Recently, there has been a growing interest in studying both long-term and short-term forecasts of electricity demand using dynamic regression models with seasonal ARIMA (SARIMA) errors and neural network autoregression (NNAR) models. Most of the electricity demand forecasting models investigated in the literature involved two features: temperature and day type, and only the point forecasts of temperature are used to obtain forecasts of electricity demand. However, it is crucial to acknowledge that temperature fluctuates throughout the day, and it is more appropriate to incorporate the forecast error variability and use the fuzzy forecasts of the temperature as an input to forecast electricity demand. This paper uses a novel fuzzy two-step approach to generate fuzzy forecasts of electricity demand. In step 1, fuzzy forecasts of temperature are obtained by incorporating additional features such as precipitation, irradiance, snowfall, snow mass, cloud cover, and air density. Thirteen distinct models, including neural network regression models and Facebook industrial Prophet models, are fitted to temperature data, and the best forecasting model for temperature is selected based on forecast accuracy measures. In step 2, the fuzzy forecasts of the temperature are used as a feature with day type (weekday/weekend/holiday) to obtain fuzzy forecasts of electricity demand. The superior performance of neural network fuzzy forecasts of electricity demand in terms of forecast accuracy is demonstrated for Ontario electricity demand data.

Electricity price forecasting plays an important role in decision making on bidding strategies of selling and buying electricity. This paper computes one day-ahead (DA) quantile forecasts of electricity prices in a highly volatile market by applying regression models to a pool of point forecasts. Three data-driven forecasting methods are implemented to generate DA point forecasts of the Ontario market’s electricity prices. In order to generate the three sets of point forecasts, we use: i) the triple exponential smoothing (TES) method, ii) a neural network (NN) that combines layers of Convolutional neurons and gradient recurrent units (GRU), iii) an extreme gradient boosted (XGB) non-linear regression approach. Performance of the three models compared against a benchmark which considers the forecast of electricity prices as the average price of the same hour and day during the last four weeks. The TES method decreases the mean absolute error (MAE) of the benchmark model from 10.29 to 9.42. The Convolutional GRU (ConvGRU) model and XGB regression also reduce the MAE to 8.20 and 7.06, respectively. Finally, quantile regression averaging (QRA) is applied to the pool of point forecasts obtained by TES, ConvGRU, and XGB methods to compute DA quantile forecasts of electricity prices. Moreover, the QRA method is further developed in this work by employing gradient boosting non-linear regression (GBR). Our analysis using real data reveals that the GBR method provides more reliable quantiles as well as tighter prediction intervals with smaller forecasting errors than QRA.

Supply chain literature reveals that study of resilient supply chains and bullwhip effect (BE) have been receiving special attention during pandemic for supply chains with seasonal as well as nonseasonal demand components. The BE phenomenon has been detected in various industries and sectors, and causes multiple inefficiencies such as higher costs of producing more than needed, wastage and transportation costs. As a result, BE forecast is of great importance for academics and supply chain managers. Despite the multitude of studies that have emerged addressing this issue, the impact of the quality of dynamic forecasts on the BE has received limited coverage in the literature. Optimal dynamic forecasts of the demand could allow managers to mitigate the upstream amplification of orders (and thus the BE), as well as reduce unnecessary inventory costs. Order quantity and BE in a supply chain depend on the forecast of the future demand. Usually minimum mean square error (MMSE) forecasts of the future demand are obtained by fitting an appropriate seasonal auto-regressive moving average (ARMA) time series model. However, a major drawback of the MMSE forecasting method is that it does not provide the associated risk forecasts. In this paper, a simple yet effective machine learning demand forecasting approach without fitting any time series model is presented.Specifically, a novel data driven machine learning algorithm that bypasses traditional forecasting steps and allows forecast weights to be optimized by minimizing the one-step ahead forecast error sum of squares (FESS) is proposed. A novel stability metric of a supply chain is proposed as the risk adjusted forecast of the future demand. It is shown that the risk adjusted forecasts can be used to check whether a given supply chain is resilient. In order to be more resilient and competitive in the current market, business leaders around the world agree that it is necessary to modernize and make major changes to their supply chain strategies. Demand risk forecasts obtained by the proposed machine learning approach allow supply chain managers to enhance the forecasting power of the order quantity and construct more resilient supply chains. The performance of proposed approach is evaluated through numerical experiments using simulated data and weekly demand data of two products. The results show that the performance of the proposed forecasts and risk adjusted forecasts of the future demand are better than the commonly used MMSE forecasts of the future demand.

Electricity is a special commodity that has to be kept available at all times. In fact, power plants need to have accurate forecast of electricity demand in order to provide enough electricity for customers. Final customers are able to establish their own power plants to decrease their dependency on the grid. For example rooftop photovoltaic panels are getting more popular among residential customers. It seems that meteorological variables such as solar irradiance play an important role in load forecasting. Moreover, temperature is also a main determinant of electricity demand. In this paper, we propose a model for short-term load forecasting which consists of hourly weather data (including seasonal variation as well) and historical load data. Machine learning algorithms such as support vector regression (SVR), least absolute shrinkage and selection operator (LASSO) regression and a multilayer neural network (NN) are used for short-term load forecasting. In order to improve the forecast accuracy (smaller mean absolute error) of NN, we propose a dual phase forecasting method. In the first phase, data driven double exponential smoothing (DDDES) is used to generate electricity load forecasts. In the second phase, the results of first phase forecasting are fed into a multilayer NN to have more accurate forecasts of electricity demand. It is shown that NN outperforms the other two methods. Our data analysis shows a significant improvement in terms of performance where maximum mean absolute error (MAE) decreases from 367.26 to 115.30.