Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations such as latency, cost, available compute resource and internet connectivity are relevant in determining an appropriate approach. We consider the setting where some local compute capacity is available at inference time but internet connectivity is not. Similar to a general-purpose LLM, we assume that our much smaller Reasoning Models may be asked arbitrary questions from unknown distributions, so we focus on evaluation in an unseen setting. We train our models to answer diverse questions by instilling an ability to reason over a retrieved context. We acquire context from two knowledge sources; a Wikipedia corpus queried using a multi-hop dense retrieval system with novel extensions, and from rationales generated from a larger Language Model optimised to run in a lower resource environment. Our main contributions: We propose novel methods to show that our model is capable of answering contextualised questions without memorisation. We establish a comprehensive set of baseline results on unseen evaluation datasets. We show that the addition of novel retrieval-augmented training datasets (RATD) to the training regime of the Reasoning Model significantly improves results. We demonstrate further significant improvement through the application of methods for combining knowledge from two sources. The first method (RR) involves training a novel Rationale Ranking model to score both generated rationales and retrieved contexts with respect to relevance and truthfulness. We use the scores to derive combined contexts. We also show that utilising the RATD datasets enables our model to become proficient at utilising combined noisy contexts.

Virtual bidding plays an important role in two-settlement electric power markets, as it can reduce discrepancies between day-ahead and real-time markets. Renewable energy penetration increases volatility in electricity prices, making accurate forecasting critical for virtual bidders, reducing uncertainty and maximizing profits. This study presents a Transformer-based deep learning model to forecast the price spread between real-time and day-ahead electricity prices in the ERCOT (Electric Reliability Council of Texas) market. The proposed model leverages various time-series features, including load forecasts, solar and wind generation forecasts, and temporal attributes. The model is trained under realistic constraints and validated using a walk-forward approach by updating the model every week. Based on the price spread prediction results, several trading strategies are proposed and the most effective strategy for maximizing cumulative profit under realistic market conditions is identified through backtesting. The results show that the strategy of trading only at the peak hour with a precision score of over 50% produces nearly consistent profit over the test period. The proposed method underscores the importance of an accurate electricity price forecasting model and introduces a new method of evaluating the price forecast model from a virtual bidder's perspective, providing valuable insights for future research.

Training large-scale neural networks in vision, and multimodal domains demands substantial memory resources, primarily due to the storage of optimizer states. While LoRA, a popular parameter-efficient method, reduces memory usage, it often suffers from suboptimal performance due to the constraints of low-rank updates. Low-rank gradient projection methods (e.g., GaLore, Flora) reduce optimizer memory by projecting gradients and moment estimates into low-rank spaces via singular value decomposition or random projection. However, they fail to account for inter-projection correlation, causing performance degradation, and their projection strategies often incur high computational costs. In this paper, we present COAP (Correlation-Aware Gradient Projection), a memory-efficient method that minimizes computational overhead while maintaining training performance. Evaluated across various vision, language, and multimodal tasks, COAP outperforms existing methods in both training speed and model performance. For LLaMA-1B, it reduces optimizer memory by 61% with only 2% additional time cost, achieving the same PPL as AdamW. With 8-bit quantization, COAP cuts optimizer memory by 81% and achieves 4x speedup over GaLore for LLaVA-v1.5-7B fine-tuning, while delivering higher accuracy.

Accurate and reliable electricity price forecasting has significant practical implications for grid management, renewable energy integration, power system planning, and price volatility management. This study focuses on enhancing electricity price forecasting in California's grid, addressing challenges from complex generation data and heteroskedasticity. Utilizing principal component analysis (PCA), we analyze CAISO's hourly electricity prices and demand from 2016-2021 to improve day-ahead forecasting accuracy. Initially, we apply traditional outlier analysis with the interquartile range method, followed by robust PCA (RPCA) for more effective outlier elimination. This approach improves data symmetry and reduces skewness. We then construct multiple linear regression models using both raw and PCA-transformed features. The model with transformed features, refined through traditional and SAS Sparse Matrix outlier removal methods, shows superior forecasting performance. The SAS Sparse Matrix method, in particular, significantly enhances model accuracy. Our findings demonstrate that PCA-based methods are key in advancing electricity price forecasting, supporting renewable integration and grid management in day-ahead markets. Keywords: Electricity price forecasting, principal component analysis (PCA), power system planning, heteroskedasticity, renewable energy integration.

The present study aims to evaluate the current fuzzy landscape of Trustworthy AI (TAI) within the European Union (EU), with a specific focus on the energy sector. The analysis encompasses legal frameworks, directives, initiatives, and standards like the AI Ethics Guidelines for Trustworthy AI (EGTAI), the Assessment List for Trustworthy AI (ALTAI), the AI act, and relevant CEN-CENELEC standardization efforts, as well as EU-funded projects such as AI4EU and SHERPA. Subsequently, we introduce a new TAI application framework, called E-TAI, tailored for energy applications, including smart grid and smart building systems. This framework draws inspiration from EGTAI but is customized for AI systems in the energy domain. It is designed for stakeholders in electrical power and energy systems (EPES), including researchers, developers, and energy experts linked to transmission system operators, distribution system operators, utilities, and aggregators. These stakeholders can utilize E-TAI to develop and evaluate AI services for the energy sector with a focus on ensuring trustworthiness throughout their development and iterative assessment processes.

