International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1710715

1710715PublishedVol 9 · Issue 3

AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities

Terry Eda Okwari Matthew Ehikhamenle

Subject area: Science,Engineering and Technology  ·  Area of research: Internet of Things

Abstract

Rural agriculture, vital to global food security and livelihoods, continues to face persistent challenges of weak connectivity, unreliable energy access, and inefficient data management, all of which constrain productivity and economic growth in underserved regions. This study introduces an AI-driven smart connectivity and sustainable energy model that integrates solar-based energy management, AI-optimized signal amplification, and IoT-enabled precision farming into a unified off-grid framework. Field deployment in Agbanganam village, Nigeria, demonstrated that intelligent solar management sustained IoT and communication services for up to four days under limited sunlight, while adaptive amplification improved average reference signal received power by ?10 dB, raising levels from below ?110 dBm to above ?85 dBm, extending coverage from 0.3 km? to over 5 km?, and boosting throughput by 28%. On the agricultural front, smart farming validation using an LSTM model achieved an F1-score of 0.87 in predicting irrigation events, enabling more efficient water use and reducing irrigation by 15%. Statistical analysis further confirmed that AI-assisted plots yielded significantly higher cassava output than control plots (ANOVA, p < 0.01), with yield improvements of up to 22%. These outcomes demonstrate that the proposed AHOM framework not only enhances network accessibility and energy reliability but also delivers measurable gains in agricultural efficiency and productivity. Overall, the findings affirm that strategically combining AI, IoT, and renewable energy within a community-centered platform can sustainably bridge the digital divide, improve food security, and empower rural economies.

Keywords

Smart Agriculture, Sustainable Energy, Signal Boosting, Internet of Things (IoT) Artificial Intelligence (AI)

How to cite this paper

Terry Eda Okwari, Matthew Ehikhamenle "AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities" Iconic Research And Engineering Journals Volume 9 Issue 3 2025 Page 898-911
Terry Eda Okwari, Matthew Ehikhamenle "AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities" Iconic Research And Engineering Journals, vol. 9, no. 3, Sep. 2025
Terry Eda Okwari, Matthew Ehikhamenle (2025). AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities. Iconic Research And Engineering Journals, 9(3).
Terry Eda Okwari, Matthew Ehikhamenle "AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities" Iconic Research And Engineering Journals, vol. 9, no. 3, Sep. 2025.
@article{1710715,
      author = {Terry Eda Okwari, Matthew Ehikhamenle},
      title = {AI-Driven Smart Connectivity and Sustainable Energy Model for Rural Agricultural Communities},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {3},
      pages = {898-911},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710715.pdf},
      abstract = {Rural agriculture, vital to global food security and livelihoods, continues to face persistent challenges of weak connectivity, unreliable energy access, and inefficient data management, all of which constrain productivity and economic growth in underserved regions. This study introduces an AI-driven smart connectivity and sustainable energy model that integrates solar-based energy management, AI-optimized signal amplification, and IoT-enabled precision farming into a unified off-grid framework. Field deployment in Agbanganam village, Nigeria, demonstrated that intelligent solar management sustained IoT and communication services for up to four days under limited sunlight, while adaptive amplification improved average reference signal received power by ?10 dB, raising levels from below ?110 dBm to above ?85 dBm, extending coverage from 0.3 km? to over 5 km?, and boosting throughput by 28%. On the agricultural front, smart farming validation using an LSTM model achieved an F1-score of 0.87 in predicting irrigation events, enabling more efficient water use and reducing irrigation by 15%. Statistical analysis further confirmed that AI-assisted plots yielded significantly higher cassava output than control plots (ANOVA, p < 0.01), with yield improvements of up to 22%. These outcomes demonstrate that the proposed AHOM framework not only enhances network accessibility and energy reliability but also delivers measurable gains in agricultural efficiency and productivity. Overall, the findings affirm that strategically combining AI, IoT, and renewable energy within a community-centered platform can sustainably bridge the digital divide, improve food security, and empower rural economies.},
      keywords = {Smart Agriculture, Sustainable Energy, Signal Boosting, Internet of Things (IoT) Artificial Intelligence (AI)},
      month = {September},
  }