The Electrical Power System (EPS) is a vital subsystem in CubeSats, responsible for powering all onboard components. Due to the standardized size and weight constraints, the limited surface area of solar panels restricts power generation. To address this, Maximum Power Point Tracking (MPPT) is crucial. However, traditional MPPT techniques struggle in CubeSats’ dynamic orbital environments, where solar irradiance varies across different facets. This paper presents a novel MPPT method combining a Deep Feed Forward Neural Network DFFNN with a Proportional-Integral (PI) controller to adapt to these rapidly changing conditions. A year-long simulation of a 3U CubeSat in Systems Tool Kit (STK) generated real-time orbital temperature and irradiance data to train the DFFNN using 70,000 data points. The trained DFFNN was integrated into a Simulink model for testing under variable illumination. Results showed the DFFNN-based MPPT achieved 97.4% efficiency, outperforming Perturb and Observe (P&O) (88.9%), Incremental conductance (InC) (89.7%), and Particle Swarm Optimization (PSO) (94.08%). It also achieved 88.3% overall system efficiency, reduced power ripple to under 2.5%, and improved transient performance. These findings confirm the DFFNN-PI approach’s effectiveness in optimizing power extraction for CubeSat missions under dynamic conditions.

This work investigates the implementation of the Deep Deterministic Policy Gradient (DDPG) algorithm to enhance the target-reaching capability of the seven degree-of-freedom (7-DoF) Franka Pandarobotic arm. A simulated environment is established by employing OpenAI Gym, PyBullet, and Panda Gym. After 100,000 training time steps, the DDPG algorithm attains a success rate of 100% and an average reward of −1.8. The actor loss and critic loss values are 0.0846 and 0.00486, respectively, indicating improved decision-making and accurate value function estimations. The simulation results demonstrate the efficiency of DDPG in improving robotic arm performance, highlighting its potential for application to improve robotic arm manipulation.

The depletion of fossil fuel is driving the world towards the application of renewable energy sources. However, their intermittent nature, in addition to load variation and transmission line sag-tension change due to temperature, is a great deal of problems for reliable power delivery. Without a reliable power delivery, power generation is just a waste of resources. A reliable power delivery can be achieved when the best and the worst case steady state information of a power system network is known to plan and control accordingly. If a system is affected by the presence of uncertainty, a deterministic load flow analysis fails to provide the worst-case load flow result in a single analysis. As a result, a load flow analysis considering the presence of uncertainty is mandatory. On this paper, a novel complex affine arithmetic (AA) based load flow analysis in the presence of generation and load uncertainties is proposed. The proposed approach is tested on an IEEE bus systems and compared with Monte Carlo approach. The proposed approach convergence faster than the Monte Carlo based method and it is slightly conservative.

This work presents the implementation of Deep Deterministic Policy Gradient (DDPG) algorithm to enhance target reaching capability of the seven Degree-of-Freedom (7-DoF) Franka Panda robot arm. A simulated environment is established by employing OpenAI Gym, PyBullet, and Panda Gym. Upon completion of 100,000 training time steps, the DDPG algorithm attains a success rate of 100% and an average reward of -1.8. The actor loss and critic loss values are 0.0846 and 0.00486, respectively, indicating improved decision-making and accurate value function estimations. The simulation results demonstrate the efficiency of DDPG in improving robotic arm performance, highlighting its potential for application to improve robot arm manipulation.

This paper presents a hybrid forecasting model for a wind power named Secondary Hybrid Decomposition (SHD)-Long Short-Term Memory (LSTM) with Crisscross Optimization (CSO).The model integrates three key techniques to improve prediction accuracy. Firstly, the SHD mitigates the limitations of single-stage decomposition by employing a two-step Empirical Mode Decomposition (EMD) process. This improves the predictability of wind power series by decomposing it into its Intrinsic Mode Functions (IMFs) and residual components. Secondly, LSTM networks are utilized to forecast each subseries and residue generated by SHD, capturing temporal dependencies within wind power data effectively. Finally, the CSO is used to optimize the hyperparameter of individual LSTM networks, enhancing global search performance. Two sets of wind farm data are used to validate the accuracy of the model. A comparative study shows that the proposed SHD-LSTM-CSO model performs better than other hybrid models such as SHD-LSTM, EMD-LSTM, LSTM based on variable mode decomposition (VMD) (VMD-LSTM), Gray Worm Optimization-based backpropagation neural network (GWO-BPANN) and EMD-based Artificial Neural Network (EMD-ANN) methods.