2023 International Conferences on Data Science, Agents, and Artificial Intelligence
Smart Optimization of Biogas Production for
Enhanced Gas Yield
2023 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI) | 979-8-3503-4891-0/23/$31.00 ©2023 IEEE | DOI: 10.1109/ICDSAAI59313.2023.10452630
D. Menaka S. Nandhakumar R. Abishek
Department of Computer Science Department of Computer Science Department of Computer Science
and Engineering and Engineering and Engineering
Sathyabama Institute of Science and Sathyabama Institute of Science and Sathyabama Institute of Science and
Technology, Technology, Technology,
India, India, India,
[email protected] [email protected] [email protected] M. Rahul Raghavendran A. S. Vishnu Hariharan
Department of Computer Science and Department of Computer Science
Engineering and Engineering
Sathyabama Institute of Science and Sathyabama Institute of Science and
Technology, Technology,
India, India,
[email protected] [email protected] Abstract: This study presents a novel approach to biogas production operations frequently falls short
enhance biogas generation by integrating the of its potential due to issues like poor process
capabilities of the Internet of Things (IoT) with organic conditions, lengthy digestion times[2], and
waste recycling. Although organic waste can be challenges handling various waste compositions [3].
harnessed to produce biogas, the conventional process
This project uses the capabilities of the Internet of
can be time-intensive. To optimize equipment control,
this research leverages IoT technology, involving the Things (IoT) in an effort to address these restrictions
connection of sensors to the internet. Continuous in a novel way that takes advantage of upcoming
monitoring of critical parameters such as temperature, technology[4].
acidity levels, waste volume, flow rate, waste
composition, and gas production rate is imperative. The way we interact with and manage our
The proposed Smart Optimized Biogas Production surroundings has been completely reimagined by the
(SOBP) system employs advanced computational Internet of Things[5], which is defined by the
analyses and machine learning techniques to internet-based connectivity of numerous objects.
dynamically adjust and stimulate the system's internal Incorporating IoT technologies to create an
conditions while it operates. Specifically, temperature intelligent and adaptable biogas production
and acidity levels are adapted based on the type of environment[6], this concept suggests a paradigm
waste being processed. This strategy aims to expedite
leap in biogas production. The central idea centers
biogas production while maintaining an efficient and
on real-time data monitoring and dynamic parameter
eco-friendly process. The potential outcomes of this
study are promising, including accelerated energy changes that adapt to the particular circumstances
production, reduced resource consumption, and a inside the biogas reactor. The system can
transition toward innovative and sustainable energy optimize[7] the biogas production process by
solutions. continually measuring and analyzing key
operational variables like temperature, pH, waste
Keywords - Biogas, ML Algorithm, Temperature Sensor,
composition, load weight, and flow rate[8-9].
pH level sensor, Load Cell, Arduino, IoT.
Conventional biogas production techniques
frequently function in a static environment and are
I. INTRODUCTION unable to adjust to changing microbial dynamics and
waste properties[10-11]. Due to this restriction, the
Biogas generation from organic waste
rate of gas production is less than ideal, and the
stands out as a strong response to the growing
digestion time is prolonged. The proposed IoT-
environmental problems and the need to switch to
driven method includes real-time adaptation to close
sustainable energy sources. Anaerobic digestion of
this gap[12]. IoT sensors will gather data inside the
organic matter yields biogas[1], a sustainable energy
biogas reactor, allowing for a thorough insight into
source with potential for both energy production and
the dynamics of the system. To find hidden patterns,
efficient waste management. The effectiveness of
979-8-3503-4891-0/23/$31.00 ©2023 IEEE
Authorized licensed use limited to: SRM Institute of Science and Technology- RamaPuram. Downloaded on January 09,2025 at 10:22:56 UTC from IEEE Xplore. Restrictions apply.
dependencies, and trends, the data will go through a ……………………..
thorough analysis using data analytics and machine
learning techniques. These revelations will guide the
skillful adjustment of critical process variables,
particularly pH and temperature, with accuracy
catered to the particular waste type being processed.
By fostering a climate that encourages the growth of
the microorganisms needed for effective biogas
production, this dynamic optimization aims to
increase gas yield.
This project's significance has many different facets.
