After the M9.0 earthquake in 2011, Japan has faced severe electric shortage. The tsunami caused by the earthquake destroyed many power plans along the coast lines, and still, sufficient power is not provided even in 2012. Electricity (i.e., power data) management using information and communication technology (ICT) is getting more and more popular these days. Many projects (not only by academia but also by vendors and service providers) have been established to control such electricity using the Internet technology. This paper reports the work of "66kV power data management on the Internet space", which we have built at five campuses of the University of Tokyo.
In recent years, privacy-sensitive data has become increasingly prevalent in autonomous vehicles, smart devices, and sensor nodes that can move around and make opportunistic contact with each other. The federation of these nodes has been discussed in the context of federated learning with a centralized mechanism. However, due to multi-vendor issues, relying on a specific server operated by a third party is not desirable in some cases. To address this challenge, wireless ad hoc federated learning (WAFL) has been proposed to realize a fully distributed collaborative machine learning with the nodes physically encountered. WAFL can develop generalized models from non-lID datasets stored in distributed nodes by exchanging and aggregating them with each other over opportunistic node-to-node contacts. Despite these advancements, WAFL's learning speed and accuracy remain relatively slow in sparsely and dynamically connected situations because the model update frequency has to be lower than that in static and frequently connected situations. In this study, we propose MemWAFL, which improves learning accuracy and speed in sparsely and dynamically connected situations. We incorporated a mechanism to store the models of the nodes contacted in the WAFL learning algorithm. As a result, we successfully improved the average learning speed by up to 1209 epochs and the learning accuracy by up to approximately 0.42% compared to the original WAFL in sparsely and dynamically connected situations.
In cooperative ITS, security and privacy protection are essential. Cooperative Awareness Message (CAM) is a basic V2V message standard, and misbehavior detection is critical for protection against attacking CAMs from the inside system, in addition to node authentication by Public Key Infrastructure (PKI). On the contrary, pseudonym IDs, which have been introduced to protect privacy from tracking, make it challenging to perform misbehavior detection. In this study, we improve the performance of misbehavior detection using observation data of other vehicles. This is referred to as collective perception message (CPM), which is becoming the new standard in European countries. We have experimented using realistic traffic scenarios and succeeded in reducing the rate of rejecting valid CAMs (false positive) by approximately 15 percentage points while maintaining the rate of correctly detecting attacks (true positive).
Many message routing schemes have been proposed in the context of delay tolerant networks (DTN) and intermittently connected mobile networks (ICMN). Those routing schemes are tested on specific environments that involve particular mobility complexity whether they are random-based or sociologically organized. We, in this paper, propose community structured environment (CSE) and mobility entropy to discuss the effect of node mobility complexity on message routing performance. We also propose potential-based entropy adaptive routing (PEAR) that adaptively carries messages over the change of mobility entropy. According to our simulation, PEAR has achieved high delivery rate on wide range of mobility entropy, while link-state routing has worked well only at small entropy scenarios and controlled replication-based routing only at large entropy environments.
Photovoltaic (PV) power stations are rapidly increasing as an alternative energy resources for oil, natural gas, coal, and nuclear. If each PV module has intelligence and the ability to report its working status (e.g., voltage and temperature), we can manage the system status of such PV power stations with IoT systems. PV modules are usually installed on an XY-grid, indicating that we can apply an XY multihop routing for gathering such sensor readings with tiny wireless nodes. We propose the architecture and routing schemes of an infrared multihop communication for XY-coordinated PV modules (IR-XY-PV). This includes neighbor discovery and disruption tolerant packet forwarding, i.e., single-copy forwarding and multi-copy forwarding schemes for packet propagation in the network. We have developed 20 node scale IR-XY-PV network and confirmed that IR-XY-PV can provide practically enough performance regarding delivery success rate, delivery latency and memory usage.
Anomaly detection has emerged as a popular technique for detecting malicious behaviors in local area networks (LANs). Various aspects of LAN anomaly detection have been widely studied. Nonetheless, the privacy concern about individual users or their relationship in LAN has not been thoroughly explored in the prior work. In some realistic cases, the anomaly detection analysis needs to be carried out by an external party, located outside the LAN. Thus, it is important for the LAN admin to release LAN data to this party in a private way in order to reveal no information about LAN users; at the same time, the released data must also preserve the utility of being able to detect anomalies. This paper investigates the possibility of privately releasing ARP data that can later be used to identify anomalies in LAN. We present two approaches and show that they satisfy different levels of differential privacy - a rigorous and provable notion for quantifying privacy loss in a system. Our real-world experimental results confirm practical feasibility of our approaches. With a proper privacy budget, both of our approaches preserve more than 90% utility of the released data.
