Time series forecasting, particularly within the Internet of Things (IoT) and hydrological domains, plays a critical role in predicting future events based on historical data, which is essential for strategic decision making. Effective flood forecasting is pivotal for optimal water resource management and for mitigating the adverse impacts of flood events. While deep learning methods have demonstrated exceptional performance in time series prediction through advanced feature extraction and pattern recognition, they encounter significant limitations when applied to scenarios with sparse data, especially in flood forecasting. The scarcity of historical data can severely hinder the generalization capabilities of traditional deep learning models, presenting a notable challenge in practical flood prediction applications. To address this issue, we introduce MetaTrans-FSTSF, a pioneering meta-learning framework that redefines few-shot time series forecasting. By innovatively integrating MAML and Transformer architectures, our framework provides a specialized solution tailored for the unique challenges of flood prediction, including data scarcity and complex temporal patterns. This framework goes beyond standard implementations, delivering significant improvements in predictive accuracy and adaptability. Our approach leverages Model-Agnostic Meta-Learning (MAML) to enable rapid adaptation to new forecasting tasks with minimal historical data. Our inner architecture is a Transformer-based meta-predictor capable of capturing intricate temporal dependencies inherent in flood time series data. Our framework was evaluated using diverse datasets, including a real-world hydrological dataset from a small catchment area in Wuyuan, China, and other benchmark time series datasets. These datasets were preprocessed to align with the meta-learning approach, ensuring their suitability for tasks with limited data availability. Through extensive evaluation, we demonstrate that MetaTrans-FSTSF substantially improves predictive accuracy, achieving a reduction of up to 16%, 19%, and 8% in MAE compared to state-of-the-art methods. This study highlights the efficacy of meta-learning techniques in overcoming the limitations posed by data scarcity and enhancing flood forecasting accuracy where historical data are limited.

Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consider infrastructure challenges, such as resource limitations and device churn. Furthermore, the training of RL methods is often not designed for practical application, as these approaches frequently do not consider generalizability and are not optimized for energy efficiency. To fill this gap, we propose BIPPO (Budget-aware Independent Proximal Policy Optimization), which is an energy-efficient multi-agent RL solution that improves performance. We evaluate BIPPO on two image classification tasks run in a highly budget-constrained setting, with FL clients training on non-IID data, a challenging context for vanilla FL. The improved sampler of BIPPO enables it to increase the mean accuracy compared to non-RL mechanisms, traditional PPO, and IPPO. In addition, BIPPO only consumes a negligible proportion of the budget, which stays consistent even if the number of clients increases. Overall, BIPPO delivers a performant, stable, scalable, and sustainable solution for client selection in IoT-FL.

Hierarchical federated learning (HFL) designs introduce intermediate aggregator nodes between clients and the global federated learning server in order to reduce communication costs and distribute server load. One side effect is that machine learning model replication at scale comes "for free" as part of the HFL process: model replicas are hosted at the client end, intermediate nodes, and the global server level and are readily available for serving inference requests. This creates opportunities for efficient model serving but simultaneously couples the training and serving processes and calls for their joint orchestration. This is particularly important for continual learning, where serving a model while (re)training it periodically, upon specific triggers, or continuously, takes place over shared infrastructure spanning the computing continuum. Consequently, training and inference workloads can interfere with detrimental effects on performance. To address this issue, we propose an inference load-aware HFL orchestration scheme, which makes informed decisions on HFL configuration, considering knowledge about inference workloads and the respective processing capacity. Applying our scheme to a continual learning use case in the transportation domain, we demonstrate that by optimizing aggregator node placement and device-aggregator association, significant inference latency savings can be achieved while communication costs are drastically reduced compared to flat centralized federated learning.

The increasing volume and complexity of IoT systems demand a transition from the cloud-centric model to a decentralized IoT architecture in the so-called Computing Continuum, with no or minimal reliance on central servers. This paradigm shift, however, raises novel research concerns for decentralized coordination, calling for accurate policies. However, building such strategies is not trivial. Our work aims to relieve the DevOps engineers from this concern and propose a solution for autonomous, decentralized task allocation at runtime for IoT systems. To this end, we present a semantic communication approach and an ad-hoc lightweight coordination strategy based on Ant Colony Optimization (ACO). We compare the ACO strategy with Random Search and Gossip protocol-based algorithms. We conduct accurate experiments with up to a hundred nodes in both a static and a dynamic environment, i.e., with device outages. We show that ACO finds a matching node with the smallest hops and messages sent. While the Gossip strategy can allocate the most tasks successfully, ACO scales better, thus being a promising candidate for decentralized task coordination in IoT clusters.