Neural network-assisted integration of renewable sources in microgrids: A case study
This study examines the incorporation of renewable energy sources into microgrids using neural network-assisted optimization methods. The objective is to tackle the difficulties related to the fluctuation and uncertainty of renewable energy production. An examination of the collected data over vario...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | MATEC Web of Conferences |
| Subjects: | |
| Online Access: | https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01172.pdf |
| _version_ | 1827311547570978816 |
|---|---|
| author | Vladimirovich Kotov Evgeny Ramesh Banoth |
| author_facet | Vladimirovich Kotov Evgeny Ramesh Banoth |
| author_sort | Vladimirovich Kotov Evgeny |
| collection | DOAJ |
| description | This study examines the incorporation of renewable energy sources into microgrids using neural network-assisted optimization methods. The objective is to tackle the difficulties related to the fluctuation and uncertainty of renewable energy production. An examination of the collected data over various time periods indicates encouraging patterns in the production of renewable energy. The solar energy use shows a steady rise from 120 kWh to 140 kWh, representing a 16.67% increase. Similarly, wind energy usage also demonstrates an upward trend, increasing from 80 kWh to 95 kWh, marking an 18.75% expansion. The biomass energy production has seen a substantial increase from 50 kWh to 65 kWh, representing a significant 30% rise. The examination of microgrid load consumption demonstrates the increasing energy needs in residential, commercial, and industrial sectors. The household load consumption has increased from 150 kWh to 165 kWh, representing a 10% spike. Additionally, the commercial load and industrial load have also seen a surge of 15%. The predictions made by the neural network demonstrate a high level of accuracy, closely matching the actual output of renewable energy. The accuracy rates for solar, wind, and biomass projections are 98.4%, 95.5%, and 97.3% correspondingly. The assessment of improved energy distribution emphasizes the effective usage of renewable sources, guaranteeing grid stability and optimal resource utilization. The results highlight the capacity of neural network-assisted methods to precisely predict renewable energy outputs and efficiently incorporate them into microgrids, hence promoting sustainable and resilient energy solutions. This report provides valuable insights on improving microgrid operations, decreasing reliance on traditional energy sources, and accelerating the shift towards sustainable energy systems. |
| first_indexed | 2024-04-24T20:21:47Z |
| format | Article |
| id | doaj.art-7b2a85c21e1e4d52a9516fa37befd42d |
| institution | Directory Open Access Journal |
| issn | 2261-236X |
| language | English |
| last_indexed | 2024-04-24T20:21:47Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | MATEC Web of Conferences |
| spelling | doaj.art-7b2a85c21e1e4d52a9516fa37befd42d2024-03-22T08:05:26ZengEDP SciencesMATEC Web of Conferences2261-236X2024-01-013920117210.1051/matecconf/202439201172matecconf_icmed2024_01172Neural network-assisted integration of renewable sources in microgrids: A case studyVladimirovich Kotov Evgeny0Ramesh Banoth1Lovely Professional UniversityDepartment of AIMLE, GRIETThis study examines the incorporation of renewable energy sources into microgrids using neural network-assisted optimization methods. The objective is to tackle the difficulties related to the fluctuation and uncertainty of renewable energy production. An examination of the collected data over various time periods indicates encouraging patterns in the production of renewable energy. The solar energy use shows a steady rise from 120 kWh to 140 kWh, representing a 16.67% increase. Similarly, wind energy usage also demonstrates an upward trend, increasing from 80 kWh to 95 kWh, marking an 18.75% expansion. The biomass energy production has seen a substantial increase from 50 kWh to 65 kWh, representing a significant 30% rise. The examination of microgrid load consumption demonstrates the increasing energy needs in residential, commercial, and industrial sectors. The household load consumption has increased from 150 kWh to 165 kWh, representing a 10% spike. Additionally, the commercial load and industrial load have also seen a surge of 15%. The predictions made by the neural network demonstrate a high level of accuracy, closely matching the actual output of renewable energy. The accuracy rates for solar, wind, and biomass projections are 98.4%, 95.5%, and 97.3% correspondingly. The assessment of improved energy distribution emphasizes the effective usage of renewable sources, guaranteeing grid stability and optimal resource utilization. The results highlight the capacity of neural network-assisted methods to precisely predict renewable energy outputs and efficiently incorporate them into microgrids, hence promoting sustainable and resilient energy solutions. This report provides valuable insights on improving microgrid operations, decreasing reliance on traditional energy sources, and accelerating the shift towards sustainable energy systems.https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01172.pdfrenewable energymicrogridsneural networkenergy integrationsustainability |
| spellingShingle | Vladimirovich Kotov Evgeny Ramesh Banoth Neural network-assisted integration of renewable sources in microgrids: A case study MATEC Web of Conferences renewable energy microgrids neural network energy integration sustainability |
| title | Neural network-assisted integration of renewable sources in microgrids: A case study |
| title_full | Neural network-assisted integration of renewable sources in microgrids: A case study |
| title_fullStr | Neural network-assisted integration of renewable sources in microgrids: A case study |
| title_full_unstemmed | Neural network-assisted integration of renewable sources in microgrids: A case study |
| title_short | Neural network-assisted integration of renewable sources in microgrids: A case study |
| title_sort | neural network assisted integration of renewable sources in microgrids a case study |
| topic | renewable energy microgrids neural network energy integration sustainability |
| url | https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01172.pdf |
| work_keys_str_mv | AT vladimirovichkotovevgeny neuralnetworkassistedintegrationofrenewablesourcesinmicrogridsacasestudy AT rameshbanoth neuralnetworkassistedintegrationofrenewablesourcesinmicrogridsacasestudy |