Motivated by decentralized sensing and policy evaluation problems, we consider a particular type of distributed stochastic optimization problem over a network, called the online stochastic distributed averaging problem. We design a dual-based method for this distributed consensus problem with Polyak--Ruppert averaging and analyze its behavior. We show that the proposed algorithm attains an accelerated deterministic error depending optimally on the condition number of the network, and also that it has an order-optimal stochastic error. This improves on the guarantees of state-of-the-art distributed stochastic optimization algorithms when specialized to this setting, and yields -- among other things -- corollaries for decentralized policy evaluation. Our proofs rely on explicitly studying the evolution of several relevant linear systems, and may be of independent interest. Numerical experiments are provided, which validate our theoretical results and demonstrate that our approach outperforms existing methods in finite-sample scenarios on several natural network topologies.

The variability of wind power supply can present substantial challenges to incorporating wind power into a grid system. Thus, Wind Power Forecasting (WPF) has been widely recognized as one of the most critical issues in wind power integration and operation. There has been an explosion of studies on wind power forecasting problems in the past decades. Nevertheless, how to well handle the WPF problem is still challenging, since high prediction accuracy is always demanded to ensure grid stability and security of supply. We present a unique Spatial Dynamic Wind Power Forecasting dataset: SDWPF, which includes the spatial distribution of wind turbines, as well as the dynamic context factors. Whereas, most of the existing datasets have only a small number of wind turbines without knowing the locations and context information of wind turbines at a fine-grained time scale. By contrast, SDWPF provides the wind power data of 134 wind turbines from a wind farm over half a year with their relative positions and internal statuses. We use this dataset to launch the Baidu KDD Cup 2022 to examine the limit of current WPF solutions. The dataset is released at https://aistudio.baidu.com/aistudio/competition/detail/152/0/datasets.

This paper proposes a method for lifelong learning of Recurrent Neural Networks, such as NNARX, ESN, LSTM, and GRU, to be used as plant models in control system synthesis. The problem is significant because in many practical applications it is required to adapt the model when new information is available and/or the system undergoes changes, without the need to store an increasing amount of data as time proceeds. Indeed, in this context, many problems arise, such as the well known Catastrophic Forgetting and Capacity Saturation ones. We propose an adaptation algorithm inspired by Moving Horizon Estimators, deriving conditions for its convergence. The described method is applied to a simulated chemical plant, already adopted as a challenging benchmark in the existing literature. The main results achieved are discussed.

In human-robot interactions, eye movements play an important role in non-verbal communication. However, controlling the motions of a robotic eye that display similar performance as the human oculomotor system is still a major challenge. In this paper, we study how to control a realistic model of the human eye with a cable-driven actuation system that mimics the six degrees of freedom of the extra-ocular muscles. The biomimetic design introduces novel challenges to address, most notably the need to control the pretension on each individual muscle to prevent the loss of tension during motion, that would lead to cable slack and lack of control. We built a robotic prototype and developed a nonlinear simulator and two controllers. In the first approach, we linearized the nonlinear model, using a local derivative technique, and designed linear-quadratic optimal controllers to optimize a cost function that accounts for accuracy, energy expenditure, and movement duration. The second method uses a recurrent neural network that learns the nonlinear system dynamics from sample trajectories of the system, and a non-linear trajectory optimization solver that minimizes a similar cost function. We focused on the generation of rapid saccadic eye movements with fully unconstrained kinematics, and the generation of control signals for the six cables that simultaneously satisfied several dynamic optimization criteria. The model faithfully mimics the three-dimensional rotational kinematics and dynamics observed for human saccades. Our experimental results indicate that while both methods yielded similar results, the nonlinear method is more flexible for future improvements to the model, for which the calculations of the linearized model's position-dependent pretensions and local derivatives become particularly tedious.

The thrust for increased rating capacity of wind turbines has resulted into larger generators, longer blades, and taller towers. Presently, up to 16 MW wind turbines are being offered by wind turbines manufacturers which is nearly a 60 percent increase in the design capacity over the last five years. Manufacturing of these turbines involves assembling of gigantic sized components. Due to the frequent design changes and the variety of tasks involved, conventional automation is not possible making it a labor-intensive activity. However the handling and assembling of large components are challenging the human capabilities. The article proposes the use of mobile robotic assistants for partial automation of wind turbines manufacturing. The robotic assistant can result into reducing production costs, and better work conditions. The article presents development of a robot assistant for human operators to effectively perform assembly of wind turbines. The case is from a leading wind turbines manufacturer. The developed system is also applicable to other cases of large component manufacturing involving intensive manual effort.

Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe. The current use of physics-based numerical weather prediction (NWP) limits accuracy due to high computational cost and strict time-to-solution limits. We report that a data-driven deep learning Earth system emulator, FourCastNet, can predict global weather and generate medium-range forecasts five orders-of-magnitude faster than NWP while approaching state-of-the-art accuracy. FourCast-Net is optimized and scales efficiently on three supercomputing systems: Selene, Perlmutter, and JUWELS Booster up to 3,808 NVIDIA A100 GPUs, attaining 140.8 petaFLOPS in mixed precision (11.9%of peak at that scale). The time-to-solution for training FourCastNet measured on JUWELS Booster on 3,072GPUs is 67.4minutes, resulting in an 80,000times faster time-to-solution relative to state-of-the-art NWP, in inference. FourCastNet produces accurate instantaneous weather predictions for a week in advance, enables enormous ensembles that better capture weather extremes, and supports higher global forecast resolutions.

In terms of the operation of microgrids, optimal scheduling is a vital issue that must be taken into account. In this regard, this paper proposes an effective framework for optimal scheduling of renewable microgrids considering energy storage devices, wind turbines, micro turbines. Due to the nonlinearity and complexity of operation problems in microgrids, it is vital to use an accurate and robust optimization technique to efficiently solve this problem. To this end, in the proposed framework, the teacher learning-based optimization is utilized to efficiently solve the scheduling problem in the system. Moreover, a deep learning model based on bidirectional long short-term memory is proposed to address the short-term wind power forecasting problem. The feasibility and performance of the proposed framework as well as the effect of wind power forecasting on the operation efficiency are examined using IEEE 33-bus test system. Also, the Australian Wool north wind site data is utilized as a real-world dataset to evaluate the performance of the forecasting model. Results show the effective and efficient performance of the proposed framework in the optimal scheduling of microgrids.

Molecular dynamics simulations are an invaluable tool in numerous scientific fields. However, the ubiquitous classical force fields cannot describe reactive systems, and quantum molecular dynamics are too computationally demanding to treat large systems or long timescales. Reactive force fields based on physics or machine learning can be used to bridge the gap in time and length scales, but these force fields require substantial effort to construct and are highly specific to a given chemical composition and application. A significant limitation of machine learning models is the use of element-specific features, leading to models that scale poorly with the number of elements. This work introduces the Gaussian multipole (GMP) featurization scheme that utilizes physically-relevant multipole expansions of the electron density around atoms to yield feature vectors that interpolate between element types and have a fixed dimension regardless of the number of elements present. We combine GMP with neural networks to directly compare it to the widely used Behler-Parinello symmetry functions for the MD17 dataset, revealing that it exhibits improved accuracy and computational efficiency. Further, we demonstrate that GMP-based models can achieve chemical accuracy for the QM9 dataset, and their accuracy remains reasonable even when extrapolating to new elements. Finally, we test GMP-based models for the Open Catalysis Project (OCP) dataset, revealing comparable performance to graph convolutional deep learning models. The results indicate that this featurization scheme fills a critical gap in the construction of efficient and transferable machine-learned force fields.

Today\'s world of space\'s primary concern is the uncontrolled growth of space debris and its probability of collision with spacecraft, particularly in the low earth orbit (LEO) regions. This paper is aimed to design an optimized micro-propulsion system, Cold Gas Thruster, to de-orbit the PSLV debris from 668km to 250 km height after capturing process. The propulsion system mainly consists of a storage tank, pipes, control valves, and a convergent-divergent nozzle. The paper gives an idea of the design of each component based on a continuous iterative process until the design thrust requirements are met. All the components are designed in the CATIA V5, and the structural analysis is done in the ANSYS tool for each component where our cylinder tank can withstand the high hoop stress generated on its wall of it. And flow analysis is done by using the K-$\epsilon$ turbulence model for the CD nozzle, which provides the required thrust to de-orbit PSLV from a higher orbit to a lower orbit, after which the air drag will be enough to bring back to earth\'s atmosphere and burn it. Hohmann\'s orbit transfer method has been used to de-orbit the PSLV space debris, and it has been simulated by STK tools. And the result shows that our optimized designed thruster generates enough thrust to de-orbit the PSLV debris to a very low orbit.

A large class of inverse problems in imaging aims at recovering locations of sources of waves from sensor measurements of the wavefield radiated by these sources. Many applications for locating sources exist in the literature, in various fields such as acoustics, geophysics, non-destructive evaluation and more [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. These "inverse source" problems are usually ill-posed. The incomplete data provided only by a few sensors makes the solution very sensitive to that data. In addition, traditional imaging methods such as Kirchhoff migration suffer from the so-called resolution limit, when close-by sources cannot be distinguished from each other in the image due to the nonzero width of the Green's function. Various super-resolution techniques can in principle overcome these limitations, however at the expense of extreme sensitivity to noise in the data and highly nontrivial mathematical theory, which is currently applicable only in a limited number of cases (see Section 2). The use of machine-learning (ML) for solving inverse problems is spreading fast within the scientific community [11, 12, 13, 14]. According to this paradigm, many PDE-based inverse problems of the form A(x) y, including the one in this paper, can be formulated as data-driven problems, i.e. searching for a general neural network model NN