Donghun Lee

As the scale of electricity consumption grows, the peak electricity consumption prediction of campus buildings is essential for effective building energy system management. The selection of an appropriate model is of paramount importance to accurately predict peak electricity consumption of campus buildings due to the substantial variations in electricity consumption trends and characteristics among campus buildings. In this paper, we proposed eight deep recurrent neural networks and compared their performance in predicting peak electricity consumption for each campus building to select the best model. Furthermore, we applied an attention approach capable of capturing long sequence patterns and controlling the importance level of input states. The test cases involve three campus buildings in Incheon City, South Korea: an office building, a nature science building, and a general education building, each with different scales and trends of electricity consumption. The experiment results demonstrate the importance of accurate model selection to enhance building energy efficiency, as no single model’s performance dominates across all buildings. Moreover, we observe that the attention approach effectively improves the prediction performance of peak electricity consumption.

Discovering sustainable business partnerships is crucial for small and medium-sized companies, where they can realize potential value through operational resources and abilities. Prior studies have mostly focused on predicting and developing new business partners using various machine learning techniques or social network analyses. However, effectively estimating potential benefits from business partnerships is much more valuable to companies. Therefore, this study proposes a method which combines deep learning and network analyses to estimate the potential value of business partnerships for companies. To demonstrate the effectiveness of the proposed method, we expand business partnerships between companies and assess potential value derived from the parenthesis using business transaction data collected from the Republic of Korea. The results suggest that companies can gain more potential value from extended networks when compared to previous ones. Furthermore, potential value results show clear distinctions between industries. Our findings provide evidence that small and medium-sized companies can experience significant benefits by establishing adequate business partnerships.

This study considers a parallel dedicated machine scheduling problem towards minimizing the total tardiness of allocated jobs on machines. In addition, this problem comes under the category of NP-hard. Unlike classical parallel machine scheduling, a job is processed by only one of the dedicated machines according to its job type defined in advance, and a machine is able to process at most one job at a time. To obtain a high-quality schedule in terms of total tardiness for the considered scheduling problem, we suggest a machine scheduler based on double deep Q-learning. In the training phase, the considered scheduling problem is redesigned to fit into the reinforcement learning framework and suggest the concepts of state, action, and reward to understand the occurrences of setup, tardiness, and the statuses of allocated job types. The proposed scheduler, repeatedly finds better Q-values towards minimizing tardiness of allocated jobs by updating the weights in a neural network. Then, the scheduling performances of the proposed scheduler are evaluated by comparing it with the conventional ones. The results show that the proposed scheduler outperforms the conventional ones. In particular, for two datasets presenting extra-large scheduling problems, our model performs better compared to existing genetic algorithm by 12.32% and 29.69%.

District heating system is designed to minimize energy consumption and environmental pollution by employing centralized production facilities connected to demand regions. Traditionally, optimization based algorithms were applied to the heat production planning problem in the district heating systems. Optimization-based models provide near optimal solutions, while it takes a while to generate solutions due to the characteristics of the underlying solution mechanism. When prompt re-planning due to any parameter changes is necessary, the traditional approaches might be inefficient to generate modified solutions quickly. In this study, we developed a two-phase solution mechanism, where deep learning algorithm is applied to learn optimal production patterns from optimization module. In the first training phase, the optimization module generates optimal production plans for the input scenarios derived from operations history, which are provided to the deep learning module for training. In the second planning phase, the deep learning module with trained parameters predicts production plan for the test scenarios. The computational experiments show that after the training process is completed, it has the characteristic of quickly deriving results appropriate to the situation. By combining optimization and deep learning modules in a solution framework, it is expected that the proposed algorithm could be applied to online optimization of district heating systems.

Recently, the prediction of photovoltaic (PV) power has become of paramount importance to improve the expected revenue of PV operators and the effective operations of PV facility systems. Additionally, the precise PV power output prediction in an hourly manner enables more sophisticated strategies for PV operators and markets as the electricity price in a renewable energy market is continuously changing. However, the hourly prediction of PV power outputs is considered as a challenging problem due to the dynamic natures of meteorological information not only in a day but also across days. Therefore, in this paper, we suggest three PV power output prediction methods such as artificial neural network (ANN)-, deep neural network (DNN)-, and long and short term memory (LSTM)-based models that are capable to understand the hidden relationships between meteorological information and actual PV power outputs. In particular, the proposed LSTM based model is designed to capture both hourly patterns in a day and seasonal patterns across days. We conducted the experiments by using a real-world dataset. The experimental results show that the proposed ANN based model fails to yield satisfactory results, and the proposed LSTM based model successfully better performs more than 50% compared to the conventional statistical models in terms of mean absolute error.