智能电网中无线传感器网络通信链路可靠性置信区间预测

Reliability Confidence Interval Prediction for Communication Link of Wireless Sensor Network in Smart Grid

实时准确的无线链路质量预测是保证智能电网厂、站区域通信链路可靠性的必要信息。无线链路质量信噪比时间序列所表现出的非线性和非平稳随机性的叠加是影响预测准确性的主要因素。为此,提出一种通信链路可靠性置信区间预测方法,通过对无线链路质量的信噪比序列近似解耦处理,将其分解为非线性序列和非平稳随机序列,采用小波神经网络建立信噪比非线性序列和非平稳随机方差序列的预测模型,并用预测结果计算通信链路可靠性置信区间上、下界。最后,在实际的智能电网环境中验证了所提出的算法和结果。

Real-time prediction of wireless link quality is a main problem which needs to be solved in the smart grid station area to guarantee the transmission reliability of wireless communication applications. The superposition of nonlinear and non- stationary sequences expressed by signal to noise ratio （SNR） time series of wireless link quality is the main factor that affects the prediction accuracy. For this reason, reliability confidence interval prediction is proposed by approximately decoupling the wireless link SNR sequence into nonlinear and non-stationary random sequences. And the wavelet neural network is used to develop the wireless link SNR sequence prediction model and the variance of non-stationary random sequence prediction model. Based on the model prediction results, this paper calculates the upper bound and lower bound of the wireless link reliability confidence interval. In the actual smart grid environment, the correctness and effectiveness of the proposed algorithm are verified, and the practicality of the proposed algorithm is illustrated through an application example.