Random Forest-Based Method for Micro Grid System in Energy Consumption Prediction

Raj, Murugananth Gopal; Pradip, C.; Saju, N; Sangeetha, S.

doi:10.1088/1742-6596/1964/5/052002

Cited by 3 publications

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

Wicaksono,

Trat,

Bashyal

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The transition towards renewable electricity provides opportunities for manufacturing companies to save electricity costs through participating in demand response programs. End-to-end implementation of demand response systems focusing on manufacturing power consumers is still challenging due to multiple stakeholders and subsystems that generate a heterogeneous and large amount of data. This work develops an approach utilizing artificial intelligence for a demand response system that optimizes industrial consumers’ and prosumers’ production-related electricity costs according to time-variable electricity tariffs. It also proposes a semantic middleware architecture that utilizes an ontology as the semantic integration model for handling heterogeneous data models between the system’s modules. This paper reports on developing and evaluating multiple machine learning models for power generation forecasting and load prediction, and also mixed-integer linear programming as well as reinforcement learning for production optimization considering dynamic electricity pricing represented as Green Electricity Index (GEI). The experiments show that the hybrid auto-regressive long-short-term-memory model performs best for solar and convolutional neural networks for wind power generation forecasting. Random forest, k-nearest neighbors, ridge, and gradient-boosting regression models perform best in load prediction in the considered use cases. Furthermore, this research found that the reinforcement-learning-based approach can provide generic and scalable solutions for complex and dynamic production environments. Additionally, this paper presents the validation of the developed system in the German industrial environment, involving a utility company and two small to medium-sized manufacturing companies. It shows that the developed system benefits the manufacturing company that implements fine-grained process scheduling most due to its flexible rescheduling capacities.

show abstract

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

Wicaksono,

Trat,

Bashyal

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

Machine learning scopes on microgrid predictive maintenance: Potential frameworks, challenges, and prospects

Arafat,

Hossain,

Alam

2024

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

A multi-gas sensor for environmental gases: towards miniaturization with mid-infrared Quantum Cascade Lasers (QCL) and silicon integration of photoacoustic cells

Constancias,

Ben Bakir,

Doron

et al. 2024

Optical Sensing and Detection VIII

View full text Add to dashboard Cite

Atmospheric composition varies both spatially and temporally, notably in terms of relative humidity and greenhouse gases. Current methods rely on massive and expensive sensors deployed sparsely. Here, we are interested in developing a multigas sensor that targets very small atmospheric composition variations. In addition, it intends to be gas specific, lightweight, autonomous and compact. Targeted gases are either greenhouse gases such as CO2, CH4 and N2O, or toxic gases such as CO and SO2. For this purpose, we have developed a Photoacoustic Spectroscopy sensor, using Mid Infrared QCL laser sources (Quantum Cascad Lasers), which achieve a very narrow spectral linewidth and have a good potential for miniaturization. We developed a dedicated electronic device to perform data acquisition. Our prototype begins its calibration phase in a laboratory environment, prior further integration for real time measurements.

show abstract

Random Forest-Based Method for Micro Grid System in Energy Consumption Prediction

Cited by 3 publications

References 8 publications

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

Artificial-intelligence-enabled dynamic demand response system for maximizing the use of renewable electricity in production processes

Machine learning scopes on microgrid predictive maintenance: Potential frameworks, challenges, and prospects

A multi-gas sensor for environmental gases: towards miniaturization with mid-infrared Quantum Cascade Lasers (QCL) and silicon integration of photoacoustic cells

Contact Info

Product

Resources

About