Irish Building Stock Observatory’s Post

➡Massive integration of renewable resources into the electric distribution systems has led to new trends in power exchanges at the interface between Transmission & Distribution systems. ➡An accurate prediction of power exchanges at Transmission–Distribution interfaces is crucial for both the Transmission System Operators (TSOs) and the Distribution System Operators (DSOs) considering the short-term operational control and long-term planning perspectives. 💡In our new research published in the Electric Power System Research journal, we proposed a novel 𝗣𝗵𝘆𝘀𝗶𝗰𝘀-𝗜𝗻𝗳𝗼𝗿𝗺𝗲𝗱 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (PIML) model 𝘁𝗼 𝗲𝗻𝗵𝗮𝗻𝗰𝗲 𝘁𝗵𝗲 𝗽𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗽𝗼𝘄𝗲𝗿 𝗲𝘅𝗰𝗵𝗮𝗻𝗴𝗲𝘀 𝗮𝘁 𝗧𝗿𝗮𝗻𝘀𝗺𝗶𝘀𝘀𝗶𝗼𝗻–𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻 𝗶𝗻𝘁𝗲𝗿𝗳𝗮𝗰𝗲𝘀. 🎯Novelty of the proposed model lies in its combination of an Inverse Load Flow formulation, which defines an 𝗲𝗾𝘂𝗶𝘃𝗮𝗹𝗲𝗻𝘁 𝗺𝗼𝗱𝗲𝗹 𝗼𝗳 𝘁𝗵𝗲 𝗱𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻 𝗻𝗲𝘁𝘄𝗼𝗿𝗸, 𝘄𝗶𝘁𝗵 𝘁𝗵𝗲 𝗰𝗹𝗮𝘀𝘀𝗶𝗰𝗮𝗹 𝗱𝗮𝘁𝗮-𝗱𝗿𝗶𝘃𝗲𝗻 𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻 𝘁𝗲𝗰𝗵𝗻𝗶𝗾𝘂𝗲𝘀. ✅ Simulation results conducted on a modified version of the Oberrhein MV network highlight 𝘁𝗵𝗲 𝘀𝘂𝗽𝗲𝗿𝗶𝗼𝗿𝗶𝘁𝘆 𝗼𝗳 𝘁𝗵𝗲 𝗽𝗿𝗼𝗽𝗼𝘀𝗲𝗱 𝗣𝗜𝗠𝗟 𝗮𝗽𝗽𝗿𝗼𝗮𝗰𝗵 𝗼𝘃𝗲𝗿 𝘁𝗵𝗲 𝗳𝘂𝗹𝗹 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴-𝗯𝗮𝘀𝗲𝗱 𝗺𝗲𝘁𝗵𝗼𝗱𝘀, as demonstrated by the statistical indicators. ✅ In addition, this research adopts the TSO perspective through a 2-step Optimal Power Flow analysis that integrates power predictions and enables the calculation of production and deviation costs linked to predicted powers. 📝This research is authored by Arnaud Rosseel, Bashir Bakhshideh Zad, Francois Vallee and Zacharie De Grève from Power Systems and Markets Research Group - University of Mons (Belgium). 📝 The paper is accessible (for free over the next 50 days) at: https://lnkd.in/e6-6biWP

The refining industry is struggling with aging facilities and an aging workforce. Institutional knowledge and various data necessary to run legacy equipment are often lost in individual electronic files or paper documents ENEOS is therefore now using Cognite Data Fusion's Industrial AI capabilities to build the digital infrastructure required to both capture its unique institutional knowledge and accelerate AI-powered efficiency improvements across its sites in Japan Exciting times for the refining industry https://lnkd.in/d4yFJpkd

For highly technical industries that rely on complex data sets and highly optimized processes, correct predictions can mean the difference between smooth performance and complete shutdown. Understanding and managing model risk is a critical element in overall operations—and it will only become more important as the technologies continue to evolve. #energy #industrials #machinelearning #MLOps https://lnkd.in/gshQ4Psw

