Turbine maintenance is an expensive, high-risk task. According to a recent analysis from the news website, wind farm owners are expected to spend more than $40 billion on operations and maintenance over a decade. Another recent study finds by using drone-based inspection instead of traditional rope-based inspection, you can reduce the operational costs by 70% and further decrease revenue lost due to downtime by up to 90%. This blog post will present how drones, machine learning (ML), and Internet of Things (IoT) can be utilized on the edge and the cloud to make turbine maintenance safer and more cost effective. First, we trained the machine learning model on the cloud to detect hazards on the turbine blades, including corrosion, wear, and icing.
Moving towards climate security, electric power systems are going through a major paradigm shift with wide integration of distributed energy resources, such as solar PV, wind power, energy storage and electric vehicles. However, today's grid cannot handle the voltage rise and fast voltage fluctuations from high penetration of renewables. It is widely recognized that the lack of adequate control mechanisms to regulate the voltages is a key hindrance. The goal of this project is to use AI and deep reinforcement learning to advance the current control designs by making them more data-driven and communication efficient. Depending on the candidate's qualifications and scientific interests, the project can be directed towards smart grid optimization, AI algorithm development or hardware implementations.
Wind farms are now a reality in the U.S., heralding a new chapter in the country's sustainable energy production ambitions. But new technologies come with new challenges, and for offshore wind generation, inspection is one of the biggest. In much the same way as energy companies operate and maintain oil and gas subsea assets, wind farm cables, structural foundations, and all other components of the turbines need continuous monitoring and maintenance. That's dangerous work for humans, but it's a job tailor made for underwater robots and smart AI-powered analytics. Given the bright future and growing (albeit still small) footprint of offshore wind in the nation's energy power generation infrastructure, I reached out to Harry Turner, a machine learning specialist for Vaarst, a business driving the future of marine robotics, to discuss how robots and machine learning are changing the game for energy creation.
IBM's fully-autonomous edge AI-powered ship Mayflower has set off on its crewless voyage from Plymouth, UK to Plymouth, USA. The ship is named after the Mayflower vessel which transported pilgrim settlers from Plymouth, England to Plymouth, Massachusetts in 1620. On its 400th anniversary, it was decided that a Mayflower for the 21st century should be built. Mayflower 2.0 is a truly modern vessel packed with the latest technological advancements. Onboard edge AI computing enables the ship to carry out scientific research while navigating the harsh environment of the ocean--often without any connectivity.
A failure detection system is the first step towards predictive maintenance strategies. A popular data-driven method to detect incipient failures and anomalies is the training of normal behaviour models by applying a machine learning technique like feed-forward neural networks (FFNN) or extreme learning machines (ELM). However, the performance of any of these modelling techniques can be deteriorated by the unexpected rise of non-stationarities in the dynamic environment in which industrial assets operate. This unpredictable statistical change in the measured variable is known as concept drift. In this article a wind turbine maintenance case is presented, where non-stationarities of various kinds can happen unexpectedly. Such concept drift events are desired to be detected by means of statistical detectors and window-based approaches. However, in real complex systems, concept drifts are not as clear and evident as in artificially generated datasets. In order to evaluate the effectiveness of current drift detectors and also to design an appropriate novel technique for this specific industrial application, it is essential to dispose beforehand of a characterization of the existent drifts. Under the lack of information in this regard, a methodology for labelling concept drift events in the lifetime of wind turbines is proposed. This methodology will facilitate the creation of a drift database that will serve both as a training ground for concept drift detectors and as a valuable information to enhance the knowledge about maintenance of complex systems.
Greater direct electrification of end-use sectors with a higher share of renewables is one of the pillars to power a carbon-neutral society by 2050. This study uses a recent deep learning technique, the normalizing flows, to produce accurate probabilistic forecasts that are crucial for decision-makers to face the new challenges in power systems applications. Through comprehensive empirical evaluations using the open data of the Global Energy Forecasting Competition 2014, we demonstrate that our methodology is competitive with other state-of-the-art deep learning generative models: generative adversarial networks and variational autoencoders. The models producing weather-based wind, solar power, and load scenarios are properly compared both in terms of forecast value, by considering the case study of an energy retailer, and quality using several complementary metrics.
Building on a project she began as an undergraduate, Higgins started the data-gathering process at Concordia's Building Aerodynamics/Wind Tunnel Lab. It can simulate wind gusts on large buildings with a 1 to 100 or smaller-scale model of a block of downtown Montreal, as well as on individual buildings of different shapes -- square, rectangular, U-shaped, T-shaped or L-shaped, and in different configurations. The lab also has a scale model of a section of the Louis-Hippolyte Lafontaine Bridge-Tunnel in east-end Montreal. "This preliminary work involved a lot of wind tunnel experiments with various building configurations," explains Stathopoulos, a professor in the Department of Building, Civil and Environmental Engineering at the Gina Cody School of Engineering and Computer Science. "Stéphanie ran tests for each of them, with wind coming from different directions, as it would in real life, and tried to predict what the amplification of the wind would be at each location. This particular experimentation was interesting because we are trying to see where we can get the highest wind speed. This is the opposite of what we usually do, which is to try to reduce exposure to wind to protect buildings from natural disasters."
As the world seeks to become more sustainable, intelligent solutions are needed to increase the penetration of renewable energy. In this paper, the model-free deep reinforcement learning algorithm Rainbow Deep Q-Networks is used to control a battery in a small microgrid to perform energy arbitrage and more efficiently utilise solar and wind energy sources. The grid operates with its own demand and renewable generation based on a dataset collected at Keele University, as well as using dynamic energy pricing from a real wholesale energy market. Four scenarios are tested including using demand and price forecasting produced with local weather data. The algorithm and its subcomponents are evaluated against two continuous control benchmarks with Rainbow able to outperform all other method. This research shows the importance of using the distributional approach for reinforcement learning when working with complex environments and reward functions, as well as how it can be used to visualise and contextualise the agent's behaviour for real-world applications.
Running a flexible Machine Learning engine at scale is hard. We must ingest and process large volumes of data uninterruptedly and store it in a scalable manner. The data needs to be prepared and served to hundreds of models constantly. All the predictions of the models, as well as other data pipelines, must be stored and reachable for our web application(s) to present the generated insights to our customers. We work on the system that delivers this functionality and also allows the machine learning engineers to deliver new and improved models at ease, manage existing models, monitor these models, and many different interactions, all of which are crucial to day to day operations.
The increased digitalisation and monitoring of the energy system opens up numerous opportunities % and solutions which can help to decarbonise the energy system. Applications on low voltage (LV), localised networks, such as community energy markets and smart storage will facilitate decarbonisation, but they will require advanced control and management. Reliable forecasting will be a necessary component of many of these systems to anticipate key features and uncertainties. Despite this urgent need, there has not yet been an extensive investigation into the current state-of-the-art of low voltage level forecasts, other than at the smart meter level. This paper aims to provide a comprehensive overview of the landscape, current approaches, core applications, challenges and recommendations. Another aim of this paper is to facilitate the continued improvement and advancement in this area. To this end, the paper also surveys some of the most relevant and promising trends. It establishes an open, community-driven list of the known LV level open datasets to encourage further research and development.