Search

Chiller systems hold a critical role in upholding comfort and energy efficiency within commercial buildings. Precise prediction of chiller energy consumption is imperative for operational optimization and the reduction of energy expenditures. This paper introduces an innovative methodology that integrates deep learning (DL), specifically Fixed Forward Neural Networks (FFNN), with Teaching-Learning-Based Optimization (TLBO) to enhance the accuracy of chiller energy consumption forecasts. Drawing on a diverse dataset from a commercial building, encompassing vital input parameters such as Chilled Water Rate, Building Load, Cooling Water Temperature, Humidity, and Dew Point, the study conducts a comprehensive comparison of metaheuristic algorithms (Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Barnacles Mating Optimizer (BMO), Harmony Search Algorithm (HSA), Differential Evolution (DE), Ant Colony Optimization (ACO), and the latest RIME algorithm). TLBO's adept navigation of the intricate parameter space of DL yields highly precise predictions for chiller energy consumption. The study's outcomes underscore TLBO's potential, along with other metaheuristics, in optimizing DL and refining energy management practices in commercial buildings. This research significantly contributes to the evolving discourse on the symbiosis between DL, particularly FFNNs, and metaheuristic optimization, offering a robust framework for chiller energy consumption prediction, thereby advancing sustainability and cost-effectiveness in building operations. • Hybrid TLBO-DL is used in predicting the chiller energy consumption. • Real data from a commercial building is used for training and testing of TLBO-DL. • TLBO-DL shows potential in predicting chiller energy consumption compared to others. [ABSTRACT FROM AUTHOR]

Flue gas water-alternating gas (flue gas-WAG) is a promising technique for enhancing oil production and reducing greenhouse gas emissions. The effective utilization of this technique relies on identifying the optimal factors, often determined through numerous numerical simulations. This paper introduces a cost-effective optimization framework that integrates machine learning models and diverse optimization algorithms to identify the best parameters for injecting flue gas-WAG into the "Gullfaks" reservoir. Robust Machine learning models, including Multilayer Perceptron, Cascade Forward Neural Network (CFNN), Radial Basis Function, and Generalized Regression Neural Network, were employed as proxy models. The CFNN model, with satisfactory agreement with actual data (average absolute relative error of 0.4543 % for oil recovery factor (RF) and 1.9366 % for CO 2 storage), is selected for optimization through metaheuristic algorithms, including Non-dominated sorting genetic algorithm version II (NSGA-II), Pareto envelope-based selection Algorithm version-II (PESA_II), Multi-objective particle swarm optimization (MOPSO), and Multi-objective gray wolf optimization (MOGWO(. Among the optimization algorithms, MOGWO outperforms others in terms of speed and accuracy, yielding Pareto-optimal solutions with an RF of 0.8284 and a CO 2 storage of 1.5314 × 107 (kg-mol). The proposed approach uses Pareto dominance for insightful field development planning, enabling decision-makers to choose flue gas-WAG parameters based on future circumstances. [Display omitted] • A robust optimization framework is proposed for flue gas storage and enhanced oil recovery. • NSGA-II, MOPSO, MOGWO and PESA-II algorithms are utilized to optimize the water-alternating flue gas process. • CFNN, MLP, RBFNN, and GRNN are developed as proxy models that imitate the numerical simulator. • CFNN outperforms all developed models with AAPRE of 0.4543 % and 1.9633 % to estimate oil recovery factor and CO 2 storage, respectively. • The created Pareto fronts allow flexible applicability conditions to examine the design factors of the process. [ABSTRACT FROM AUTHOR]