Solar


Sci-Fi Doesn't Have to Be Depressing: Welcome to Solarpunk www.ozy.com

#artificialintelligence

Imagine a scene, set in the future, where a child in Burning Man–style punk clothing is standing in front of a yurt powered by solar panels. There weren't many books with scenes like that in 2014, when Sarena Ulibarri, an editor, first grew interested in a genre of science fiction that imagines a renewable and sustainable future. Welcome to solarpunk, a new genre within science fiction that is a reaction against the perceived pessimism of present-day sci-fi and hopes to bring optimistic stories about the future with the aim of encouraging people to change the present. The first book that explicitly identified as solarpunk was Solarpunk: Histórias ecológicas e fantásticas em um mundo sustentável (Solarpunk: Ecological and Fantastic Stories in a Sustainable World), a Brazilian book published in 2012. In 2014, author Adam Flynn wrote Solarpunk: Notes Toward a Manifesto.


Raycatch uses artificial intelligence technology for PV power plant O&M

#artificialintelligence

Raycatch has introduced'DeepSolar 2.0,' a fully automated, AI-based diagnostic software program for cost-optimized maintenance and monitoring of photovoltaic power plants. Raycatch, which is backed by BayWa r.e., developed the next-generation of DeepSolar, its AI-based Software as a Service (SaaS) solution. The software supports solar plant owners by providing them with comprehensive ROI information and data-driven operational insights. In addition, the diagnostic system can identify the sources behind technical issues, outline issue resolutions, evaluate costs and make prioritized recommendations based on plant owners' respective needs. DeepSolar is a diagnostic software program for cost-optimized maintenance of PV power plants.


Artificial intelligence and green algorithms contribute to improved energy efficiency at BBVA headquarters

#artificialintelligence

During the construction of BBVA's current headquarters in Madrid, criteria was used to ensure its maximum energy efficiency and minimum environmental impact. Together with the use of recycled, sustainable material; the inclusion of extensive green areas; and a sprinkler system that uses rainwater, 50,000 sensors were installed at the bank's headquarters to detect and collect data about the status of the facilities, the environmental conditions, and the proximity of people. BBVA's new corporate headquarters in Madrid have become an architectural and sustainability landmark. Architects Jacques Herzog and Pierre de Meuron have designed not only a smart but an environmentally and people friendly city, reflective of the financial group's global digital transformation strategy. "Once the complex was functioning and after analyzing all this data, we realized that it didn't have to be limited to properly managing the facilities, it could also further improve our energy efficiency and reduce costs," explains Borja Eugui Pemán, BBVA Head of Facility Management.


Probabilistic Forecasting using Deep Generative Models

arXiv.org Machine Learning

The Analog Ensemble (AnEn) method tries to estimate the probability distribution of the future state of the atmosphere with a set of past observations that correspond to the best analogs of a deterministic Numerical Weather Prediction (NWP). This model post-processing method has been successfully used to improve the forecast accuracy for several weather-related applications including air quality, and short-term wind and solar power forecasting, to name a few. In order to provide a meaningful probabilistic forecast, the AnEn method requires storing a historical set of past predictions and observations in memory for a period of at least several months and spanning the seasons relevant for the prediction of interest. Although the memory and computing costs of the AnEn method are less expensive than using a brute-force dynamical ensemble approach, for a large number of stations and large datasets, the amount of memory required for AnEn can easily become prohibitive. Furthermore, in order to find the best analogs associated with a certain prediction produced by a NWP model, the current approach requires searching over the entire dataset by applying a certain metric. This approach requires applying the metric over the entire historical dataset, which may take a substantial amount of time. In this work, we investigate an alternative way to implement the AnEn method using deep generative models. By doing so, a generative model can entirely or partially replace the dataset of pairs of predictions and observations, reducing the amount of memory required to produce the probabilistic forecast by several orders of magnitude. Furthermore, the generative model can generate a meaningful set of analogs associated with a certain forecast in constant time without performing any search, saving a considerable amount of time even in the presence of huge historical datasets.


CPS Energy supports clean energy and grid cybersecurity research at UTSA

#artificialintelligence

UTSA will design data driven approaches and AI to better identify and mitigate cyber threats for IOT devices including smart meters. Through the strategic alliance between the Texas Sustainable Energy Research Institute (TSERI) at UTSA and CPS Energy, three new projects totaling approximately $750,000 will focus on improving grid security and resilience, solar energy generation and more efficient technology for power generation. "We are thrilled to embark on these three new projects that aim to contribute to CPS Energy's position as a key player in the new energy economy," said Krystel Castillo, TSERI Director. "We have been able to build knowledge and grow innovation through our partnership with UTSA over the past decade," said Cris Eugster, CPS Energy's Chief Operating Officer. "We expect these new projects to also bring new insights that will help us plan for the future of energy."


Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods

arXiv.org Artificial Intelligence

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often needed to be solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the prior states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of widely adopted OPF linear DC approximation by at least two orders of magnitude.


Elon Musk wants to read your mind

#artificialintelligence

We all know Elon Musk to be a very ambitious guy. I mean, seriously, the guy has a company which specializes in electric car manufacturing, you've heard of Tesla, right? He also runs an aerospace manufacturing and space transportation services company called SpaceX. I am sure you've heard about it in the news or somewhere else. SolarCity, a solar energy company, now owned by Tesla.


The Tech Innovations We Need to Happen if We're Going to Survive Climate Change

TIME - Tech

In the 1970s, the U.S. Department of Energy poured money into making practical a miraculous technology: the ability to convert sunlight into electricity. Solar energy was a pipe dream, far too expensive and unreliable to be considered a practical power source. But yesterday's moon shot is today's reality. The expense of solar power has fallen more quickly than expected, with installations costing about 80% less today than a decade ago. Alternative energy (like wind and solar) is now often cheaper than conventional energy (like coal and gas).


NYC, get ready for the robots: The city needs a battle-plan for how automation will threaten people's jobs

#artificialintelligence

Today, CUNY's continuing education programs teach job-specific tools ranging from business management to plumbing, but in-depth courses can pose a significant cost burden if not paid for by an employer. Lifelong learning dollars could also be used to earn specific industry-recognized credentials in fields like video production, solar installation, or IT support, or retrain for a tech career at a bootcamp like General Assembly or Flatiron School, which deliver a strong return on investment but come at a high upfront cost.


How are Machine Learning and Artificial Intelligence (AI) Reshaping the Energy Industry in Europe? - Commercial UAV News

#artificialintelligence

DNV GL operates globally across a range of industries to provide trust and help stakeholders understand and manage risks. The company has over 2,200 experts providing advice for renewable generation, transmission, distribution and energy management and efficiency. The work they do ranges from testing high voltage grid components to bankability assessments to allow solar farms to be financed. Their latest research showcases the insight related to how drone technology and computer vision can help with inspections while also providing a global outlook to 2050. We wanted to learn more about the energy innovations DNV GL is exploring and utilizing, so we talked with Elizabeth Traiger, Senior Researcher, Power & Renewables DK & GB at DNV GL – Energy.