Enterprise AI Analysis
Jaya Hunger Game Search Enabled Energy Efficient Optimal Resource Allocation in Internet of Things and Energy Prediction Using Deep Long Short Term Memory
Authors: Yannam Bharath Bhushan · S. Aparna
Publication: International Journal of Computational Intelligence Systems (2026) 19:113
Published: March 10, 2026
This paper introduces a novel hybrid optimization and deep learning framework, Jaya-Hungry Game Search (Jaya-HGS) with Deep LSTM, for energy-efficient resource allocation in IoT networks. By combining the Hunger Game Search (HGS) and Jaya algorithms, and predicting energy using Deep LSTM, the framework optimizes critical functions like makespan, communication cost, and execution time. This innovative approach yields superior results in energy efficiency, execution time, and throughput compared to existing methodologies, paving the way for more sustainable and high-performing IoT deployments.
Executive Impact: Driving IoT Efficiency
The Jaya-HGS framework offers tangible improvements for enterprise IoT, directly impacting operational costs and network performance.
0
Energy Efficiency Boost
0
Min. Execution Time
0
Max. Network Throughput
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
IoT Resource Optimization
The paper introduces Jaya-Hunger Game Search (Jaya-HGS) with Deep LSTM for energy-efficient resource allocation in IoT networks. This hybrid optimization approach, combined with advanced deep learning for energy prediction, significantly improves how resources are managed, leading to enhanced network longevity and performance. It addresses the complexity and time-consuming nature of traditional resource allocation models by providing a more agile and effective solution.
AI/ML in IoT
Deep Long Short Term Memory (Deep LSTM) plays a crucial role in predicting energy consumption, forming a foundational component of the Jaya-HGS framework. This integration of deep learning with a novel hybrid optimization algorithm (Jaya-HGS, combining Jaya and HGS) exemplifies how AI and Machine Learning can drive intelligent decision-making in IoT. The framework leverages ML's predictive power for proactive resource management, outperforming prior DRL, GNN, and traditional routing protocols in terms of energy efficiency and execution speed.
Energy Efficiency
A primary objective and outcome of the Jaya-HGS framework is vastly improved energy efficiency. By optimizing resource allocation based on predicted energy, makespan, communication cost, and execution time, the model achieves a maximum residual energy of 0.121 J, demonstrating significant energy savings. This directly contributes to extending the operational lifespan of battery-powered IoT devices and reducing the overall energy footprint of large-scale IoT deployments, leading to substantial cost benefits for enterprises.
0.121 J
Max. Residual Energy Achieved
The proposed Jaya-HGS with Deep LSTM framework significantly enhances energy efficiency in IoT networks, achieving a maximum residual energy of 0.121 J, which is a key indicator of prolonged network lifetime and optimized power utilization. This performance metric demonstrates the framework's ability to conserve power effectively while maintaining operational effectiveness in complex IoT environments. Enterprises can leverage this for substantial operational cost reductions and extended device longevity.
Jaya-HGS Resource Allocation Process
IoT Simulation & Energy Model
→
Deep LSTM Energy Prediction
→
Jaya-HGS Hybrid Optimization
→
Multi-Objective Fitness Evaluation
→
Optimal Resource Allocation
The Jaya-Hunger Game Search (Jaya-HGS) process for optimal resource allocation in IoT begins with simulating the IoT network and modeling energy consumption. Deep Long Short Term Memory (Deep LSTM) is then employed for accurate energy prediction. The Jaya-HGS algorithm, combining the strengths of Jaya optimization and Hunter Game Search, utilizes this predicted energy along with other multi-objective fitness functions (makespan, communication cost, execution time) to perform optimal resource allocation. This structured approach ensures a highly efficient and adaptable system for dynamic IoT resource management.
