The increase of the computing capacity of IoT devices and the appearance of lightweight machine learning frameworks have led to the situation that machine learning can nowadays be run in IoT applications at the network edge. There is an opportunity to implement machine learning algorithms with the more and more computationally powerful edge nodes and using the ever increasing amount of local data coming from nearby sensors. For this purpose, federated learning becomes a promising machine learning approach, where a machine learning model is trained by various nodes using their local data. For performing practical federated learning experiments, we have built a testbed deployed within a wireless city mesh network with geographically distributed low capacity devices. We describe the testbed implementation and show its potential to experimentally study federated learning protocols and algorithms in real edge environments.

Environmental monitoring is a growing application of the Internet of Things. The low cost of the sensor nodes, LoRa connectivity, and increased awareness of environmental issues have motivated many citizens to participate in open IoT monitoring applications. However, the value of these applications for decision makers is limited since the data from the IoT sensors do not have sufficient guarantees to be trusted. In this paper, we introduce a new concept that attributes value to both IoT data and devices, such as sensor nodes and gateways, and leverage distributed ledger technology to enable a data trust system. A first design decision was to assign Ethereum addresses with their associated public and private key pairs to all actors. This allows the authentication of data senders and hence the accounting for the contribution of each participant. Secondly, we introduce an auditor to validate the received IoT data. The results of these audits increase the trust in the quality of the data. We present the architectural components that we designed to enhance trust in open IoT monitoring applications and present an operational prototype to show the feasibility of the implementation. By achieving both trust in the data and accounting of contributions for giving rewards, open participatory IoT monitoring applications can become both valuable and sustainable. Then, trusted open monitoring may complement commercial solutions as a technical and economic alternative for addressing the increasing environmental monitoring needs of our society.

Federated learning is a distributed learning technique in which a machine learning model is trained collaboratively among several nodes. While the privacy preservation of the training data is one of the important promises of federated learning, there is also an opportunity to use low capacity devices for machine learning model training by taking advantage of the fact that the training effort is divided among many nodes. In this paper we conduct experiments with a federated learning network deployed on several low capacity devices connected to a wireless mesh network. The measurements show the hardware capacity and link bandwidth of the clients on the federated learning process. The results suggest that for heterogeneous networks the federated learning clients should be extended with more autonomous decision capacities according to the network and local conditions.