Building energy management is essential for achieving carbon reduction goals, improving occupant comfort and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS’s strong performance over existing methods, showing that STEMS achieves 21% cost reduction and 18% emission reduction over traditional methods, 65% safety violation reduction compared with learning-based baselines, and maintains the lowest discomfort rate. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types.

Accurate electric load forecasting is of critical importance for modern power grids. It can help optimize energy management, reduce operational costs, and enhance grid stability. Existing load forecasting tools typically perform well when modelling long-term trends with substantive data upon which to build a model, but can perform poorly for short-term load forecasting or when data is sparse or incomplete. Diffusion models have recently emerged as powerful generative tools that excel in modelling complex distributions, making them a promising approach for electric load forecasting. In this paper, we build upon recent diffusion models for time series forecasting and explore the potential of combining diffusion models with prior models to improve performance. Additionally, we propose a metric-based meta-learning approach for fast data adaptation. Experimental results with this metric-based meta-learning approach on real-world load forecasting datasets outperform state-of-the-art baselines, showcasing the potential of diffusion-based refinement in practical forecasting applications.

Time series data permeates our daily existence and has been recognized as of significant importance for many sectors, such as energy, transportation, telecommunication, and health care. Ensemble learning stands as a prevalent technique in time series forecasting, adept at handling dynamic data distributions and enhancing robustness. Nevertheless, the determination of model combination weights for computing ensemble outputs remains an unresolved issue. In this endeavour, we introduce a comprehensive reinforcement learning-based approach to tackle this challenge. Moreover, our method remains agnostic to the base models within the ensemble and exhibits versatility across a spectrum of time series forecasting tasks, thereby holding promise for application across diverse real-world scenarios. In this work, we extensively test the performance of our method on real-world datasets. Experimental results show that our proposed method achieves an average 6.2% forecasting accuracy improvement over all other single baseline methods.

This paper introduces a thermographic vision system to detect different types of hotspots on a variety of cable junctions commonly found in Hydro-Québec underground electrical distribution network. Cable junctions of underground distribution networks operate in harsh conditions, potentially leading to failure overtime. Faults can be prevented by the timely detection of local hotspot on these junctions. Hotspot detection is carried out by mean of image segmentation using a deep neural network. Special care is given to uncertainty estimation and validation. Uncertainty is used to assess the quality of a segmentation to avoid misdiagnosis or returning in the field to recapture images. It is also proposed as a tool to evaluate whether unannotated images should be included in the dataset. System performance has been evaluated on a test dataset as well as in the field by regular inspection teams. Promising results obtained so far led to the deployment of the vision system on a fleet of five inspection trucks performing inspection over the province over the last year Authorization was granted to scale the solution to 35 trucks starting this year.

In most research papers, the industrial car sequencing problem, as defined during the ROADEF 2005 Challenge, has been tackled by organizing objectives in a hierarchy. However from a decision-making viewpoint it would be interesting to tackle this problem in a Pareto sense. Indeed, tackling the problem in Pareto sense can offer greater latitude to a manager by presenting him several alternative solutions. In this paper, we suggest to adapt the GISMOO algorithm to solve the industrial car sequencing problem. A comparison of the performance is carried out using well-known published algorithms and proves an advantage for GISMOO. As well, we aim to demonstrate the relevance of handling applied problems such as the industrial car sequencing problem using a Pareto multi-objective approach.

Until now, the industrial car sequencing problem, as defined during the ROADEF 2005 Challenge, has been tackled by organizing objectives in a hierarchy. In this paper, we suggest tackling this problem in a Pareto sense for the first time. We thus suggest the adaptation of the PMSMO, an elitist evolutionary algorithm which distinguishes itself through a fitness calculation that takes into account the history of solutions found so as to diversify the compromise solutions along the Pareto frontier. A comparison of the performance is carried out using a well-known published algorithm, the NSGAII, and proves an advantage for the PMSMO. As well, we aim to demonstrate the relevance of handling applied problems such as the car sequencing problem using a multi-objective approach.

In this paper, we present three new integrative approaches for solving the classical car sequencing problem. These approaches are essentially based on a genetic algorithm which incorporates two crossover operators using an integer linear programming model. The two proposed hybrid crossover are combined efficiently in a genetic algorithm and we show that the hybrid approach outperforms a genetic algorithm with local search on the CSPLib benchmarks. Although that the computations time are long when integrative hybridization is used, this study well illustrates the interest of designing hybrid approaches exploiting the strengths of different methods.