| Method | Energy (J) |
|---|---|
| Jaya-HGS (Proposed) | 0.121 |
| Transformer-based DRL (TDRL) | 0.032 |
| OBLMFO | 0.037 |
| Deep Recurrent Q-learning Networks (DRQNs) | 0.045 |
| Graph Neural Network (GNN) | 0.053 |
| Energy-efficient, Congestion Resource allocation and Routing protocol (ECRR) | 0.063 |
| AI-driven Collaborative Dynamic Resource Allocation (ACDRA) | 0.069 |
| Deep Learning (DL) routing protocol | 0.069 |
Comparing the energy performance with 10 resources, the proposed Jaya-HGS framework demonstrates superior energy efficiency, achieving 0.121 J compared to 0.032 J for TDRL, 0.037 J for OBLMFO, 0.045 J for DRQNs, 0.053 J for GNN, 0.063 J for ECRR, 0.069 J for ACDRA, and 0.069 J for DL routing protocol. This highlights a significant improvement of up to 60.24% over existing methods, enabling longer operational lifespans for IoT devices and substantial reductions in energy consumption for enterprise deployments.
4.4032 s
Reduced Computational Time
The Jaya-HGS model achieves a remarkable computational time of just 4.4032 seconds, significantly outperforming existing methods like TDRL (9.9876 s) and OBLMFO (10.0598 s). This efficiency ensures faster decision-making for resource allocation in dynamic IoT environments, which is critical for real-time applications and maintaining optimal system performance without introducing undue latency. Enterprises benefit from quicker response times and more agile network management.
Enhanced Scalability and Robustness for Dynamic IoT
Challenge: Traditional IoT resource allocation struggles with scalability in large networks and maintaining performance under node failures or dynamic environmental changes.
Solution: The Jaya-HGS framework is designed to consistently sustain higher residual energy as the network grows and maintain robust performance across varying bandwidths, device types, and network topologies. Its hybrid optimization and deep learning approach allow it to adapt effectively to dynamic conditions, ensuring reliable resource management.
Impact: Enterprises deploying Jaya-HGS can expect significantly enhanced network longevity, reduced downtime, and stable performance even in ultra-dense or rapidly changing IoT scenarios. This translates to lower maintenance costs and higher operational reliability for critical infrastructure.
The proposed Jaya-HGS framework excels in both scalability and robustness, critical aspects for real-world IoT deployments. It demonstrates consistent high residual energy even with increasing node density and maintains stable performance across diverse network conditions, including varying bandwidths, device types, and topologies. This resilience ensures that enterprise IoT networks remain operational and efficient, even when facing significant growth or unexpected challenges, making it an ideal solution for dynamic and large-scale applications.
Calculate Your Potential ROI
Estimate the financial and operational benefits of implementing AI-driven IoT resource optimization in your enterprise.
Estimated Annual Savings
Calculating...
Reclaimed Employee Hours Annually
Calculating...
Your AI Implementation Roadmap
A typical journey to integrate advanced AI into your IoT resource management, tailored for enterprise success.
Phase 1: Discovery & Strategy (2-4 Weeks)
Comprehensive assessment of existing IoT infrastructure, resource allocation challenges, and business objectives. Define clear KPIs for energy efficiency, execution time, and throughput. Develop a tailored AI strategy and project scope.
Phase 2: Data Integration & Model Training (6-10 Weeks)
Integrate IoT data sources, clean and preprocess data for Deep LSTM. Initial training and validation of the Jaya-HGS and Deep LSTM models using historical and simulated data. Establish baseline performance metrics.
Phase 3: Pilot Deployment & Optimization (4-8 Weeks)
Deploy the Jaya-HGS framework in a controlled pilot environment. Monitor performance, fine-tune model parameters, and iteratively optimize resource allocation rules. Gather feedback and ensure seamless integration with existing systems.
Phase 4: Full-Scale Rollout & Continuous Improvement (Ongoing)
Expand deployment across the entire IoT network. Implement continuous learning mechanisms for Deep LSTM to adapt to evolving network conditions. Establish monitoring dashboards and ongoing support for maximum ROI.
Ready to Transform Your IoT?
Connect with our AI specialists to explore how Jaya-HGS can revolutionize your enterprise's IoT resource allocation and energy efficiency.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat