently popular `Facebook Prophet' model for time series.

Machine learning provides a promising avenue for incorporating rich sensing modalities into autonomous systems. However, our coarse understanding of how ML systems fail limits the adoption of data-driven techniques in real-world applications. In particular, applications involving feedback require that errors do not accumulate and lead to instability. In this work, we propose and analyze a baseline method for incorporating a learning-enabled component into closed-loop control, providing bounds on the sample complexity of a reference tracking problem. Much recent work on developing guarantees for learning and control has focused on the case that dynamics are unknown [Dean et al., 2017, Simchowitz and Foster, 2020, Mania et al., 2020].

Radiation-induced photocurrent in semiconductor devices can be simulated using complex physics-based models, which are accurate, but computationally expensive. This presents a challenge for implementing device characteristics in high-level circuit simulations where it is computationally infeasible to evaluate detailed models for multiple individual circuit elements. In this work we demonstrate a procedure for learning compact delayed photocurrent models that are efficient enough to implement in large-scale circuit simulations, but remain faithful to the underlying physics. Our approach utilizes Dynamic Mode Decomposition (DMD), a system identification technique for learning reduced order discrete-time dynamical systems from time series data based on singular value decomposition. To obtain physics-aware device models, we simulate the excess carrier density induced by radiation pulses by solving numerically the Ambipolar Diffusion Equation, then use the simulated internal state as training data for the DMD algorithm. Our results show that the significantly reduced order delayed photocurrent models obtained via this method accurately approximate the dynamics of the internal excess carrier density -- which can be used to calculate the induced current at the device boundaries -- while remaining compact enough to incorporate into larger circuit simulations.