Optical devices lie at the heart of most of the technology we see around us. When one actually wants to make such an optical device, one can predict its optical behavior using computational simulations of Maxwell's equations. If one then asks what the optimal design would be in order to obtain a certain optical behavior, the only way to go further would be to try out all of the possible designs and compute the electromagnetic spectrum they produce. When there are many design parameters, this brute force approach quickly becomes too computationally expensive. We therefore need other methods to create optimal optical devices. An alternative to the brute force approach is inverse design. In this paradigm, one starts from the desired optical response of a material and then determines the design parameters that are needed to obtain this optical response. There are many algorithms known in the literature that implement this inverse design. Some of the best performing, recent approaches are based on Deep Learning. The central idea is to train a neural network to predict the optical response for given design parameters. Since neural networks are completely differentiable, we can compute gradients of the response with respect to the design parameters. We can use these gradients to update the design parameters and get an optical response closer to the one we want. This allows us to obtain an optimal design much faster compared to the brute force approach. In my thesis, I use Deep Learning for the inverse design of the Fabry-P\'erot resonator. This system can be described fully analytically and is therefore ideal to study.

The Resource Allocation approach (RA) improves the performance of MOEA/D by maintaining a big population and updating few solutions each generation. However, most of the studies on RA generally focused on the properties of different Resource Allocation metrics. Thus, it is still uncertain what the main factors are that lead to increments in performance of MOEA/D with RA. This study investigates the effects of MOEA/D with the Partial Update Strategy in an extensive set of MOPs to generate insights into correspondences of MOEA/D with the Partial Update and MOEA/D with small population size and big population size. Our work undertakes an in-depth analysis of the populational dynamics behaviour considering their final approximation Pareto sets, anytime hypervolume performance, attained regions and number of unique non-dominated solutions. Our results indicate that MOEA/D with Partial Update progresses with the search as fast as MOEA/D with small population size and explores the search space as MOEA/D with big population size. MOEA/D with Partial Update can mitigate common problems related to population size choice with better convergence speed in most MOPs, as shown by the results of hypervolume and number of unique non-dominated solutions, the anytime performance and Empirical Attainment Function indicates.

Renewable energy resources (RERs) have been increasingly integrated into modern power systems, especially in large-scale distribution networks (DNs). In this paper, we propose a deep reinforcement learning (DRL)-based approach to dynamically search for the optimal operation point, i.e., optimal power flow (OPF), in DNs with a high uptake of RERs. Considering uncertainties and voltage fluctuation issues caused by RERs, we formulate OPF into a multi-objective optimization (MOO) problem. To solve the MOO problem, we develop a novel DRL algorithm leveraging the graphical information of the distribution network. Specifically, we employ the state-of-the-art DRL algorithm, i.e., deep deterministic policy gradient (DDPG), to learn an optimal strategy for OPF. Since power flow reallocation in the DN is a consecutive process, where nodes are self-correlated and interrelated in temporal and spatial views, to make full use of DNs' graphical information, we develop a multi-grained attention-based spatial-temporal graph convolution network (MG-ASTGCN) for spatial-temporal graph information extraction, preparing for its sequential DDPG. We validate our proposed DRL-based approach in modified IEEE 33, 69, and 118-bus radial distribution systems (RDSs) and show that our DRL-based approach outperforms other benchmark algorithms. Our experimental results also reveal that MG-ASTGCN can significantly accelerate the DDPG training process and improve DDPG's capability in reallocating power flow for OPF. The proposed DRL-based approach also promotes DNs' stability in the presence of node faults, especially for large-scale DNs.

Correlated time series (CTS) forecasting plays an essential role in many cyber-physical systems, where multiple sensors emit time series that capture interconnected processes. Solutions based on deep learning that deliver state-of-the-art CTS forecasting performance employ a variety of spatio-temporal (ST) blocks that are able to model temporal dependencies and spatial correlations among time series. However, two challenges remain. First, ST-blocks are designed manually, which is time consuming and costly. Second, existing forecasting models simply stack the same ST-blocks multiple times, which limits the model potential. To address these challenges, we propose AutoCTS that is able to automatically identify highly competitive ST-blocks as well as forecasting models with heterogeneous ST-blocks connected using diverse topologies, as opposed to the same ST-blocks connected using simple stacking. Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models. Extensive experiments on eight commonly used CTS forecasting benchmark datasets justify our design choices and demonstrate that AutoCTS is capable of automatically discovering forecasting models that outperform state-of-the-art human-designed models. This is an extended version of ``AutoCTS: Automated Correlated Time Series Forecasting'', to appear in PVLDB 2022.

