Compensation Method for Missing and Misidentified Skeletons in Nursing Care Action Assessment by Improving Spatial Temporal Graph Convolutional Networks

With the urgency of mitigating global warming, the low-carbon transformation of power grid systems has emerged as a pivotal industry upgrade for sustainable development. We proposed a novel deep neural network-based approach for investment decision planning in the low-carbon transformation of power grids, which aimed to address multidimensional key indicators related to power grid transformation and provided reliable electricity industry layouts and investment plans for power system investment decisions. To achieve this, three targeted investment branch models were established, encompassing investment behavior, electricity production and consumption, and predictions of new capacity investment. These models effectively tackled challenges associated with power distribution, electricity price scheduling, power carbon quotas, and the feasibility of low-carbon power generation technologies. Subsequently, a global investment decision planning model was constructed, employing spatiotemporal neural networks and recurrent neural networks, which integrated the aforementioned branch models and incorporated existing low-carbon transformation data. A comparative analysis was conducted, examining the predicted results against actual values from three perspectives: power generation portfolio, grid economy, and overall investment decision plans. The results demonstrated the effectiveness of our method in accurately predicting future installed capacity of diverse low-carbon power generation technologies, sustainability indices, and investment returns. Notably, our method achieves an impressive forecasting accuracy of over 90% compared to actual values of investment decision planning over the past 4 years.

Deep neural network for investment decision planning on low-carbon transition in power grid

Wang,

Chen

et al. 2024

A Novel Reinforcement Learning Balance Control Strategy for Electric Vehicle Energy Storage Battery Pack

Tang,

Yang,

Feng

2024

Energy imbalance in electric vehicle energy storage battery packs poses a challenge due to design and usage variations. Traditional balancing control algorithms struggle to cope with large-scale battery data and complex nonlinear relationship modeling, which jeopardizes the stability of energy storage systems. To overcome this issue, we propose a reinforcement learning (RL)-based strategy for battery pack balancing control. Our approach begins with adaptive battery pack modeling followed by the employment of an active balancing control strategy to determine the duration of the balancing charge state and rank the balancing strength of individual battery pack cells. Subsequently, a RL network is employed to learn dynamic parameters that capture battery pack variations, enabling subsequent automatic learning and prediction of effective balancing strategies while simultaneously selecting the optimal control policy. Our simulation experiments demonstrate that our approach ensures an orderly charge and discharge process of battery pack cells, achieving an impressive balance efficiency of 91% when compared to other similar balancing control methods. Furthermore, the optimization of RL methods results in significant improvements in battery pack energy efficiency, stability, and operational costs. Notably, our method also outperforms other similar control methods in terms of energy utilization rates, establishing its superiority in this category.

Capacity Allocation in Distributed Wind Power Generation Hybrid Energy Storage Systems

Wang,

Fan

2024

The inherent variability and uncertainty of distributed wind power generation exert profound impact on the stability and equilibrium of power storage systems. In response to this challenge, we present a pioneering methodology for the allocation of capacities in the integration of wind power storage. Firstly, we introduce a meticulously designed uncertainty modeling technique aimed at optimizing wind power forecasting deviations, thus augmenting the controllability of distributed wind power variations. Subsequently, we establish a cutting-edge real-time dynamic optimization model for state of charge, which effectively mitigates the fluctuations associated with grid-connected wind power. Moreover, we employ a state-of-the-art distributed robust optimization algorithm to enhance the stability of the distributed wind power storage system. Through comprehensive simulation testing, our findings unequivocally demonstrate the efficacy of our approach in preserving a harmonious balance between wind power load and output demand, thereby assuring the unwavering operation of the entire system. Notably, our approach attains an exceptional capacity allocation efficiency of 91% in the rigorous wind power grid-smoothing test, outperforming comparable methodologies. Lastly, we proffer essential recommendations pertaining to attenuation optimization at the effective capacity level of the batteries, effectively safeguarding the long-term stability of the energy storage system.