Recurrent dendritic neuron model artificial neural network for time series forecasting

Observer-based differential evolution constrained control for safe reference tracking in robots

Big torque inputs in controls could increase energy consumption, and big estimated perturbations in observers could produce device damages. Therefore, it would be interesting to propose a constrained control for safe reference tracking and a constrained observer for safe perturbation estimation in robots. Furthermore, the best gains in controls produce a balance between safe reference tracking and save energy consumption. Therefore, it would be interesting to propose a method to find the best gains. In this paper, an observer-based differential evolution constrained control is proposed for safe reference tracking in robots. The contributions are described as follows: (1) a constrained observer is proposed for safe perturbation estimation in robots, (2) a constrained control is proposed for safe reference tracking in robots, (3) a differential evolution optimizer is used to find the best gains in an observer-based constrained control, (4) the robust stability in an observer-based constrained control is assured, (5) the pseudo-code of an observer-based differential evolution constrained control is detailed. The proposed observer-based differential evolution constrained control is applied for safe reference tracking in two robots.

Wind Power Forecasting Using Optimized Dendritic Neural Model Based on Seagull Optimization Algorithm and Aquila Optimizer

It is necessary to study different aspects of renewable energy generation, including wind energy. Wind power is one of the most important green and renewable energy resources. The estimation of wind energy generation is a critical task that has received wide attention in recent years. Different machine learning models have been developed for this task. In this paper, we present an efficient forecasting model using naturally inspired optimization algorithms. We present an optimized dendritic neural regression (DNR) model for wind energy prediction. A new variant of the seagull optimization algorithm (SOA) is developed using the search operators of the Aquila optimizer (AO). The main idea is to apply the operators of the AO as a local search in the traditional SOA, which boosts the SOA’s search capability. The new method, called SOAAO, is employed to train and optimize the DNR parameters. We used four wind speed datasets to assess the performance of the presented time-series prediction model, called DNR-SOAAO, using different performance indicators. We also assessed the quality of the SOAAO with extensive comparisons to the original versions of the SOA and AO, as well as several other optimization methods. The developed model achieved excellent results in the evaluation. For example, the SOAAO achieved high R2 results of 0.95, 0.96, 0.95, and 0.91 on the four datasets.

Globalized simulation-driven miniaturization of microwave circuits by means of dimensionality-reduced constrained surrogates

Small size has become a crucial prerequisite in the design of modern microwave components. Miniaturized devices are essential for a number of application areas, including wireless communications, 5G/6G technology, wearable devices, or the internet of things. Notwithstanding, size reduction generally degrades the electrical performance of microwave systems. Therefore, trade-off solutions have to be sought that represent acceptable compromises between the ability to meet the design targets and physical compactness. From an optimization perspective, this poses a constrained task, which is computationally expensive because a reliable evaluation of microwave components has to rely on full-wave electromagnetic analysis. Furthermore, due to its constrained nature, size reduction is a multimodal problem, i.e., the results are highly dependent on the initial design. Thus, utilization of global search algorithms is advisable in principle, yet, often undoable in practice because of the associated computational expenses, especially when using nature-inspired procedures. This paper introduces a novel technique for globalized miniaturization of microwave components. Our technique starts by identifying the feasible region boundary, and by constructing a dimensionality-reduced surrogate model therein. Global optimization of the metamodel is followed by EM-driven local tuning. Application of the domain-confined surrogate ensures low cost of the entire procedure, further reduced by the incorporation of variable-fidelity EM simulations. Our framework is validated using two microstrip couplers, and compared to nature-inspired optimization, as well as gradient-based size reduction. The results indicate superior miniaturization rates and low running cost, which make the presented algorithm a potential candidate for efficient simulation-based design of compact structures.