A smart grid is the future vision of power systems that will be enabled by artificial intelligence (AI), big data, and the Internet of things (IoT), where digitalization is at the core of the energy sector transformation. However, smart grids require that energy managers become more concerned about the reliability and security of power systems. Therefore, energy planners use various methods and technologies to support the sustainable expansion of power systems, such as electricity demand forecasting models, stochastic optimization, robust optimization, and simulation. Electricity forecasting plays a vital role in supporting the reliable transitioning of power systems. This paper deals with short-term load forecasting (STLF), which has become an active area of research over the last few years, with a handful of studies. STLF deals with predicting demand one hour to 24 h in advance. We extensively experimented with several methodologies from machine learning and a complex case study in Panama. Deep learning is a more advanced learning paradigm in the machine learning field that continues to have significant breakthroughs in domain areas such as electricity forecasting, object detection, speech recognition, etc. We identified that the main predictors of electricity demand in the short term: the previous week’s load, the previous day’s load, and temperature. We found that the deep learning regression model achieved the best performance, which yielded an R squared (R²) of 0.93 and a mean absolute percentage error (MAPE) of 2.9%, while the AdaBoost model obtained the worst performance with an R² of 0.75 and MAPE of 5.70%.

Last-mile operations in forward and reverse logistics are responsible for a large part of the costs, emissions, and times in supply chains. These operations have increased due to the growth of electronic commerce and direct-to-consumer strategies. We propose a novel data- and model-driven framework to support decision making for urban distribution. The methodology is composed of diverse, hybrid, and complementary techniques integrated by a decision support system. This approach focuses on key elements of megacities such as socio-demographic diversity, portfolio mix, logistics fragmentation, high congestion factors, and dense commercial areas. The methodological framework will allow decision makers to create early warning systems and, with the implementation of optimization, machine learning, and simulation models together, make the best utilization of resources. The advantages of the system include flexibility in decision making, social welfare, increased productivity, and reductions in cost and environmental impacts. A real-world illustrative example is presented under conditions in one of the most congested cities: the megacity of Bogota, Colombia. Data come from a retail organization operating in the city. A network of stakeholders is analyzed to understand the complex urban distribution. The execution of the methodology was capable of solving a complex problem reducing the number of vehicles utilized, increasing the resource capacity utilization, and reducing the cost of operations of the fleet, meeting all constraints. These constraints included the window of operations and accomplishing the total number of deliveries. Furthermore, the methodology could accomplish the learning function using deep reinforcement learning in reasonable computational times. This preliminary analysis shows the potential benefits, especially in understudied metropolitan areas from emerging markets, supporting a more effective delivery process, and encouraging proactive, dynamic decision making during the execution stage.

Manufacturing enterprise decisions can be classified into four groups: business decisions, design decisions, engineering decisions, and production decisions. Numerous physical and software simulation techniques have been used to evaluate specific decisions by predicting their impact on either system performance or product performance. In this paper, we focus on the impact of production decisions, evaluated using discrete-event-simulation models, on enterprise-level performance measures. We argue that these discrete-event models alone are not enough to capture this impact. To address this problem, we propose integrating discrete-event simulation models with system dynamics models in a hybrid approach to the simulation of the entire enterprise system. This hybrid approach is conceptually consistent with current business trend toward integrated systems. We show the potentials for using this approach through an example of a semiconductor enterprise.

Predicting the future peak demand growth becomes increasingly important as more consumer loads and electric vehicles (EVs) start connecting to the grid. Accurate forecasts will enable energy suppliers to meet demand more reliably. However, this is a challenging problem since the peak demand is very nonlinear. This study addresses the research question of how deep learning methods, such as convolutional neural networks (CNNs) and long-short term memory (LSTM) can provide better support to these areas. The goal is to build a suitable forecasting model that can accurately predict the peak demand. Several data from 2004 to 2019 was collected from Panama’s power system to validate this study. Input features such as residential consumption and monthly economic index were considered for predicting peak demand. First, we introduced three different CNN architectures which were multivariate CNN, multivariate CNN-LSTM and multihead CNN. These were then benchmarked against LSTM. We found that the CNNs outperformed LSTM, with the multivariate CNN being the best performing model. To validate our initial findings, we then evaluated the robustness of the models against Gaussian noise. We demonstrated that CNNs were far more superior than LSTM and can support spatial-temporal time series data.

The production and supply chain management of biofuels from organic waste as raw material has been identified as a promising strategy in the field of renewable energies and circular economy initiatives. This industry involves complex tasks such as strategic land use, feedstock purchasing, production plant location, production capacity strategy, and material flows, which can be solved by mathematical modeling. The study proposed a multi-objective mixed-integer linear programming model to design a sustainable supply chain of biofuels with forest residues from its triple function: economic, environmental, and social. The trade-offs between the proposed objectives were determined with computational results. The proposed objectives were profit maximization, CO₂ minimization, and employment generation maximization. Thus, the proposed model serves as a tool for decision-making, allowing the projection of a long-term structure of the biofuel supply chains and contribute to the United Nations Sustainable Development Goals.

Virtual training platform allows interactive and engaging learning through practice without exposing trainees to hazards. In the recent pandemic (COVID-19) situation, online training is gaining importance as it allows learning with social distancing. This research study develops two online training modes—slide-based and virtual world—and assesses them on factors such as knowledge retention, engagement, and attention. Fire safety and emergency evacuation procedures were selected for online training development, focusing on a university community. A Lean Startup methodology was employed to develop training content for virtual and slide-based safety training (SBST). A virtual university building was developed with 15 learning objectives on fire safety. An empirical evaluation of the training modes was conducted with 143 participants. The results validated that a Virtual Safety World (VSW) can provide the same knowledge as SBST but can do so in a more engaging manner. Retention of concepts after a month was higher in VSW participants. The participants’ attention levels, measured by employing qEEG, showed that participants exhibited better-sustained attention while in VSW than in SBST mode. In addition, initial studies of the virtual training platform, designed to be adaptive to the user, are performed using deep learning and qEEG.