The project directly contributes to reaching
renewable energy targets and developing sustainable
waste management practices by speeding biogas
generation while guaranteeing ideal conditions. The
primary goal of promoting eco-friendly practices is
aligned with the decreased resource usage and
increased energy output. The combination of IoT-
enabled intelligence has the ability to set a new
course toward a greener and more efficient energy Fig. 1. Work Flow of the SOBP System.
future as biogas grows popularity as a workable
renewable energy source. An extensive network of sensors is strategically
positioned throughout the biogas production system
II. METHODOLOGY as the project's foundation. These sensors
Although the production of biogas from organic continuously track vital indicators that are necessary
waste is a promising renewable energy option, for the production of biogas. Temperature, pH
efficiency issues including sluggish gas generation levels, gas composition, humidity, and other factors
and unfavorable process conditions limit its are among the parameters. The production
potential. The potential of the Internet of Things environment is thoroughly understood thanks to the
(IoT) and biogas production systems must be regular data collection. Using fundamental IoT
combined in an innovative way to increase gas yield networking techniques, the captured data is
and streamline waste-to-energy conversion. smoothly sent to a central computer. The center of
the data processing is this computer. The incoming
The development and deployment of an IoT-enabled data is methodically organized and securely stored
system that optimizes biogas production by in a data repository once it reaches the central
dynamically altering key operational factors is computer. This repository provides historical and
covered within the project's scope. The main goal is real-time datasets and acts as a database center for
to employ real-time data gathering, analysis, and data management.
feedback systems to promote wiser decision-making
within the biogas digester. The research uses sophisticated machine learning
techniques concurrently. These algorithms use
In order to achieve Real-Time Data Collection, historical datasets and present-day sensor inputs to
analysis and prediction of collected data, dynamic continuously assess the incoming data. Their main
parameter adjustment, and user-friendly interface to job is to forecast and suggest the best parameter
provide insight on processes, production rate, and changes for maximizing biogas production. These
performance, the proposed SOBP system will suggestions are founded on the data's patterns,
integrate sensors, microcontrollers, actuators, cloud correlations, and predictive insights.
computing, data analytics, and machine learning
techniques as depicted in figure 1. It will also allow The system's capacity to affect substantial change in
the production process is the main focus of this
users to manually intervene and adjust parameters.
research. The essential parameters in the biogas
production system are manually adjusted in response
to suggestions from the machine learning algorithm.
Temperature, feedstock ratios, gas recirculation
rates, and other variables may all need to be
adjusted. The modifications are exact and made in
reaction to the industrial environment's constantly
Authorized licensed use limited to: SRM Institute of Science and Technology- RamaPuram. Downloaded on January 09,2025 at 10:22:56 UTC from IEEE Xplore. Restrictions apply.
shifting conditions. The system maintains a
watchful monitoring process to guarantee continued
optimization and adaptability. It continuously
evaluates how parameter changes affect the biogas
production process, and if any unfavourable changes
are seen, it notifies the authorized users so that
manual control can be used to avert potential risks.
The ultimate goal of this workflow is to produce
biogas as quickly and as efficiently as feasible. The
system makes an effort to accomplish this by
ongoing data analysis, in-the-moment parameter
modifications, and adaptive optimization. A smart,
self-improving biogas production method that
Fig. 4. Circuit for measuring Gas Type.
maximizes output while decreasing resource use and
operational costs is the end result.
III. DEVICE DESIGN AND WORK FLOW The Arduino Uno R3 Microcontroller, Power
Source, Temperature Sensor, pH Sensor, Gas Sensor,
A. Device Design Resistors, IC, Speaker, etc. are some of the
The device's design incorporates a number of electronic components used in the circuit as in figure
circuits that were created independently and 4. The circuits' schematic designs are as follows:
then merged to create a single working
B. Working Flow of the Device
environment as shown in figure 2. The pH,
temperature, and gas in the biogas tank are
measured by these separate circuits from figure
2, 3 and 4.
Fig. 2. Circuit for measuring pH value.
Fig. 5. flow chat of SOBP system to enhance Gas yield.
IV. RESULTS
Two Biogas Digester were used at a same time
under the same condition and environment for 6
days to test the optimized production of the biogas
as depicted in figure 6. The load used in the
Fig. 3. Circuit for measuring Temperature.
experimented biogas digester is food waste of same
type.
Authorized licensed use limited to: SRM Institute of Science and Technology- RamaPuram. Downloaded on January 09,2025 at 10:22:56 UTC from IEEE Xplore. Restrictions apply.
