In recent years, the use of AI has been promoted in the construction industry to solve labour shortages. This study focuses on determining the reinforcement degree when constructing a kind of infrastructure, which has required the empirical knowledge of experts, and proposes a machine learning method to automate the process. The target structure is divided into many sections, and the reinforcement degree for each section needs to be determined based on observation data.

In this paper, we formulate the problem as a time series recognition one in which the degree is determined using observation data from the current construction section and previous sections already constructed. Then, we apply a recurrent neural network (RNN) to the problem, which has a feedback mechanism suitable for time series processing. In addition, we propose RNNs which use different weights corresponding to observation data at different construction site. Through verification experiments using datasets observed at real construction sites, we show the advantages of the proposed RNNs by comparing the existing methods.

This paper considers a hierarchical decentralized control for virtual power plants. Virtual power plants act as aggregator of electric energy resources, including distributed generator, battery storage/electric vehicle and controllable loads. A virtual power plant becomes a large-scale system containing a large number of electric power equipment. A centralized management method may not be suitable for operation of virtual power plants. We propose the individual optimization by each equipment and real-time pricing strategy. The proposed management methodology allows plug-and-play type operation and can mitigate the effects of uncertainties due to weather condition, load profiles, machine failure or installation of additional equipment. The effectiveness of the proposed hierarchical decentralized management method is evaluated through real physical experiments including real-scale electric power equipment and actual load changes.