This paper proposes a method for calibrating control parameters. Examples of such control parameters are gains of PID controllers, weights of a cost function for optimal control, filter coefficients, the sliding surface of a sliding mode controller, or weights of a neural network. Hence, the proposed method can be applied to a wide range of controllers. The method uses a Kalman filter that estimates control parameters rather than the system's state, using data of closed-loop system operation. The control parameter calibration is driven by a training objective, which encompasses specifications on the performance of the dynamical system. The calibration method tunes the parameters online and robustly, is computationally efficient, has low data storage requirements, and is easy to implement making it appealing for many real-time applications. Simulation results show that the method is able to learn control parameters quickly (approximately 24% average decay factor of closed-loop cost), is able to tune the parameters to compensate for disturbances (approximately 29% improvement on tracking precision), and is robust to noise. Further, a simulation study with the high-fidelity vehicle simulator CarSim shows that the method can calibrate controllers of a complex dynamical system online, which indicates its applicability to a real-world system.

To address this complex issue, the most promising research directions are oriented toward the conceptualization of improved information processing paradigms and smart decision support systems aimed at enhancing standard operating procedures, based on pre-defined grid conditions and static operating thresholds, with a set of interactive information services, which could promptly provide the right information at the right moment to the right decision maker. To effectively support the deployment of these services in modern smart grids it will be incumbent upon the scientific community to develop advanced techniques and algorithms for reliable power system data acquisition and processing, which should support semantics and content-based data extraction and integration from heterogeneous sensor networks. This research topic contains four articles.The paper Optimal Balancing of Wind Parks with Virtual Power Plants by Vadim Omelčenko and Valery Manokhin addresses data-driven solutions in the context of optimization of virtual power plants. This work proposes the use of machine learning to process available data measurements. The goal is to balance the power production and at the same time maximize the revenue of a portfolio of power plants with different technologies (biogas, wind, batteries, etc.) considering uncertainty in both price and power production.The paper Supporting Regulatory Measures in the Context of Big Data Applications for Smart Grids by Mihai A. Mladin discusses the policy and regulatory aspects. This paper focuses in particular on big data applications to the ongoing "energy transition" process built on higher renewable energy integration and digitalization, and discusses how this can help regulatory measures through societal acceptance and involvement.The paper Data Consistency for Data-Driven Smart Energy Assessment by Gianfranco Chicco addresses the issue of data consistency and discusses data-versus model-based approaches.

In the 1960s, the advent of computer-aided design (CAD) sparked a revolution in design. For his PhD thesis in 1963, MIT Professor Ivan Sutherland developed Sketchpad, a game-changing software program that enabled users to draw, move, and resize shapes on a computer. Over the course of the next few decades, CAD software reshaped how everything from consumer products to buildings and airplanes were designed. "CAD was part of the first wave in computing in design. The ability of researchers and practitioners to represent and model designs using computers was a major breakthrough and still is one of the biggest outcomes of design research, in my opinion," says Maria Yang, Gail E. Kendall Professor and director of MIT's Ideation Lab.

Despite widespread popularity, today's microwave ovens are limited in their cooking capabilities, given that they heat food blindly, resulting in a nonuniform and unpredictable heating distribution. We present software-defined cooking (SDC), a low-cost closed-loop microwave oven system that aims to heat food in a software-defined thermal trajectory. SDC achieves this through a novel high-resolution heat sensing and actuation system that uses microwave-safe components to augment existing microwaves. SDC first senses the thermal gradient by using arrays of neon lamps that are charged by the electromagnetic (EM) field a microwave produces. SDC then modifies the EM-field strength to desired levels by accurately moving food on a programmable turntable toward sensed hot and cold spots. To create a more skewed arbitrary thermal pattern, SDC further introduces two types of programmable accessories: A microwave shield and a susceptor. We design and implement one experimental test bed by modifying a commercial off-the-shelf microwave oven. Our evaluation shows that SDC can programmatically create temperature deltas at a resolution of 21 C with a spatial resolution of 3 cm without the programmable accessories, and 183 C with them. We further demonstrate how an SDC-enabled microwave can be enlisted to perform unexpected cooking tasks: Cooking meat and fat in bacon discriminatively and heating milk uniformly. Since the introduction of microwaves to the consumer market in the 1970s, they have seen widespread adoption and are today the third most popular domestic food heating method (after baking and grilling).13 Indeed, the original patents for the microwave by Raytheon Inc. in the late 1940s envisioned a universal food cooking instrument for all kinds of food ranging from meat to fish.1 While microwaves have revolutionized the kitchen since their inception, today's consumer microwaves are mainly used as blunt heating appliances (e.g., reheating pizzas) rather than precise cooking instruments (e.g., cooking steak).

