Forecasting method for weak trend quantities

Sometimes the output or input quantities of a system are subjected to random variations incurred from surrounding environments. In such a case, the available historical quantities can not be fitted to one of the known patterns. Therefore, the forecasting about future quantities becomes a stochastic problem. In other words, the methods of time series analysis, in any way, can't be conducted directly to the given data. This paper presents an approximation method for forecasting when the original historical quantities don't fit a trend. The method is mainly based on the assumption that the quantities constitute a frequency distribution with repetitive folds; each of them can be explained by a probability distribution at a specific significance level.