Yoon-Sik Yoo

As the adoption of lithium-ion batteries increases, concerns over safety incidents and replacement costs have become increasingly pressing. Accurate battery state prediction is thereby vital for reducing costs and ensuring safety. This paper introduces a novel system based on a transformer encoder architecture, leveraging Multi-Head Self-Attention (MHSA) layers to enhance battery capacity prediction. To address variability in battery data collection, we implement robust preprocessing techniques and a sliding window method to standardize data input. Positional encoding is applied to embed sequence order information at the input stage, while residual connections and layer normalization between MHSA layers optimize the learning process. Final predictions are generated through a fully connected neural network (FNN). Experimental results on the NASA dataset, obtained from repeated charge-discharge cycles, demonstrate that the proposed model mostly achieves superior predictive accuracy across multiple cell datasets, as measured by MAPE and RMSE. The proposed model showed enhanced performance, achieving a MAPE of 0.9918% and an RMSE of 0.02542 in experiments on specific cells. Furthermore, compared to other models in most experiments, it showed a performance improvement of at least 41% in MAPE and 29% in RMSE. Notably, the model maintains excellent performance while reducing complexity. Additionally, to prevent overestimation of overall performance due to high accuracy in only the early stages, we conducted interval-based performance evaluations, confirming that the proposed model consistently provides accurate predictions with minimal variance across different stages compared to other models.

Air compressors are widely used in industrial fields. Compressed air systems aggregate air flows and then supply them to places of demand. These huge systems consume a significant amount of energy and generate heat internally. Machine components in compressed air systems are vulnerable to heat, and, in particular, a radiator to cool the heat of the overall air compressor is the core component. Dirty radiators increase energy consumption due to anomalous cooling. To reduce the energy consumption of air compressors, this mechanism emphasizes a machine learning-based radiator fault detection, using features such as RPM, motor power, outlet pressure, air flow, water pump power, and outlet temperature with slight true fault labels. Moreover, the proposed system adds an LSTM-based motor power prediction model to point out the initial judgment of radiator fault possibility. Via the rigorous analysis and the comparison among machine learning models, this meticulous approach improves the performance of radiator fault prediction up to 93.0%, and decreases the mean power consumption of the air compressor around 2.24%.

With the technical growth and the reduction of deployment cost for distributed energy resources (DERs), such as solar photovoltaic (PV), energy trading has been recently encouraged to energy consumers, which can sell energy from their own energy storage system (ESS). Meanwhile, due to the unprecedented rise of greenhouse gas (GHG) emissions, some countries (e.g., Republic of Korea and India) have mandated using a renewable energy certificate (REC) in energy trading markets. In this paper, we propose an energy broker model to boost energy trading between the existing power grid and energy consumers. In particular, to maximize the profits of energy consumers and the energy provider, the proposed energy broker is in charge of deciding the optimal demand and dynamic price of energy in an REC-based energy trading market. In this solution, the smart agents (e.g., IoT intelligent devices) of consumers exchange energy trading associated information, including the amount of energy generation, price and REC. For deciding the optimal demand and dynamic pricing, we formulate convex optimization problems using dual decomposition. Through a numerical simulation analysis, we compare the performance of the proposed dynamic pricing strategy with the conventional pricing strategies. Results show that the proposed dynamic pricing and demand control strategies can encourage energy trading by allowing RECs trading of the conventional power grid.

On a future tactical-battle field network, combat radio nodes will be deployed for various operations, forming a mobile ad-hoc network (MANET). However, because of the nodes’ mobility, a single group might be divided into several small groups with fewer nodes. Conversely, several small groups might be merged into one group. In such an environment, an unmanned aerial vehicle (UAV) will provide an effective way to improve network coverage and connectivity among the small groups. However, some issues should be considered for the optimal deployment of the UAV. One issue is to find the proper position of the UAV, which enhances the connectivity among the groups, because a tactical network places a high priority on network survivability rather than throughput maximization. We also need to exploit real topographic information to obtain more accurate connectivity information among nodes. Second, an efficient resource allocation scheme for reliable communications through the UAV should be taken into account. Since most of the links between the UAV and the ground nodes are line-of-sight (LoS), due to the good quality of these links, the traffic via the UAV will be heavy in spite of the limited data slot resources. Moreover, the traffic flows of the network require diverse quality-of-service (QoS), and different priorities should be imposed upon the nodes depending on the involved tactical operations. In this paper, we formulate a UAV positioning problem maximizing group connectivity (GC) and a data slot-allocation problem maximizing GC utility. Subsequently, we propose an optimal positioning and slot allocation algorithm, which satisfies QoS requirement and supports the predetermined priorities of the nodes and the groups. Numerical analysis verifies that the proposed scheme is effective in UAV positioning and slot allocation, outperforming conventional methods.

In a tactical mobile ad-hoc network (MANET), unmanned vehicles are deployed for surveillance and reconnaissance. They send multimedia data to a center node in real time. In this letter, we propose a centralized TDMA slot and power scheduling schemes which maximize energy efficiency (EE) considering Quality-of-Service (QoS) for the tactical MANET. We formulate this problem as a non-concave ratio optimization, and propose the optimal slot allocation and power control algorithms based on the Dinkelbach method and the concave-convex procedure. The performance of the proposed algorithm is verified by numerical results, which show a fairly good energy efficiency.

This paper proposes a prioritized energy optimal management for home-to-home in smart grid. As this proposed mechanism configures the prioritized optimal energy, if there is a surplus of energy from the energy provider of home, the energy broker in smart grid distributes the optimal energy to the requesting user for the purpose of maximizing the user's payoff.

This paper designs an energy optimal management in smart grid infrastructure. As a way of assigning the prioritized optimal energy of the adjacent energy provider from the energy-requesting user, if there is a surplus of energy from the energy provider, the smart grid as being the closest to the user preferentially allocates the optimal energy to the requesting user in order to maximize the user satisfaction.

This paper proposes a weighted priority-based optimal energy distribution scheme among microgrids. Since this scheme intend to allocate the weighted priority to the neighboring energy provider in microgrid, the energy requesting-consumer can be receive the optimal energy. Using the optimal energy distribution modeling, this scheme provides the optimal energy solution to the energy needed-consumer. As a result, solving the weighted priority-based optimization problem maximizes the user satisfaction.