Mixture-of-Experts (MOE) has garnered significant attention for their ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does not relieve the massive memory requirements of networks, which limits their practicality in real-world applications, especially in the era of large language models (LLMs). While recent work explores the possibility of removing entire layers of MoE to reduce memory, the performance degradation is still notable. In this paper, we propose Condense-MoE (CD-MoE} that, instead of dropping the entire MoE layer, condenses the big, sparse MoE layer into a small but dense layer with only a few experts that are activated for all tokens. Our approach is specifically designed for fine-grained MoE with shared experts, where Feed-Forward Networks are split into many small experts, with certain experts isolated to serve as shared experts that are always activated. We demonstrate the effectiveness of our method across multiple MoE models such as DeepSeekMoE and QwenMoE on various benchmarks. Specifically, for the DeepSeekMoE-16B model, our approach maintains nearly 90% of the average accuracy while reducing memory usage by 30% and enhancing inference speed by 30%. Moreover, we show that with lightweight expert fine-tuning, the pruned model can achieve further improvements on specific tasks. Our code are available at https://github.com/duterscmy/CD-MoE/tree/main.

Recurrent stochastic configuration networks (RSCNs) have shown great potential in modelling nonlinear dynamic systems with uncertainties. This paper presents an RSCN with hybrid regularization to enhance both the learning capacity and generalization performance of the network. Given a set of temporal data, the well-known least absolute shrinkage and selection operator (LASSO) is employed to identify the significant order variables. Subsequently, an improved RSCN with L2 regularization is introduced to approximate the residuals between the output of the target plant and the LASSO model. The output weights are updated in real-time through a projection algorithm, facilitating a rapid response to dynamic changes within the system. A theoretical analysis of the universal approximation property is provided, contributing to the understanding of the network's effectiveness in representing various complex nonlinear functions. Experimental results from a nonlinear system identification problem and two industrial predictive tasks demonstrate that the proposed method outperforms other models across all testing datasets.

The forecasting skill of numerical weather prediction (NWP) models critically depends on the accurate initial conditions, also known as analysis, provided by data assimilation (DA). Traditional DA methods often face a trade-off between computational cost and accuracy due to complex linear algebra computations and the high dimensionality of the model, especially in nonlinear systems. Moreover, processing massive data in real-time requires substantial computational resources. To address this, we introduce an artificial intelligence-based data assimilation framework (ADAF) to generate high-quality kilometer-scale analysis. This study is the pioneering work using real-world observations from varied locations and multiple sources to verify the AI method's efficacy in DA, including sparse surface weather observations and satellite imagery. We implemented ADAF for four near-surface variables in the Contiguous United States (CONUS). The results indicate that ADAF surpasses the High Resolution Rapid Refresh Data Assimilation System (HRRRDAS) in accuracy by 16% to 33% for near-surface atmospheric conditions, aligning more closely with actual observations, and can effectively reconstruct extreme events, such as tropical cyclone wind fields. Sensitivity experiments reveal that ADAF can generate high-quality analysis even with low-accuracy backgrounds and extremely sparse surface observations. ADAF can assimilate massive observations within a three-hour window at low computational cost, taking about two seconds on an AMD MI200 graphics processing unit (GPU). ADAF has been shown to be efficient and effective in real-world DA, underscoring its potential role in operational weather forecasting.

The Jaya R package offers a robust and versatile implementation of the parameter-free Jaya optimization algorithm, suitable for solving both single-objective and multi-objective optimization problems. By integrating advanced features such as constraint handling, adaptive population management, Pareto front tracking for multi-objective trade-offs, and parallel processing for computational efficiency, the package caters to a wide range of optimization challenges. Its intuitive design and flexibility allow users to solve complex, real-world problems across various domains. To demonstrate its practical utility, a case study on energy modeling explores the optimization of renewable energy shares, showcasing the package's ability to minimize carbon emissions and costs while enhancing system reliability. The Jaya R package is an invaluable tool for researchers and practitioners seeking efficient and adaptive optimization solutions.

Analytical framework for predicting General Matrix Multiplication (GEMM) performance on modern GPUs, focusing on runtime, power consumption, and energy efficiency. Our study employs two approaches: a custom-implemented tiled matrix multiplication kernel for fundamental analysis, and NVIDIA's CUTLASS library for comprehensive performance data collection across advanced configurations. Using the NVIDIA RTX 4070 as our experimental platform, we developed a Random Forest-based prediction model with multi-output regression capability. Through analysis of both naive tiled matrix multiplication with varying tile sizes (1 to 32) and 16,128 CUTLASS GEMM operations across diverse configurations, we identified critical performance patterns related to matrix dimensions, thread block configurations, and memory access patterns. Our framework achieved exceptional accuracy with an R^2 score of 0.98 for runtime prediction (mean error 15.57%) and 0.78 for power prediction (median error 5.42%). The system successfully predicts performance across matrix sizes, demonstrating robust scaling behavior. Our results show that optimal tile size selection can improve performance by up to 3.2x while reducing power consumption by 22% compared to baseline configurations. Analysis of shared memory utilization and SM occupancy reveals that tile sizes of 16x16 achieve the best balance between parallelism and resource usage. The implementation of our framework, including prediction models and analysis tools, is available as an open-source project at GPPerf [https://github.com/pavlyhalim/GPPerf].