Constructing a smart framework for supplying the biogas energy in green buildings using an integration of response surface methodology, artificial intelligence and petri net modelling. (15th November 2021)

• Record Type: Journal Article
• Authors: Shahsavar, Mohammad M.; Akrami, Mehran; Gheibi, Mohammad; Kavianpour, Babak; Fathollahi-Fard, Amir M.; Behzadian, Kourosh
• Is Part Of: Energy conversion and management. Volume 248(2021)
• Publication Date: 2021-11-15
• Subjects: Biogas -- Solid waste management -- Response surface methodology -- Artificial intelligence -- Petri net modelling; Direct energy conversion -- Periodicals; Energy storage -- Periodicals; Energy transfer -- Periodicals; Énergie -- Conversion directe -- Périodiques; Direct energy conversion; Periodicals; 621.3105
• DOI: 10.1016/j.enconman.2021.114794
• Languages: English
• ISSNs: 0196-8904

Abstract

Highlights: Creating a biogas setup for household energy applications based on biological wastes in green buildings. The proposed methodology combines the Clostridiales, wastewater treatment plant's sludge and food wastes' activities. Optimizing the effective parameters on the biogas production in green buildings with the CCD and RSM. Constructing a smart model using the RT, RF, ANN and ANFIS algorithms. Presenting a controlling model in green buildings with the Petri net system. Abstract: Nowadays, energy crisis is considered an essential active issue for future urbanization in megacities. While the rate of population growth increases, the volume of municipal solid waste production increases significantly. This highlights the need of Sustainable Development Goals (SDGs) for both developed and developing countries. This paper constructs a novel smart framework for supplying biogas energy. Our study is applicable for fields of waste management and energy supply in green buildings. The proposed framework integrates the Response Surface Methodology (RSM), Artificial Intelligence (AI), and Petri net modeling. In this regard, the AI techniques including the Random Tree (RT), Random Forest (RF), Artificial Neural Network (ANN) and, Adaptive-Network-based Fuzzy Inference System (ANFIS) are employed. In addition, for creating the optimum condition, a dynamic control system using the Petri Net modeling is applied. Among all machine learning methods, ANFIS with 0.99 correlation coefficient had the best accuracy for Accumulated Biogas Production (ABP) based on effective factors. Finally, the main findings of this paper are to introduce a novel framework for addressing different scientific issues such as supplying the clean energy in green buildings, the development of a smart and sustainable biogas production control system, integration of solid waste management with the SDGs in green buildings.