The objective of this research is to improve the short-term load forecasting accuracy using deep learning models such as long short-term memory (LSTM) and deep belief network (DBN). The required historical data is provided by Electricity Generating Authority of Thailand (EGAT). Long short-term memory model which can learn to store time series data in memory and solve long dependencies problems and deep belief network model are investigated to overcome back propagation problems in the network. The proposed models are trained and tested using the cleaned data during the period of January 2016 to January 2017 by smoothing the raw data. Mean absolute percentage error (MAPE) and root mean square error (RMSE) are used to measure the forecasting accuracy. In this research, the results generated by the LSTM model are compared with those of the DBN model. The results show that the LSTM model execute higher accuracy performance than the DBN model.

The next-day load forecasting is complex due to the load pattern variations driven by external factors, such as weather and time. This study proposes a hybrid model that incorporates the Classification and Regression Tree (CART) with pruning conditions and a Deep Belief Network (DBN) to improve forecasting accuracy. The CART can recognize the load patterns by classifying similar groups with low variance, thus reducing the complexity of the forecasting model. The actual 48-period load data from the Electricity Generating Authority of Thailand (EGAT) is used. The proposed model is compared with six widely used standalone forecasting benchmark models and provides better at the minimum 0.46% mean absolute percentage error. Moreover, the forecasting performance of DBN and the other four benchmark models are improved by using our hybrid approach.

Short-term load forecasting (STLF) plays a pivotal role in the electricity industry because it helps reduce, generate, and operate costs by balancing supply and demand. Recently, the challenge in STLF has been the load variation that occurs in each period, day, and seasonality. This work proposes the bagging ensemble combining two machine learning (ML) models—linear regression (LR) and support vector regression (SVR). For comparative analysis, the performance of the proposed model is evaluated and compared with three advanced deep learning (DL) models, namely, the deep neural network (DNN), long short-term memory (LSTM), and hybrid convolutional neural network (CNN)+LSTM models. These models are trained and tested on the data collected from the Electricity Generating Authority of Thailand (EGAT) with four different input features. The forecasting performance is measured considering mean absolute percentage error (MAPE), mean absolute error (MAE), and mean squared error (MSE) parameters. Using several input features, experimental results show that the integrated model provides better accuracy than others. Therefore, it can be revealed that our approach could improve accuracy using different data in different forecasting fields.

Industry 4.0 represents a significant transformation in industrial systems through digital integration, presenting both opportunities and challenges for aligning the workforce, especially in emerging economies like Thailand. This study adopts a sequential exploratory mixed-method approach to investigate how strategic human resource development (HRD) contributes to sustainable transformation, defined as the enduring alignment between workforce capabilities and technological advancement. The qualitative phase involved case studies of five Thai manufacturing firms at varying levels of Industry 4.0 adoption, utilizing semi-structured interviews with executives and HR leaders. Thematic findings informed the development of a structured survey, distributed to 144 firms. Partial Least Squares Structural Equation Modeling (PLS SEM) was used to test the hypothesized relationships among business pressures, leadership support, HRD preparedness, and technological readiness. The analysis reveals that business pressures significantly influence leadership and HRD, which in turn facilitate technological readiness. However, business pressures alone do not directly enhance readiness without the support of intermediaries. These results underscore the critical role of integrated HRD and leadership frameworks in enabling sustainable digital transformation. This study contributes to theoretical perspectives by integrating HRD, leadership, and technological readiness, offering practical guidance for firms aiming to navigate the complexities of Industry 4.0.

The increasing use of Renewable Energy (RE), the influence of forecasted load error, and Electric Vehicles (EVs) add significant uncertainty and variables to power system Unit Commitment (UC) planning. For addressing this challenge, this paper proposes a Fuzzy Mathematical Mixed-Integer Linear Programming (FMMILP) approach for daily UC that incorporates the scheduling of Pumped Storage Hydropower (PSH) and Battery Energy Storage (BES) to manage supply and demand fluctuations. The FMMILP model explicitly considers these uncertainties and aims to minimize total production cost and carbon emissions while ensuring reliable and sustainable power system operation. The effective solution method for solving FMMILP is explained. The FMMILP model is applied to Thailand’s national power system, characterized by its diverse generation mix, substantial RES penetration, and growing EV adoption. A comprehensive stochastic reliability analysis using Monte Carlo Simulation is performed, incorporating a wide range of supply and demand scenarios, including extreme worst-case scenarios, to evaluate the effectiveness of the proposed models. These scenarios incorporate optimal solutions from UC and RES dispatch patterns. Three distinct FMMILP models are compared against a deterministic UC benchmark in the rainy, summer, and winter seasons. Numerical simulations demonstrate that the FMMILP model achieves optimal solutions within acceptable computational time and significantly enhances system reliability compared to the deterministic model, with reliability improvements of 15.99%, 26.14%, and 51.44% in the rainy season, summer season, and winter season, respectively. This is evidenced by the reduction in the Loss of Load Probability (LOLP) and Expected Energy Not Supplied (EENS) in power system operation.