Predição de dados de sensoriamento visando eficiência energética de redes de sensores sem fio

• Charles M. P. Almeida UFAL
• Geymerson S. Ramos UFAL
• Andre L. L. Aquino UFAL

DOI: https://doi.org/10.5753/sbcup.2018.3282

Resumo

Este artigo tem como objetivo comparar modelos de predição de dados de sensoriamento em redes de sensores sem fio com a finalidade de economizar energia na coleta de dados. Modelos ARIMA, SVM e ANN foram utilizados em uma aplicação de coleta de dados de temperatura e avaliados quanto à economia de energia proporcionada. As medições foram realizados por dispositivos reais e foi possível observar o desempenho dos modelos para um conjunto de dados de sensoriamento em um ambiente de escritório. Para este estudo de caso, o modelo ARIMA apresentou melhor desempenho em relação ao SVM e ANN em termos de eficiência energética.

Referências

Akyildiz, I., Su, W., Sankarasubramaniam, Y., and Cayirci, E. (2002). Wireless sensor networks: a survey. Computer Networks, 38(4):393 – 422.

Cortes, C. and Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20(3):273–297.

Liu, C., Wu, K., and Tsao, M. (2005). Energy Efficient Information Collection with the ARIMA model in Wireless Sensor Networks. IEEE Communications.

Moghadam, R. A. and Keshmirpour, M. (2011). Hybrid ARIMA and Neural Network Model for Measurement stimation in Energy-Efficient Wireless Sensor Networks. In Informatics Engineering and Information Science, PT III, volume 253 of Communications in Computer and Information Science, pages 35–48.

Pai, P. and Hong, W. (2005). Support vector machines with simulated annealing algorithms in electricity load forecasting. Energy Conversion and Management, 46(17):2669–2688.

Pai, P. and Lin, C. (2005). A hybrid ARIMA and support vector machines model in stock price forecasting. Omega-International Journal of Management Science, 33(6):497–505.

Ruela, A. S., Cabral, R. S., and Aquino, Andre L. L. Guimaraes, F. G. (2009). Evolutionary design of wireless sensor networks based on complex networks. In Proceedings of the 2009 Fifth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, pages 237–242.

Thamizhselvi, S. and Mary, P. S. (2016). A Survey about Data Prediction in Wireless Sensor Networks with Improved Energy Efficiency. Research Journal of OF Pharmaceutical Biological and Chemical Sciences, 7(2):2118–2120.

Wang, X., Wang, S., Ma, J., and Bi, D. (2008). Energy efficient organization of wireless sensor networks with adaptive forecasting. SENSORS, 8(4):2604–2616.

Xiao-Ying, D., Ding-Hui, Y., Tao, L., and Jing, X. (2009). Study on Mercer condition extension of support vector regression based on Ricker wavelet kernel. Chinese Journal of Geophysics-Chinese Edition, 52(9):2335–2344.

Yuan, C., Liu, S., and Fang, Z. (2016). Comparison of china’s primary energy consumption forecasting by using arima (the autoregressive integrated moving average) model and gm(1,1) model. Energy, 100:384 – 390.

Zhang, G. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50(Supplement C):159 – 175.

Zhang, G., Patuwo, E., and Hu, M. Y. (1998). Forecasting with artificial neural networks: the state of the art. International Journal of Forecasting, 14(14):35–62.