Congratulations to Priyesh Saini and Dr. Sanjoy K. Parida for publishing an article in 𝐄𝐍𝐄𝐑𝐆𝐘 (Q1, IF: 9, h5-index: 153). Interested one may go through the article. Abstract: Existing regression, tree-based and NN models either lacks probabilistic prediction, takes longer training time, have high computational requirements or sacrifice accuracy. This paper introduces a novel framework, (MAFS+ISTD+PGBM), specifically to overcome these limitations. First three challenges are addressed by integrating gradient boosting and quantile regression model. The key idea is to combine speed and scalability of gradient boosting with probabilistic capabilities of quantile regression, forming PGBM. However, the issue of mediocre accuracy still remained. To address this, two pre-processing techniques are introduced. MAFS utilizes statistical methods and knowledge-based analysis to identify the most relevant features, while ISTD extracts and eliminates trend and seasonality components, ensuring stationarity. After rigorous evaluations, (MAFS+ISTD+PGBM) emerges as the superior performer surpassing all existing models in terms of training time and accuracy with highest R2 score of 0.997 and low values across all error metrics. The proposed model took less than one-third of training time (15 min) compared to CNN-LSTM+attn., (48 min), the only model with comparable accuracy of proposed model. Thus, proposed approach shall be used to empower grid operators with highly accurate and cost-effective probabilistic forecasts which allows them to make informed decisions about system stability and optimize resource utilization, ensuring reliability and efficiency. https://lnkd.in/de8YRax5

New blog post alert! 💡Machine Learning Engineer Manuel Santos introduces how Jungle’s power forecasting tool, Toucan, is designed to enable renewable assets teams to autonomously access power forecasts in an easy and straightforward way. Follow the link to discover how our API-based solution ensures lightning-fast responses, unwavering reliability, and top-notch security: https://lnkd.in/dZ_qDZzW #PowerForecasting #RenewableEnergy #APISolutions

Condition Monitoring Using Predictive ML Applications This blog delves into the realm of Condition Monitoring Using Predictive ML Applications, authored by. Venkat Krishna Soundarraja . It discusses the traditional method of condition monitoring through sensor measurements and the limitations it faces. An alternative approach, using predictive ML models like Pattern Recognition, is proposed to overcome these limitations. The blog explains how Pattern Recognition works, its advantages over conventional methods, and its applications in industries like Oil & Gas. It showcases real-life examples of anomaly detection in various machinery components and emphasizes the importance of continuous monitoring and model retuning for optimal performance. Finally, it discusses the benefits of predictive diagnostics in terms of cost savings, improved efficiency, and environmental impact. Do check out the blog for more information #blogs #mlmodels #patternrecognition #conditionmonitoring #seaandbeyond Capt. Gaurav Rana Riya shetty Shruti Arora Javeria A. Pinaki Dasgupta Sakina Bhanpurawala Jinal Lakdawala Jyothi Mendon Saniya Ansari Sobiya A. Taniya Modak Aaliya Kadri Anjali T. Pooja Yadav Shalu Jaiswal Mehjabeen Shaikh Smita Chauhan Disha Sawant Pratik Kini Sea Beyond Sea and Beyond

RAGAS is a quicker and cheaper alternative to using LLMs for evaluating the RAG pipeline's performance. In the second article of the Superlinked series, Atita Arora goes in-depth on how to set up your #RAGAS evaluation framework. Learn how to: ✅ Create an evaluation dataset that serves as a reference point for evaluating our RAG pipeline. ✅ Understand the evaluation metrics and how to make sense of them. ✅ Test a basic RAG pipeline and measure its performance using RAGAS metrics. This one goes deep, so get ready to dive in and enjoy the read!

SCADA time-series data is critical for utilities to monitor usage, optimize operations, and uncover inefficiencies. But traditional formats like SCADA interfaces, spreadsheets, and Power BI can be challenging for people with a vision impairment. We're committed to delivering accessible, high-impact tools for all utility staff. This blog describes a recent collaboration with WaterAble and Greater Western Water - and we thank them for this. 💌 #DisabilityInclusion #WaterUtilities #SmartWater #DigitalUtility #WaterManagement #WaterLoss #DataMining #Water

Data Minimalism and renewable energy are the key for the new era