EPFSTO-ARIMA: Electric Power Forced Stochastic Optimization Predicting Based on ARIMA

With the advance of new technology and management reforms, data sharing has unleashed the full potential for social production during the past decade, especially for enterprise survival. Data poisoning attack is a typical attack faced by data sharing, EPSTO-ARIMA (Electric Power Stochastic Optimization Predicting Based on Autoregressive Integrated Moving Average model) would increase prediction error by generating adversarial shared data, which leads to the failure of the prediction. In response to the EPSTO-ARIMA attack, this paper proposes EPFSTO-ARIMA (Electric Power Forced Stochastic Optimization Predicting Based on Autoregressive Integrated Moving Average model) combined with data sanitization and data grouping. The model was validated by seven sets of data from three datasets. Experimental results indicate that EPFSTO-ARIMA can remedy the flaws of excessive accuracy error caused by the EPSTO-ARIMA. For publicly dataset “Column2”, the proposed EPFSTO-ARIMA achieves 30.44% lower prediction error than EPSTO-ARIMA, respectively. Simultaneously, the terrific results in other datasets have also been ascertained the viability and generalization ability of our proposed EPFSTO-ARIMA.