Geospatial navigation in GPS-denied environments presents significant challenges, particularly for autonomous vehicles operating in complex, unmapped regions. We explore the Earth’s geomagnetic field, a globally distributed and naturally occurring resource, as a reliable alternative for navigation. Since vehicles can only observe the geomagnetic field along their traversed paths, they must rely on incomplete information to infer the navigation strategy; therefore, we formulate the navigation problem as a partially observed Markov decision process (POMDP). To address this POMDP, we employ proximal policy optimization with long short-term memory (PPO-LSTM), a deep reinforcement learning framework that captures temporal dependencies and mitigates the effects of noise. Using real-world geomagnetic data from the international geomagnetic reference field (IGRF) model, we validate our approach through experiments under noisy conditions. The results demonstrate that PPO-LSTM outperforms baseline algorithms, achieving smoother trajectories and higher heading accuracy. This framework effectively handles the uncertainty and partial observability inherent in geomagnetic navigation, enabling robust policies that adapt to complex gradients and offering a robust solution for geospatial navigation.

When the wind turbine operates under frequently fluctuating mission profiles, the power semiconductors of its converter will generate low-frequency junction temperature fluctuations, resulting in accumulation of damage to the devices and affecting the converter’s lifetime. To address the above issues, an active thermal control (ATC) strategy based on reactive circulating current for the parallel converter of permanent magnet synchronous generator wind power system was proposed in this paper, by introducing reactive circulating current during sudden wind speed drops, the thermal cycle of the power semiconductor can be effectively smoothed. On the other hand, considering the impact of the proposed strategy on the voltage vector and modulation index of the converter, both the machine-side converter (MSC) and the grid-side converter (GSC) during the control process will be analyzed in detail, then the reactive current of GSC will be limited to prevent excessive modulation index and maintain system stability without reducing the filter size. Finally, a 2 MW wind power system is utilized as a benchmark, and both short-term simulation analysis and long-term numerical results reveal the effectiveness of the control strategy proposed in this paper.

Wind turbine blades bear the maximum cyclic load and varying self-weights in turbulent wind environments, which accelerate the propagation of cracks that ultimately progress from minor faults, resulting in blade failure and significant maintenance and shutdown costs. To address this issue, this paper proposes an adaptive control strategy for the blade’s useful life. The control system is divided into the inner control loop and the outer control loop. The outer loop is based on the Paris crack propagation model combined with a particle filtering algorithm and calculates the degradation of the blade life under the crack threshold conditions provided by the operation and maintenance strategy to determine the parameter settings of the inner-loop load-shedding controller. The control strategy we propose can balance the load-shedding capability of the controller with the fatigue load of the pitch actuator while considering the predefined remaining useful blade life in the operation and maintenance strategy, avoiding unplanned downtime and reducing maintenance costs.

The integration of solar power has been increasing as the green energy transition rolls out. The penetration of solar power challenges the grid stability and energy scheduling, due to its intermittent energy generation. Accurate and near real-time solar power prediction is of critical importance to tolerant and support the permeation of distributed and volatile solar power production in the energy system. In this paper, we propose a deep-learning based ultra-short-term solar power prediction with data reconstruction. We decompose the data for the prediction to facilitate extensive exploration of the spatial and temporal dependencies within the data. Particularly, we reconstruct the data into low- and high-frequency components, using ensemble empirical model decomposition with adaptive noise (CEEMDAN). We integrate meteorological data with those two components, and employ deep-learning models to capture long- and short-term dependencies towards the target prediction period. In this way, we excessively exploit the features in historical data in predicting a ultra-short-term solar power production. Furthermore, as ultra-short-term prediction is vulnerable to local optima, we modify the optimization in our deep-learning training by penalizing long prediction intervals. Numerical experiments with diverse settings demonstrate that, compared to baseline models, the proposed method achieves improved generalization in data reconstruction and higher prediction accuracy for ultra-short-term solar power production.