A Physics-Informed Neural Network (PINN) is a machine learning architecture designed to solve scientific problems by harmonizing data with physical laws. Its core innovation lies in training a neural network not only to fit observed data but also to adhere to known governing equations, typically ordinary or partial differential equations. This is achieved by incorporating…
Competitive electricity markets are inherently complex. They require the integration of technically feasible operations, grounded in physical laws, with economically viable solutions that incentivize investments. These interactions aim to ensure a reliable, efficient, and technologically flexible market design. However, the operation of these markets is neither trivial nor perfect. Over time, they are exposed to…
The emergence of the sharing economy has fundamentally altered paradigms of resource utilization, shifting the emphasis from individual ownership to collective access. This transformation, evident across domains such as transportation, housing, and digital infrastructure, is increasingly penetrating the energy sector. In particular, Battery Energy Storage Systems (BESS) are being reconceptualized as shared assets capable of…
This post summarizes our recent open-access publication in Energies.Read the full article here. Why Focus on Long-Term Load Forecasting? Long-term load forecasting (LTLF) is a crucial tool for planning and operating electric power systems. Accurate forecasts help system operators and planners make informed decisions about investments, operations, and policy. However, LTLF faces major challenges due…
In this article, I review the research in the 2024 NeurIPS conference paper, From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection, by Wang et al. The paper explores integrating event analysis into LLM-based time-series forecasting models. Real-time text such as news articles or social media posts are underutilized in…
Photovoltaic (PV) systems are key to the transition toward clean energy, but their real-world performance is shaped by complex environmental interactions. For researchers working on the physics of solar energy systems, understanding how variables like temperature, humidity, aerosols, and wind impact panel efficiency provides a critical foundation for deeper modeling and analysis. This blog post…
Recent advancements in the field of Natural Language Processing (NLP) and Large Language Models (LLMs) have opened new avenues for processing qualitative data. This development is particularly interesting for power systems as they have an enormous amount of untapped qualitative data. Decision-making in the power system sector has relied on quantitative data. However, qualitative data…
Author: Hamidreza Zareipour Although all research presentations share a common goal of conveying content, the most effective ones are tailored to the specific context and audience. These factors can drastically shape both the content and style of your talk. Presenting your findings at a final thesis defence differs in essential ways from delivering a presentation…
This study explores the impact of weather features on short to medium electricity load prediction across diverse geographical locations. Using hourly load data, we evaluated the effectiveness of several feature selection methods, including Mutual Information (MI), Principal Component Analysis (PCA), Lasso, and Heatmap correlation. We benchmarked these feature selection methods with a hybrid deep learning model to investigate the impact of choosing…
Transformers, powered by scaling laws, have transformed the landscape of AI, but their performance in time series forecasting is less definitive. This post explores the effectiveness of transformers, the challenges of scaling, and the rise of specialized foundation models like TTM, MOMENT, and Chronos. Do these big models live up to the hype, or are…