TITomoya Inagata

Tomoya Inagata

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tomoya Inagata has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Multi-Vehicle Optimization for Coordinating Electric Vehicle Power Supply and Charging

    by Yuji Mizuno, Tomoya Inagata, Koki Kawaoka, Jiyoung Choi, Fujio Kurokawa, Nobumasa Matsui

    Medical facilities providing dialysis treatment need to strengthen their power grid resilience against blackouts to ensure continued medical services. In Japan, the number of artificial dialysis patients is increasing, and natural disasters cause blackouts annually. Then, reinforcing power grid resilience has become a critical issue for medical facilities. Typically, most of these facilities install emergency generators that are designed to only supply power to essential equipment. As a result, load suppression must be implemented, limiting their ability to provide medical services during blackouts. To address this issue, a power supply system combining a diesel generator (DG) and electric vehicles (EVs) is being considered. By optimizing the power supply from the DG and EVs, as well as coordinating EV charging, this system is anticipated to supply power to a medical facility for a longer duration without load suppression. Therefore, this paper proposes an optimization method for multiple vehicles, coordinating EV power supply and charging. The results indicate that the proposed optimization method can supply stable power to the medical facility, even under natural disasters where additional fuel cannot be supplied to the DG fuel tank, providing power for over 72 h in summer and 48 h in winter without load suppression. In Japan, there are more than 4,500 dialysis facilities, and their aggregated power demand is comparable to that of a large-scale power plant. Accordingly, the proposed operation method has substantial significance in terms of both practical feasibility and societal impact. In addition, business buildings are legally required to install emergency power generation systems. The proposed approach can contribute not only to medical facilities but also to enhancing power resilience in business buildings that utilize EVs for commercial operations or goods transportation


  • Parameter Evaluation Method for Power Demand Forecasting Methodology of a Clinic

    by Tomoya Inagata, Yuji Mizuno, Keita Matsunaga, Fujio Kurokawa, Masaharu Tanaka, Nobumasa Matsui

    In Japan, efforts to achieve a carbon-neutral society by 2050 are underway. As part of these efforts, hospitals and clinics are particularly focusing on energy management to reduce carbon dioxide emissions with peak-cut operations. Especially, peak-cut operations necessitate accurate power demand forecasting, often facilitated by neural networks (NNs). The multilayer perceptron (MLP) and the long short-term memory (LSTM) networks represent two prominent NNs employed for this purpose. Moreover, the mean absolute error (MAE), root mean square error (RMSE), and the ratio of RMSE to MAE are used as evaluation indicators. This study employs the MLP and LSTM for the power demand forecasting of a clinic considering factors such as data partitioning, structure of the NN (the number of layers and nodes), and data period. For MLP-based forecasting models, random partitioning is preferred to improve forecasting accuracy. Additionally, for four year or longer data periods, the learning outcomes are unaffected by the structure of the NN (the number of nodes and layers). Conversely, in LSTM-based forecasting models, the choice between random and block partitioning depends on the data period. Single- or double-layer configurations show better MAE and RMSE values than three- or six-layer configurations. Employing the ratio of RMSE to MAE as an evaluation indicator, the error distribution of the NN can be estimated. The characteristics of the forecasting model can be described from the error distribution. A value of 1.414 for the ratio of RMSE to MAE indicates a Laplace distribution, a value of 1.253 indicates a normal distribution. Therefore, a good forecasting model is characterized by low RMSE to MAE values and RMSE to MAE ratios between 1.253 and 1.414.