Cluster systems are getting widely used because of good performance / cost ratio. However, their reliability has not been well discussed in practical environment so far. As the number of commodity components in a cluster system gets increased, it is indispensable to support reliability by system software. SCore cluster system software is a parallel programming environment for High Performance Computing (HPC). SCore provides checkpointing and rollback-recovery mechanism for high availability. In this paper, we analyze and evaluate the checkpointing and rollback-recovery mechanisms of SCore quantitively. The experimental results reveal that the required time for checkpointing scales very well in respect to the number of computing nodes. However, the required time is quite long due to the low effective network bandwidth. Based on the results, we modify SCore and successfully make checkpointing and recovery 1.8 2.8 times and 3.7 5.0 times faster respectively. This is very helpful for cluster systems to achieve high performance and high availability.

A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.

An important issue in accelerating the introduction of ATM networks is to offer more convenient access to the customer and a more efficient ATM system architecture. Regarding the first point, ATM network customers are currently inconvenienced by the need to declare traffic parameters, such as peak and average cell rates to the network provider before using the network. However, it is difficult for a customer to predict traffic parameters. This paper proposes a new ATM system with a dynamic bandwidth estimation and allocation scheme. This eliminates the need for traffic parameter declaration, and realizes more convenient ATM service. The proposed ATM system is a ring network. Bandwidth estimation is carried out by the "Network Server" located on the ring network. The estimation is achieved by observing the parameters closely related to media access control (MAC) protocols of LAN/MAN systems. Based on an estimation of customer traffic, the "Network Server" effectively allocates the bandwidth to each customer. This realizes a more efficient ATM network.