Uncertainty Analysis for Data-Driven Chance-Constrained Optimization

Hybrid Chaotic Maps-Based Artificial Bee Colony for Solving Wind Energy-Integrated Power Dispatch Problem

A chance-constrained programming-based optimization model for the dynamic economic emission dispatch problem (DEED), consisting of both thermal units and wind turbines, is developed. In the proposed model, the probability of scheduled wind power (WP) is included in the set of problem-decision variables and it is determined based on the system spinning reserve and the system load at each hour of the horizon time. This new strategy avoids, on the one hand, the risk of insufficient WP at high system load demand and low spinning reserve and, on the other hand, the failure of the opportunity to properly exploit the WP at low power demand and high spinning reserve. The objective functions of the problem, which are the total production cost and emissions, are minimized using a new hybrid chaotic maps-based artificial bee colony (HCABC) under several operational constraints, such as generation capacity, system loss, ramp rate limits, and spinning reserve constraints. The effectiveness and feasibility of the suggested framework are validated on the 10-unit and 40-unit systems. Moreover, to test the robustness of the suggested HCABC algorithm, a comparative study is performed with various existing techniques.

Dynamics Modeling of Industrial Robotic Manipulators: A Machine Learning Approach Based on Synthetic Data

Obtaining a dynamic model of the robotic manipulator is a complex task. With the growing application of machine learning (ML) approaches in modern robotics, a question arises of using ML for dynamic modeling. Still, due to the large amounts of data necessary for this approach, data collection may be time and resource-intensive. For this reason, this paper aims to research the possibility of synthetic dataset creation by using pre-existing dynamic models to test the possibilities of both applications of such synthetic datasets, as well as modeling the dynamics of an industrial manipulator using ML. Authors generate the dataset consisting of 20,000 data points and train seven separate multilayer perceptron (MLP) artificial neural networks (ANN)—one for each joint of the manipulator and one for the total torque—using randomized search (RS) for hyperparameter tuning. Additional MLP is trained for the total torsion of the entire manipulator using the same approach. Each model is evaluated using the coefficient of determination (R2) and mean absolute percentage error (MAPE), with 10-fold cross-validation applied. With these settings, all individual joint torque models achieved R2 scores higher than 0.9, with the models for first four joints achieving scores above 0.95. Furthermore, all models for all individual joints achieve MAPE lower than 2%. The model for the total torque of all joints of the robotic manipulator achieves weaker regression scores, with the R2 score of 0.89 and MAPE slightly higher than 2%. The results show that the torsion models of each individual joint, and of the entire manipulator, can be regressed using the described method, with satisfactory accuracy.

Environmental and Economic Assessments and Uncertainties of Multiple Lignocellulosic Biomass Utilization for Bioenergy Products: Case Studies

Life-cycle assessment (LCA) and techno-economic analysis (TEA) were applied to assess the economic feasibility and environmental benefits of utilizing multiple biomass feedstocks for bioenergy products under three different technological pathways with consideration of uncertainties. Three cases were studied for the production of pellets, biomass-based electricity, and pyrolysis bio-oil. A Monte Carlo simulation was used to examine the uncertainties of fossil energy consumption, bioenergy conversion efficiency, stochastic production rate, etc. The cradle-to-gate LCA results showed that pellet production had the lowest greenhouse gas (GHG) emissions, water and fossil fuels consumption (8.29 kg CO2 eq (equivalent), 0.46 kg, and 105.42 MJ, respectively). The conversion process presented a greater environmental impact for all three bioenergy products. When producing 46,929 Mg of pellets, 223,380 MWh of electricity, and 78,000 barrels of pyrolysis oil, the net present values (NPV) indicated that only pellet and electricity production were profitable with NPVs of $1.20 million for pellets, and $5.59 million for biopower. Uncertainty analysis indicated that pellet production showed the highest uncertainty in GHG emission, and bio-oil production had the least uncertainty in GHG emission but had risks producing greater-than-normal amounts of GHG. Biopower production had the highest probability to be a profitable investment with 85.23%.