[2] AKP Meyer, EA Ehimen, JB Holm-Nielsen, "Future
European biogas: Animal manure, straw, and grass
potentials for a sustainable European biogas production",
Biomass and Bioenergy, vol. 111, 2018, pp. 154-164.
[3] W. A. Ahmed, M. Aggour and F. Bennani, "Smart System
for biodigester monitoring." in 3rd International Renewable
and Sustainable Energy Conference (IRSEC), 2015.
[4] S Yang, Y Liu, N Wu, Y Zhang, S Svoronos, "Low-cost,
Arduino- based, portable device for measurement of
methane composition in biogas", Renewable Energi, vol.
138, 2019, pp. 224-229.
[5] F. Xia, L. Yang, L. Wang and A. Vinel, "Internet of
Things." International Journal of Communication System,
2012.
[6] D. J. Batstone, J. Keller and L. L. Blackall. "The influence
Fig. 6. Simulation results of Biogas Production Rate for 6 days of substrate kinetics on the microbial community structure
in granular anaerobic biomass," Water Research, 2004.
According to the calculated methods from [7] A. H. Abdurrahman, M. R. Kirom and A. Suhendi, "Biogas
the traditional datasets, the accuracy of 87.51% is Production Volume Measurement and Internet of Things
based Monitoring System," 2020 IEEE International
obtained in prediction using proposed SOBP system Conference on Communication, Networks and Satellite
in the same parameters are recommended to change (Comnetsat), Batam, Indonesia, 2020, pp. 213-217, doi:
by this model has been tweaked correctly and the 10.1109/Comnetsat50391.2020.9328948.
[8] X. Zhen, X. Zhang, Y. Bai, M. Luo, C. Tan and S. Li,
recorded value is represented in the graph shown in "Feasibility Analysis of Solar Constant Temperature Biogas
figure 7. Production System," 2022 3rd International Conference on
Advanced Electrical and Energy Systems (AEES), Lanzhou,
China, 2022, pp. 103-108, doi:
10.1109/AEES56284.2022.10079430.
[9] L. U. Urazaeva and N. N. Datsun, "Biogas Production:
Current State and Mathematical Modelling," 2018 IEEE
International Conference"Management of Municipal Waste
as an Important Factor of Sustainable Urban Development"
(WASTE), St. Petersburg, Russia, 2018, pp. 75-78, doi:
10.1109/WASTE.2018.8554129.
[10] T. Tenzin et al., "Optimization of Biogas Production from
Kitchen Waste installed at College of Science and
Technology," 2018 International Conference on
Computing, Power and Communication Technologies
(GUCON), Greater Noida, India, 2018, pp. 956-960, doi:
10.1109/GUCON.2018.8674963.
Fig. 7. Simulation results of Biogas Production Rate for 6 days [11] M. Kismurtono, H. Julendra, E. Mahajoeno and M.
using proposed SOBP system. Korniawan, "Development of enhanced biogas production
from palm oil mill effluent (POME)," 2016 International
V. CONCLUSION Conference on Cogeneration, Small Power Plants and
District Energy (ICUE), Bangkok, Thailand, 2016, pp. 1-7,
The SOBP system under consideration forecasts doi: 10.1109/COGEN.2016.7728954.
[12] Y. -z. Wang et al., "Screen of important metal ions on
biogas production with an impressive accuracy of biogas production by stalk," 2010 International Conference
87.51%. It signifies a potential paradigm shift in on Mechanic Automation and Control Engineering, Wuhan,
enhancing biogas generation efficiency by China, 2010, pp. 5207-5209, doi:
10.1109/MACE.2010.5535441.
seamlessly integrating IoT technology, machine
learning, and dynamic control systems. This
achievement aligns with the overarching objective
of advancing clean energy and environmental
stewardship while also tackling existing production
limitations. This endeavor stands as a testament to
the transformative influence technology can wield
on renewable energy and waste management
practices as we navigate towards a future
characterized by sustainability and ecological
awareness.
REFERENCES
[1] B Deepanraj, V Sivasubramanian, S Jayaraj, "Biogas
Generation through Anaerobic Digestion Process-An
Overview", Research Journal of Chemistry and
Environment, vol 18(25), 2014, pp. 80-93.
Authorized licensed use limited to: SRM Institute of Science and Technology- RamaPuram. Downloaded on January 09,2025 at 10:22:56 UTC from IEEE Xplore. Restrictions apply.
