Abstract:
Data prediction in wireless sensor networks (WSN) reduces redundant data transfers and extends network lifetime. Two data prediction algorithms are used today. The first reassembled historical data and provided backward models, causing unmanageable delays.
The second model predicts future data and increases data transmissions. Method: Our Combinational Data Prediction Model (CDPM) builds prior data to control delays and predicts future data to reduce data transmission. Two WSN algorithms implement this paradigm.
The first algorithm builds optimal sensor node (SN) models step-by-step. The other predicts and regenerates base station data. Comparison: A WSN-based real application is simulated using real data to test our CDPM data-prediction method.
CDPM performance is compared to HLMS, ELR, and P-PDA algorithms. Results: The CDPM model outperformed HLMS, ELR, and P-PDA algorithms in transmission suppression (16.49%, 19.51%, 20.57%), energy consumption (29.56%, 50.14%, 61.12%), and accuracy (15.38%, 21.42%, 31.25%).
Data collection can control CDPM training delays. Conclusion: The proposed CDPM reduced data transmission, improved energy efficiency, and regulated latency compared to a single forward or backward model.
Keywords : Data Models, Wireless Sensor Networks, Predictive Models, Data Communication, Delays, Computational Modeling, Energy Consumption, Energy Consumption, Telecommunication Power Management, Wireless Sensor Networks
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
