Automatic Hierarchical Time-Series Forecasting Using Gaussian Processes

Forecasting often involves multiple time-series that are hierarchically organized (e.g., sales by geography). In that case, there is a constraint that the bottom level forecasts add-up to the aggregated ones. Common approaches use traditional forecasting methods to predict all levels in the hierarchy and then reconcile the forecasts to satisfy that constraint. We propose a new algorithm that automatically forecasts multiple hierarchically organized time-series. We introduce a combination of additive Gaussian processes (GPs) with a hierarchical piece-wise linear function to estimate, respectively, the stationary and non-stationary components of the time-series. We define a flexible structure of additive GPs generated by each aggregated group in the hierarchy of the data. This formulation aims to capture the nested information in the hierarchy while avoiding overfitting. We extended the piece-wise linear function to be hierarchical by defining hyperparameters shared across related time-series. From our experiments, our algorithm can estimate hundreds of time-series at once. To work at this scale, the estimation of the posterior distributions of the parameters is performed using mean-field approximation. We validate the proposed method in two different real-world datasets showing its competitiveness when compared to the state-of-the-art approaches. In summary, our method simplifies the process of hierarchical forecasting as no reconciliation is required. It is easily adapted to non-Gaussian likelihoods and multiple or non-integer seasonalities. The fact that it is a Bayesian approach makes modeling uncertainty of the forecasts trivial.

A Finite Mixture GARCH Approach with EM Algorithm for Energy Forecasting Applications

Enhancing forecasting performance in terms of both the expected mean value and variance has been a critical challenging issue for energy industry. In this paper, the novel methodology of finite mixture Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) approach with Expectation–Maximization (EM) algorithm is introduced. The applicability of this methodology is comprehensively evaluated for the forecasting of energy related time series including wind speed, wind power generation, and electricity price. Its forecasting performances are evaluated by various criteria, and also compared with those of the conventional AutoRegressive Moving-Average (ARMA) model and the less conventional ARMA-GARCH model. It is found that the proposed mixture GARCH model outperforms the other two models in terms of volatility modeling for all the energy related time series considered. This is proven to be statistically significant because the p-values of likelihood ratio test are less than 0.0001. On the other hand, in terms of estimations of mean wind speed, mean wind power output, and mean electricity price, no significant improvement from the proposed model is obtained. The results indicate that the proposed finite mixture GARCH model is a viable approach for mitigating the associated risk in energy related predictions thanks to the reduced errors on volatility modeling.

Prediction Method of Multiple Related Time Series Based on Generative Adversarial Networks

In multiple related time series prediction problems, the key is capturing the comprehensive influence of the temporal dependencies within each time series and the interactional dependencies between time series. At present, most time series prediction methods are difficult to capture the complex interaction between time series, which seriously affects the prediction results. In this paper, we propose a novel deep learning model Multiple Time Series Generative Adversarial Networks (MTSGAN) based on generative adversarial networks to solve this problem. MTSGAN is mainly composed of three components: interaction matrix generator, prediction generator, and time series discriminator. In our model, graph convolutional networks are used to extract interactional dependencies, and long short-term memory networks are used to extract temporal dependencies. Through the adversarial training between the generator and the discriminator, we enable the final prediction generator to generate prediction values that are very close to the true values. At last, we compare the prediction performance of the MTSGAN with other benchmarks on different datasets to prove the effectiveness of our proposed model, and we find that MTSGAN model consistently outperforms other state-of-the-art methods in the multiple related time series prediction problems.

Forecasting Irregular Seasonal Power Consumption. An Application to a Hot-Dip Galvanizing Process

Distribution companies use time series to predict electricity consumption. Forecasting techniques based on statistical models or artificial intelligence are used. Reliable forecasts are required for efficient grid management in terms of both supply and capacity. One common underlying feature of most demand–related time series is a strong seasonality component. However, in some cases, the electricity demanded by a process presents an irregular seasonal component, which prevents any type of forecast. In this article, we evaluated forecasting methods based on the use of multiple seasonal models: ARIMA, Holt-Winters models with discrete interval moving seasonality, and neural networks. The models are explained and applied to a real situation, for a node that feeds a galvanizing factory. The zinc hot-dip galvanizing process is widely used in the automotive sector for the protection of steel against corrosion. It requires enormous energy consumption, and this has a direct impact on companies’ income statements. In addition, it significantly affects energy distribution companies, as these companies must provide for instant consumption in their supply lines to ensure sufficient energy is distributed both for the process and for all the other consumers. The results show a substantial increase in the accuracy of predictions, which contributes to a better management of the electrical distribution.

PERAMALAN JUMLAH KUNJUNGAN WISATAWAN MANCANEGARA DI KEPULAUAN RIAU DENGAN MENGGUNAKAN MODEL FUNGSI TRANSFER

Transfer function models is a data analysis model that combines time series and causal approach, in another words, transfer function models is a method that ilustrates that the predicted value in teh future is affected by the past value time series and based on one or more related time series. In this research, an analysis of the number of tourist arrival and rainfall in several regions in Kepulauan Riau from January 2013 until December 2017 was aimed at obtaining a transfer function model and forecasting the number of tourist arrival in several regions of the Kepulauan Riau for next periods. Based on the result of the analysis, rainfall in Tanjung Pinang does not affect the visit of tourist with the values of MAPE is 13,63494%. Rainfall in Batam also does not affect the visit of tourist with the values of MAPE is 7,977151%. While in Tanjung Balai Karimun, tourist arrivals was affected by rainfall with the values of MAPE is 10,32777%.