Cortical neural connectivity demonstrates a small World network Topology (SW), yet its effects on neural information processing are still unclear. This work investigates the Echo State Networks (ESNs) performance in the learning task utilizing the Newman-Watts-Strogatz (NWS) graph structure as a reservoir topology. The Principal Component Analysis (PCA) technique for reservoir state dimensionality reduction effectively addresses the limitations associated with the complexity of the irregular SWT graph. Additionally, in this work, we investigate the improved ESN with SW Topology (iESN-SWT) as encoder and the Deep Neural Network (DNN) as decoder for deep readout. The iESN-SWT model is evaluated on five-time series benchmark datasets, which are Arabic Digits (AD), CMUsubject16 (CMU), Japanese Vowels (Jap. V), ECG (ECG), and Swedish Leaf (SL) datasets. Results show significant improvements in classification accuracy with 91.7 %, 93.1 %, 96.3 %, 79 %, and 65.8 %, respectively, for the datasets AD, CMU, Jap. V, ECG, and SL.

To reap the benefit of big data generated by the massive number of Internet of Things (IoT) devices while preserving data privacy, federated learning (FL) has been proposed to enable IoT devices to train machine learning models locally. That is, instead of sharing the local data sets, different clients in terms of IoT devices only need to upload their local models to a centralized FL server. Client selection in FL is critical to maximize the number of qualified clients, who can successfully upload their local models to the FL server before the predefined deadline. Normally, client selection is coupled with wireless resource management owing to the fact that different clients need to share the same spectrum to upload their local models. The existing solutions of joint optimizing client selection and resource management are designed based on frequency-division multiple access (FDMA) or time-division multiple access (TDMA), which do not consider the dynamics of the clients and lead to low bandwidth utilization. In this article, we propose the Nonorthogonal-Multiple-Access (NOMA)-based resource allocation for client selection in FL to dynamically and jointly optimize client selection for each global iteration as well as the transmission power of each selected client in each time slot within a global iteration. We design the deep-reinforcement-learn-based client selection in NOMA-based federated learning (DREAM-FL) algorithm to solve the problem. Extensive simulations are conducted to demonstrate that DREAM-FL can select more qualified clients and has higher model accuracy than FDMA and TDMA-based solutions.

Federated learning (FL) is a collaborative machine learning framework to enable different clients such as Internet of Things (IoT) devices to participate in a machine learning model training process, while preserving data privacy. Client selection is critical to determine the performance of FL. Most of the existing client selection methods aim to maximize the number of selected clients, who can upload their local models before the deadline, in each global iteration, thus potentially accelerating the model convergence rate. However, these methods ignore the fact that most of the IoT devices are powered by on-board batteries and harvested green energy from the environment to prolong battery life. Hence, clients selected by these methods may not have sufficient energy to upload their local models in a global iteration or are unable to participate in the training process in the near future due to battery drainage. In this paper, we propose a novel client selection, entitled “EnerGy-AwaRe CliEnt SElection for Green FeDerated Learning (GREED)”, to optimize the trade-off between maximizing the number of selected clients and minimizing the energy drawn from batteries for the selected clients, while ensuring that all the selected clients have sufficient energy to upload their local models before the deadline. The performance of GREED is validated via extensive simulations.

Federated learning (FL) has been proposed to efficiently and privacy-preserving distributed machine learning architecture for the Internet of Things (IoT). In a wireless FL system, clients in IoT devices train their local models over the local data sets. The derived local models are uploaded to an FL server to generate a global model, broadcasted to the clients in the next global iteration for further training. Owing to the heterogeneous feature of the clients, client selection is critical to determine the overall training time. Traditionally, the objective of client selection is to select the maximum number of clients who can derive and upload their local models before the deadline in each global iteration. However, selecting more clients increases the energy consumption of the clients. Moreover, selecting the maximum number of clients is unnecessary as having fewer clients in early global iterations and more clients in later global iterations have been proved to achieve higher model accuracy. Hence, this article proposes to dynamically adjust and optimize the tradeoff between maximizing the number of selected clients and minimizing the total energy consumption of the clients by selecting suitable clients and allocating appropriate resources in terms of CPU frequency and transmission power. We formulate the joint client selection and resource management problem and design the energy and latency-aware resource management and client selection (ELASTIC) algorithm to efficiently solve the problem. Extensive simulations are conducted to demonstrate the performance of ELASTIC.

Federated learning (FL) is a distributed machine learning technique to address the data privacy issue. Participant selection is critical to determine the latency of the training process in a heterogeneous FL architecture, where users with different hardware setups and wireless channel conditions communicate with their base station to participate in the FL training process. Many solutions have been designed to consider computational and uploading latency of different users to select suitable participants such that the straggler problem can be avoided. However, none of these solutions consider the waiting time of a participant, which refers to the latency of a participant waiting for the wireless channel to be available, and the waiting time could significantly affect the latency of the training process, especially when a huge number of participants are involved in the training process and share the wireless channel in the time-division duplexing manner to upload their local FL models. In this paper, we consider not only the computational and uploading latency but also the waiting time (which is estimated based on an M/G/1 queueing model) of a participant to select suitable participants. We formulate an optimization problem to maximize the number of selected participants, who can upload their local models before the deadline in a global iteration. The Latency awarE pARticipant selectioN (LEARN) algorithm is proposed to solve the problem and the performance of LEARN is validated via simulations.

In this paper, we propose to cache popular Internet of Things (IoT) resources in the brokers (which can be considered as application layer middlewares) by applying the CoAP Publish/Subscribe protocol in order to reduce the energy consumption of the servers (e.g., IoT devices), which host these resources. If an IoT resource is cached in a broker, all the requests to retrieve the content of the IoT resource will be delivered to the broker, which responses to the requests by sending related contents, thus increasing the power consumption of the broker. In order to reduce the operational expenditure of the broker provider, each broker is powered by green energy and uses on-grid energy as a backup. On-gird energy consumption of the brokers may be different. That is, some brokers with low green energy generation and more cached IoT resources may consume more on-grid energy consumption than brokers with high green energy generation and less cached IoT resources. In order to minimize the total on-grid energy consumption of the brokers, the Green Energy Aware Resource caching (GEAR) algorithm is proposed to balance energy demands by re-allocating/re-caching the popular IoT resources among the brokers. The performance of GEAR is validated via simulations.