As renewable energy generation prediction system has been introduced into the energy trading market, making a model to accurately predict the quantity of solar photovoltaic (PV) energy generation has become a significant problem. Moreover, to encourage an accurate prediction of the quantity of energy generation, an incentive system has been implemented for those who predict the quantity of solar PV energy under the error rate of 8%. Therefore, it has become more important to investigate and analyze current prediction technology numerically and develop more advanced prediction system. In this study, we tried to develop a better model to improve the accuracy of solar PV energy generation quantity by comparing three models made with gradient boosting machine (GBM), Model 1, Model 2, Model 3 respectively. Model 1 was built with the whole training data set without any additional preprocessing. After conducting some additional preprocessing procedure to predict solar energy generation more accurately, we made Model 2 with the whole training data set and Model 3 with only upper 10% of energy generation capacity. To compare the accuracy of three models, normalized mean absolute error (nMAE) was used as an evaluation index. The nMAE of Model 1 was 9.64% while the Model 2 showed 8.41%. Also, Model 3, which was constructed with the training set of upper 10% energy generation capacity, outperformed with the nMAE of 8.08%. For further study, to check the effectiveness of models constructed with GBM, a time series model, autoregressive integrated moving average (ARIMA), was also built and the nMAE was compared.

(1) Background: P-cadherin (CDH3) is a transmembrane protein that plays a crucial role in maintaining the structural integrity of epithelial tissue and homeostasis. Its role in carcinogenesis remains a subject of debate, as its behavior can vary depending on the molecular context and the specific tumor cell model under study. In this study, we explored the role of P-cadherin in head and neck squamous cell carcinoma (HNSCC) and the mechanism underlying its function. (2) Methods: We analyzed P-cadherin expression in HNSCC patients using The Cancer Genome Atlas (TCGA) database. For in vitro functional analysis, we conducted proliferation, migration, invasion, and western blot assays after either suppressing or overexpressing P-cadherin. For in vivo functional analysis, we utilized mouse xenograft models. (3) Results: P-cadherin was significantly overex-pressed in tumor samples compared to normal samples in the TCGA-HNSCC cohort. P-cadherin knockdown resulted in decreased proliferation, migration, and invasion compared to control cells, while P-cadherin overexpression increased cell proliferation and migration in HNSCC cells. We discovered that c-Met functioned as an upstream regulator of P-cadherin. Surprisingly, we found that P-cadherin knockdown increased the phosphorylation of c-Met and STAT3. Combining P-cadherin siRNA with the c-Met inhibitor SU11274 resulted in a more effective reduction in HNSCC cell growth, both in vitro and in vivo, compared to either treatment alone. (4) Conclusions: Our study uncovered a previously unknown aspect of P-cadherin-mediated c-Met regulation. The enhanced activation of c-Met/STAT3 following P-cadherin inhibition could be responsible for the survival of resistant tumor cells. Therefore, dual inhibition of P-cadherin and c-Met may be a potentially effective approach for treating HNSCC.