[ad_1]
According to the Dubai Electricity and Water Authority (Dewa), the R&D center employs artificial intelligence (AI), machine learning (ML) and deep learning (DL) to facilitate Dewa’s efforts to enrich the experience for customers, employees and stakeholders.
This is aimed at reducing costs and carbon emissions, in addition to improving energy efficiency, smart grid integration and improving the performance of photovoltaic solar panels, according to the Emirates News Agency. WAM.
“Dewa started its AI journey in 2017 with a roadmap for AI applications. We launched several services and programs that use AI to add value to the experience of customers, employees and stakeholders. Dewa is the first government organization in Dubai to use self One – assessing tools to ensure it uses the most critical AI applications in an ethical manner and taking corrective action as needed,” said Saeed Mohammed Al Tayer, MD and CEO of Dewa.
Al Tayer noted that the R&D centre at the Mohammed bin Rashid Al Maktoum Solar Park supports innovation in all areas of production and operations, becoming a global platform to enhance the operations and services of the Dewa sector.
The Energy Efficiency R&D Center employs artificial intelligence, machine learning and deep learning to analyze load consumption and develop expansion plans for Deva to increase energy efficiency and improve demand-side management. The application of artificial intelligence to building performance big data analysis has resulted in improved benchmarking tools to validate energy project simulations and contribute to a better understanding of energy usage. It can also quantify cooling loads in buildings in Dubai and determine the impact of these on Dewa’s peak electricity demand.
Using artificial intelligence on smart meter data through ML and DL models can help identify various appliances in use, detect faulty equipment, and predict peak load periods and curves. These technologies can improve energy storage and load distribution management, while providing opportunities for energy retrofits in buildings. It also increases the efficiency of energy generation reserves, reducing CO2 emissions and saving 20% ​​in costs.
Smart Grid Integration The center uses smart meter data with machine learning to provide insights into the low-voltage network. It uses sensor measurements and Internet of Things (IoT), historical asset load, inspection and maintenance data to diagnose critical assets and predict failures, and estimate remaining useful life (RUL).
In addition, it detects potential interruptions in medium-voltage cables; uses AI-based interruption data logging to predict tripping of protective relays, and setpoints on high-voltage networks to eliminate congestion. It deploys fault detection and predictive maintenance solutions to improve key Dewa metrics such as Customer Lost Minutes (CML) and System Average Interruption Duration Index (SAIDI).
Solar Energy Resources and Forecasting Project This project develops models for assessing solar energy resources, solar radiation, and the expected production capacity of solar systems, based on artificial intelligence and machine learning, as well as various neural networks such as recurrent neural networks (RNNs), Long Short Term Memory (LSTM) networks, XGBoost and UNET.
The Sun Prediction Research Group’s deep learning and neural networks detect clouds and fog from sky cameras and satellite imagery via a multiResnet network, improve the popular UNET model for computer vision, and reduce costs and carbon emissions by increasing power generation. solar.
Solar Cell Program The center uses artificial intelligence in conjunction with materials science (known as “materials informatics”) to develop environmentally friendly lead-free materials for high-efficiency new economical solar cells.
Improving the performance of photovoltaic solar panels The center uses deep learning to detect dirt and dust spots on photovoltaic panels and enhances thermal images captured by unmanned aerial vehicles (UAVs) and real-time kinetic energy systems. The center has published several research papers at international scientific conferences on “Autonomous Photovoltaic Panel Inspection Using Drones”; and “Enhanced Photovoltaic Panel Inspection Using RTK-equipped Drones”.
[ad_2]
Source link