Artificial intelligence and machine learning can be leveraged by power companies to get better forecasts, manage their grids and schedule maintenance. Decentralised energy sources can use AI and ML to predict energy consumption in households, comparing data from a specific part of the year and previous years. Artificial intelligence (AI) and machine learning (ML) have the capability to transform the renewable energy space and can be leveraged by power companies to get better forecasts, manage their grids and schedule maintenance. Consumers can also enjoy uninterrupted green energy and get upfront information about scheduled maintenance works in the grid that could result in power outages. Adoption of electric vehicles and electrification of heating systems in the next 10-15 years will add complexity to energy grids across the globe.

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings: in- and out-of-domain language modeling, zero- and few-shot priming, and full fine-tuning. With the exception of fine-tuning, we find MoEs to be substantially more compute efficient. At more modest training budgets, MoEs can match the performance of dense models using $\sim$4 times less compute. This gap narrows at scale, but our largest MoE model (1.1T parameters) consistently outperforms a compute-equivalent dense model (6.7B parameters). Overall, this performance gap varies greatly across tasks and domains, suggesting that MoE and dense models generalize differently in ways that are worthy of future study. We make our code and models publicly available for research use.

This paper proposes a safe reinforcement learning algorithm for generation bidding decisions and unit maintenance scheduling in a competitive electricity market environment. In this problem, each unit aims to find a bidding strategy that maximizes its revenue while concurrently retaining its reliability by scheduling preventive maintenance. The maintenance scheduling provides some safety constraints which should be satisfied at all times. Satisfying the critical safety and reliability constraints while the generation units have an incomplete information of each others' bidding strategy is a challenging problem. Bi-level optimization and reinforcement learning are state of the art approaches for solving this type of problems. However, neither bi-level optimization nor reinforcement learning can handle the challenges of incomplete information and critical safety constraints. To tackle these challenges, we propose the safe deep deterministic policy gradient reinforcement learning algorithm which is based on a combination of reinforcement learning and a predicted safety filter. The case study demonstrates that the proposed approach can achieve a higher profit compared to other state of the art methods while concurrently satisfying the system safety constraints.

In his new book, SuperSight: What Augmented Reality Means for Our Lives, Our Work, and the Way We Imagine the Future, author David Rose delves into the current state of the art of augmented reality, discussing how the technology is already transforming myriad industries -- from food service to medicine to education to construction and architecture -- and what it might accomplish in the near future. In the excerpt below, Rose takes a look at two companies leveraging computer vision and generative adversarial networks to reimagine existing properties as 21st century electrified smart homes. Excerpted with permission from SuperSight: What Augmented Reality Means for Our Lives, Our Work, and the Way We Imagine the Future by David Rose, published by BenBella Books. We should all be using solar panels. The average cost for a sustainable energy system has fallen about 70% in the last decade, from $5.86/watt to $1.50/ watt, so it's a financial no-brainer.

Monte Carlo, as well as Dynamic Programming, Temporal Difference are the main methods for starters in Reinforcement Learning. First, let's have a brief reminder of what is Monte Carlo method. Monte Carlo is an algorithm that generates paths (which constitutes an episode) based on the current policy which usually splits between exploration and exploitation, like epsilon greedy, until the path reaches a terminal state. Once that state is reached, the algorithm goes back through that path again and affects each state the discounted rewards that are met during the episode. These values (discounts rewards) are averaged with any other values that happen to be contained in those states.

Utilidata, an industry leading grid-edge software company, announced today that it is developing a software-defined smart grid chip in collaboration with NVIDIA. The chip will be powered by NVIDIA's AI platform and embedded in smart meters to enhance grid resiliency, integrate distributed energy resources (DERs) -- including solar, storage, and electric vehicles (EVs) -- and accelerate the transition to a decarbonized grid. The U.S. Department of Energy's (DOE's) National Renewable Energy Laboratory (NREL) will be among the first to test the software-defined smart grid chip as a way to scale and commercialize the lab's Real-Time Optimal Power Flow (RT-OPF) technology, with support from the Solar Energy Technologies Office Technology Commercialization Fund. Originally developed with funding from DOE's Advanced Research Projects – Energy (ARPA-E) program, RT-OPF enables highly localized load control to seamlessly integrate an increasing number of DERs while ensuring stable and efficient grid operations. "To date, the scalability and commercial potential of technologies like RT-OPF have been limited by single-use hardware solutions," said Santosh Veda, Group Manager for Grid Automation and Controls at NREL. "By developing a smart grid chip that can be embedded in one of the most ubiquitous utility assets – the smart meter – this approach will potential enable wider adoption and commercialization of the technology and redefine the role of edge computing for DER integration and resiliency. Enhanced situational awareness and visibility from this approach will greatly benefit both the end customers and the utility."