Collective Learning for Energy-centric Flexible Job Shop Scheduling DOI
Arun Narayanan, Evangelos Pournaras, Pedro H. J. Nardelli

et al.

Published: June 19, 2023

Manufacturing industries can reduce their energy consumption by exploiting the flexibility in manufacturing processes, such as machine availability, flexible jobs, and resource usage. In this paper, we exploit inherent some schedules, to model an energy-centric job shop scheduling problem. We assume that there is limited electrical power machines, attempt match schedules of jobs available with objective minimizing consumption. propose collective learning, i.e., a form decentralized (and unsupervised) learning where autonomous agents coordinate decision-making collectively learn manage tasks be efficiently performed coordination, employed achieve this. present methodology combines plangeneration algorithm collective-learning tool—Iterative Economic Planning Optimized Selections (I-EPOS)—to solve problem near optimal-solutions. apply practical dataset comprising 3 machines 12 show decreases approximately 5% when they choose schedule instead acting independently or without any coordination. also it possible scale method large number obtain reasonable solutions quickly, coordination always outperforms uncoordinated independent actions increasing savings.

Language: Английский

Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation DOI Creative Commons
Robertas Damaševičius, Luka Jovanovic, Aleksandar Petrović

et al.

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e1795 - e1795

Published: Jan. 18, 2024

Renewable energy plays an increasingly important role in our future. As fossil fuels become more difficult to extract and effectively process, renewables offer a solution the ever-increasing demands of world. However, shift toward renewable is not without challenges. While reliable means storage that can be converted into usable energy, are dependent on external factors used for generation. Efficient often relying batteries have limited number charge cycles. A robust efficient system forecasting power generation from sources help alleviate some difficulties associated with transition energy. Therefore, this study proposes attention-based recurrent neural network approach generated sources. To networks make accurate forecasts, decomposition techniques utilized applied time series, modified metaheuristic introduced optimized hyperparameter values networks. This has been tested two real-world datasets covering both solar wind farms. The models by metaheuristics were compared those produced other state-of-the-art optimizers terms standard regression metrics statistical analysis. Finally, best-performing model was interpreted using SHapley Additive exPlanations.

Language: Английский

Citations

29
A Comprehensive Review of Bio-Inspired Optimization Algorithms Including Applications in Microelectronics and Nanophotonics DOI Creative Commons
Zoran Jakšić, Swagata Devi, Olga Jakšić

et al.

Biomimetics, Journal Year: 2023, Volume and Issue: 8(3), P. 278 - 278

Published: June 28, 2023

The application of artificial intelligence in everyday life is becoming all-pervasive and unavoidable. Within that vast field, a special place belongs to biomimetic/bio-inspired algorithms for multiparameter optimization, which find their use large number areas. Novel methods advances are being published at an accelerated pace. Because that, spite the fact there lot surveys reviews they quickly become dated. Thus, it importance keep pace with current developments. In this review, we first consider possible classification bio-inspired optimization because papers dedicated area relatively scarce often contradictory. We proceed by describing some detail more prominent approaches, as well those most recently published. Finally, biomimetic two related wide fields, namely microelectronics (including circuit design optimization) nanophotonics inverse structures such photonic crystals, nanoplasmonic configurations metamaterials). attempted broad survey self-contained so can be not only scholars but also all interested latest developments attractive area.

Language: Английский

Citations

40
Multi-policy deep reinforcement learning for multi-objective multiplicity flexible job shop scheduling DOI
Linshan Ding, Zailin Guan, Mudassar Rauf

et al.

Swarm and Evolutionary Computation, Journal Year: 2024, Volume and Issue: 87, P. 101550 - 101550

Published: April 1, 2024

Language: Английский

Citations

16
Energy-efficient job shop scheduling problem with transport resources considering speed adjustable resources DOI
Dalila B.M.M. Fontes, Seyed Mahdi Homayouni, João Chaves Fernandes

et al.

International Journal of Production Research, Journal Year: 2023, Volume and Issue: 62(3), P. 867 - 890

Published: Feb. 21, 2023

This work extends the energy-efficient job shop scheduling problem with transport resources by considering speed adjustable of two types, namely: machines where jobs are processed on and vehicles that around shop-floor. Therefore, being considered involves determining, simultaneously, processing each production operation, sequence operations for machine, allocation tasks to vehicles, travelling task empty loaded legs, vehicle. Among possible solutions, we interested in those providing trade-offs between makespan total energy consumption (Pareto solutions). To end, develop solve a bi-objective mixed-integer linear programming model. In addition, due complexity also propose multi-objective biased random key genetic algorithm simultaneously evolves several populations. The computational experiments performed have show it be effective efficient, even presence larger instances. Finally, provide extensive time trade-off analysis front) infer advantages general insights managers dealing such complex problem.