There is an increasing demand for piloted autonomous underwater vehicles (AUVs) to operate in polar ice conditions. At present, AUVs are deployed from ships and directly human-piloted in these regions, entailing a high carbon cost and limiting the scope of operations. A key requirement for long-term autonomous missions is a long-range route planning capability that is aware of the changing ice conditions. In this paper we address the problem of automating long-range route-planning for AUVs operating in the Southern Ocean. We present the route-planning method and results showing that efficient, ice-avoiding, long-distance traverses can be planned.

After discussing in my last two articles how digital twins can revolutionize the energy industry and how our Heat Transfer Twin can help HRSG (heat recovery steam generator) operators save millions of dollars, today I'd like to take a closer look at how a Heat Transfer Twin could be developed. As already explained, conventional inspections of HRSG walls and tubes require considerable manual effort and take up to three weeks. To reduce this expense, it's important to know in advance where corrosion might have occurred. However, identifying corrosion risks is very complicated because corrosion depends on several factors. We need to know if and how much liquid is in the steam, and where it hits the tubes.

Key words: [to use as knowledge, not to be copied verbatim]: Artificial Intelligence; big data; smart cities; climate change. Introduction: The need for a more resilient society: As human numbers continue to grow and urbanization advances, the probability of climate change impacting on impacts on natural systems and our quality of life outweighs any projected benefits of continued growth. To reduce society's vulnerability to climate change, we need sophisticated monitoring and modeling systems that can provide real-time data on the impacts of climate change, air quality and other environmental factors. However, current energy use and cities exert a heavy demand on the environment, which means that it is unrealistic to expect a return to a pre-industrial quality of living. As a result, cities will need to find ways to be resilient in the face of uncertainty.

Machine learning and AI are probably the most buzz commendable business terms that you hear nowadays. Along these lines, business across enterprises are searching for ways of executing them to improve and computerize their center cycles. Also, the energy business is no exemption! Truth be told, sustainable power organizations (wind, solar, hydro, nuclear) have extraordinarily profited from the force of AI throughout the long term. They have figured out how to bring down their expenses, improve forecasts, and increment their portfolio's pace of return.

The metaverse looks likely to reach into every corner of our lives. Apple, Disney, Nvidia, Microsoft, and Meta (formerly Facebook) have all stated their intentions to get involved, but the environmental costs from AI workloads that will arise from running the metaverse on a large scale will be huge. However, recent technological innovations in data centers will help. Furthermore, the metaverse may offset emissions by changing the very ways we interact with each other. The metaverse is a virtual world where users can share experiences and interact in real time within simulated scenarios.

The recent abundance of data on electricity consumption at different scales opens new challenges and highlights the need for new techniques to leverage information present at finer scales in order to improve forecasts at wider scales. In this work, we take advantage of the similarity between this hierarchical prediction problem and multi-scale transfer learning. We develop two methods for hierarchical transfer learning, based respectively on the stacking of generalized additive models and random forests, and on the use of aggregation of experts. We apply these methods to two problems of electricity load forecasting at national scale, using smart meter data in the first case, and regional data in the second case. For these two usecases, we compare the performances of our methods to that of benchmark algorithms, and we investigate their behaviour using variable importance analysis. Our results demonstrate the interest of both methods, which lead to a significant improvement of the predictions.