This paper presents a reinforcement learning framework for optimizing energy pricing in peer-to-peer (P2P) energy systems. The framework aims to maximize the profit of all components in a microgrid, including consumers, prosumers, the service provider, and a community battery. Experimental results on the Pymgrid dataset demonstrate the approach's effectiveness in price optimization, considering the interests of different components and the impact of community battery capacity.
Nate Hagens from the University of Minnesota spoke at KAUST's Winter Enrichment Program (WEP) 2018 about the intersection of energy, human behavior, and economics. Hagens argued that society functions as an energy-dissipating "superorganism," with human preferences correlated with increasing energy needs. He emphasized that energy, not money, is the real capital, but global society is running out of it. Why it matters: The talk highlights the importance of viewing society through an ecological lens, particularly in the context of the GCC region's reliance on energy resources.
This paper introduces DaringFed, a novel dynamic Bayesian persuasion pricing mechanism for online federated learning (OFL) that addresses the challenge of two-sided incomplete information (TII) regarding resources. It formulates the interaction between the server and clients as a dynamic signaling and pricing allocation problem within a Bayesian persuasion game, demonstrating the existence of a unique Bayesian persuasion Nash equilibrium. Evaluations on real and synthetic datasets demonstrate that DaringFed optimizes accuracy and convergence speed and improves the server's utility.
KAUST and GE have partnered to study the feasibility of using crude oils like Arabian Super Light (ASL) to power heavy-duty gas turbines. The collaboration aims to develop turbines capable of burning crude oil directly from the ground to meet Saudi Arabia's energy security needs. The research involves building a rig at KAUST's High Pressure Combustion Laboratory (HPCL) to conduct corrosion tests on turbine materials by burning ASL/AXL crude continuously for 2,000 hours. Why it matters: This partnership could reduce reliance on natural gas and offer an economically viable alternative fuel source, bolstering energy security in Saudi Arabia and potentially influencing turbine technology worldwide.
This paper analyzes the energy consumption and carbon footprint of LLM inference in the UAE compared to Iceland, Germany, and the USA. The study uses DeepSeek Coder 1.3B and the HumanEval dataset to evaluate code generation. It provides a comparative analysis of geographical trade-offs for climate-aware AI deployment, specifically addressing the challenges and potential of datacenters in desert regions.
Marilyn Brown from Georgia Institute of Technology presented a talk at KAUST's Winter Enrichment Program 2022 on strategies to reduce carbon emissions. She emphasized developing localized solutions and highlighted business opportunities in enhancing energy systems through carbon reduction. Brown noted that achieving the Paris Accord goals requires a 50% reduction in greenhouse gas emissions by 2030. Why it matters: This underscores the importance of localized carbon reduction strategies and the potential for innovation in energy systems within the region, aligning with Saudi Arabia's Vision 2030 goals for sustainability.