Language: Английский

Citations

18
Energy-Efficient Scheduling in Job Shop Manufacturing Systems: A Literature Review DOI Open Access

João M. R. C. Fernandes,

Seyed Mahdi Homayouni, Dalila B.M.M. Fontes

et al.

Sustainability, Journal Year: 2022, Volume and Issue: 14(10), P. 6264 - 6264

Published: May 20, 2022

Energy efficiency has become a major concern for manufacturing companies not only due to environmental concerns and stringent regulations, but also large incremental energy costs. Energy-efficient scheduling can be effective at improving thus reducing consumption associated costs, as well pollutant emissions. This work reviews recent literature on energy-efficient in job shop systems, with particular focus metaheuristics. We review 172 papers published between 2013 2022, by analyzing the floor type, strategy, objective function(s), newly added problem feature(s), solution approach(es). report existing data sets make them available research community. The paper is concluded pointing out potential directions future research, namely developing integrated approaches interconnected problems, fast metaheuristic methods respond dynamic hybrid big cyber-physical production systems.

Language: Английский

Citations

27
Job scheduling under Time-of-Use energy tariffs for sustainable manufacturing: a survey DOI
Daniele Catanzaro, Raffaele Pesenti, Roberto Ronco

et al.

European Journal of Operational Research, Journal Year: 2023, Volume and Issue: 308(3), P. 1091 - 1109

Published: Jan. 20, 2023

Language: Английский

Citations

16
A self-learning discrete salp swarm algorithm based on deep reinforcement learning for dynamic job shop scheduling problem DOI

Yiming Gu,

Ming Chen, Liang Wang

et al.

Applied Intelligence, Journal Year: 2023, Volume and Issue: 53(15), P. 18925 - 18958

Published: Feb. 14, 2023

Language: Английский

Citations

11
A transformer-based deep reinforcement learning approach for dynamic parallel machine scheduling problem with family setups DOI Creative Commons
Funing Li, Sebastian Lang, Yuan Tian

et al.

Journal of Intelligent Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 8, 2024

Abstract The parallel machine scheduling problem (PMSP) involves the optimized assignment of a set jobs to collection machines, which is proper formulation for modern manufacturing environment. Deep reinforcement learning (DRL) has been widely employed solve PMSP. However, majority existing DRL-based frameworks still suffer from generalizability and scalability. More specifically, state action design heavily rely on human efforts. To bridge these gaps, we propose practical learning-based framework tackle PMSP with new job arrivals family setup constraints. We variable-length matrix containing full information. This enables DRL agent autonomously extract features raw data make decisions global perspective. efficiently process this novel matrix, elaborately modify Transformer model represent agent. By integrating modified agent, representation can be effectively leveraged. innovative offers high-quality robust solution that significantly reduces reliance manual effort traditionally required in tasks. In numerical experiment, stability proposed during training first demonstrated. Then compare trained 192 instances several approaches, namely approach, metaheuristic algorithm, dispatching rule. extensive experimental results demonstrate scalability our approach its effectiveness across variety scenarios. Conclusively, thus problems high efficiency flexibility, paving way application solving complex dynamic problems.

Language: Английский

Citations

4
Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions DOI

Maziyar Khadivi,

Todd Charter, Marjan Yaghoubi

et al.

Computers & Industrial Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 110856 - 110856

Published: Jan. 1, 2025

Language: Английский

Citations

0
A comparative study of the performance of ten metaheuristic algorithms for parameter estimation of solar photovoltaic models DOI Creative Commons

Adel Zga,

Farouq Zitouni, Saad Harous

et al.

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2646 - e2646

Published: Jan. 27, 2025

This study conducts a comparative analysis of the performance ten novel and well-performing metaheuristic algorithms for parameter estimation solar photovoltaic models. optimization problem involves accurately identifying parameters that reflect complex nonlinear behaviours cells affected by changing environmental conditions material inconsistencies. is challenging due to computational complexity risk errors, which can hinder reliable predictions. The evaluated include Crayfish Optimization Algorithm, Golf Coati Crested Porcupine Optimizer, Growth Artificial Protozoa Secretary Bird Mother Election Optimizer Technical Vocational Education Training-Based Optimizer. These are applied solve four well-established models: single-diode model, double-diode triple-diode different module focuses on key metrics such as execution time, number function evaluations, solution optimality. results reveal significant differences in efficiency accuracy algorithms, with some demonstrating superior specific Friedman test was utilized rank various revealing top performer across all considered optimizer achieved root mean square error 9.8602187789E-04 9.8248487610E-04 both models 1.2307306856E-02 model. consistent success indicates strong contender future enhancements aimed at further boosting its effectiveness. Its current suggests potential improvement, making it promising focus ongoing development efforts. findings contribute understanding applicability renewable energy systems, providing valuable insights optimizing

Language: Английский

Citations

0