In Federated Learning (FL), with parameter aggregated by a central node, the communication overhead is a substantial concern. To circumvent this limitation and alleviate the single point of failure within the FL framework, recent studies have introduced Decentralized Federated Learning (DFL) as a viable alternative. Considering the device heterogeneity, and energy cost associated with parameter aggregation, in this paper, the problem on how to efficiently leverage the limited resources available to enhance the model performance is investigated. Specifically, we formulate a problem that minimizes the loss function of DFL while considering energy and latency constraints. The proposed solution involves optimizing the number of local training rounds across diverse devices with varying resource budgets. To make this problem tractable, we first analyze the convergence of DFL with edge devices with different rounds of local training. The derived convergence bound reveals the impact of the rounds of local training on the model performance. Then, based on the derived bound, the closed-form solutions of rounds of local training in different devices are obtained. Meanwhile, since the solutions require the energy cost of aggregation as low as possible, we modify different graph-based aggregation schemes to solve this energy consumption minimization problem, which can be applied to different communication scenarios. Finally, a DFL framework which jointly considers the optimized rounds of local training and the energy-saving aggregation scheme is proposed. Simulation results show that, the proposed algorithm achieves a better performance than the conventional schemes with fixed rounds of local training, and consumes less energy than other traditional aggregation schemes.

Decentralized Federated Learning (DFL), a Federated Edge Learning (FEEL) framework without a server, can avoid the huge communication overhead of the server and the single point of failure within FEEL. Since there is no server, the convergence of DFL depends not only on the communication conditions and number of edge nodes, but also on the graph topology of the network over which edge nodes communicate. Moreover, in practical scenarios, considering the limited communication resources, such as the latency and energy costs, the convergence of DFL also suffers from quantization errors. In this paper, we consider the decentralized gradient descent (DGD), which is widely applied in DFL, and examine the influence of graph topology and quantization on the convergence of DGD in different wireless networks with cost constraints. According to the derived convergence bound, the maximum quantization error acceptable for the DFL convergence is obtained. Furthermore, motivated by the limited iterations caused by the impact of constrained communication costs on each edge node, we compare the convergence bounds between higher and lower connectivity topologies, which face different energy consumption in one round of communication. Based on this comparison, the impact of graph topologies with energy constraints on the convergence can be observed. Numerical simulations confirm the validity of our analyses, supporting the correctness of our theoretical findings.

Federated learning (FL) can generate huge communication overhead for the central server, which may cause operational challenges. Furthermore, the central server’s failure or compromise may result in a breakdown of the entire system. To mitigate this issue, decentralized federated learning (DFL) has been proposed as a more resilient framework that does not rely on a central server, as demonstrated in previous works. DFL involves the exchange of parameters between each device through a wireless network. To optimize the communication efficiency of the DFL system, various transmission schemes have been proposed and investigated. However, the limited communication resources present a significant challenge for these schemes. Therefore, to explore the impact of constrained resources, such as computation and communication costs on the DFL, this study analyzes the model performance of resource-constrained DFL using different communication schemes (digital and analog) over wireless networks. Specifically, we provide convergence bounds for both digital and analog transmission approaches, enabling analysis of the model performance trained on DFL. Furthermore, for digital transmission, we investigate and analyze resource allocation between computation and communication and convergence rates, obtaining its communication complexity and the minimum probability of correction communication required for convergence guarantee. For analog transmission, we discuss the impact of channel fading and noise on the model performance and the maximum errors accumulation with convergence guarantee over fading channels. Finally, we conduct numerical simulations to evaluate the performance and convergence rate of convolutional neural networks (CNNs) and Vision Transformer (ViT) trained in the DFL framework on fashion-MNIST and CIFAR-10 datasets. Our simulation results validate our analysis and discussion, revealing how to improve performance by optimizing system parameters under different communication conditions.

Accurately estimating crop carbon sinks at large regional scales from the perspective of remote sensing is of great significance for carbon neutrality research, crop yield estimation, and scientific agriculture. In this study, an improved Carnegie–Ames–Stanford approach (CASA) model was coupled with time-series satellite remote sensing images to estimate Net primary productivity. The NEP is then further calculated by coupling the soil respiration model to represent the carbon sink at a regional scale. The main research contents: (1) The month-by-month net primary productivity of crops in Jiangsu Province in 2021. (2) The net ecosystem productivity of crops in Jiangsu Province month by month in 2021.

In federated learning (FL), a number of devices train their local models and upload the corresponding parameters or gradients to the base station (BS) for global model updates. However, the eavesdropper can recover data from parameters or gradients, resulting in data leakage. To defend against eavesdropping attacks, in this article, we propose an algorithm that divides the transmit power proportionally between the transmitted signal and artificial noise (AN) to counteract the eavesdropper for wireless FL. In this algorithm, due to the limited communication resources, the ratio of signal power to total power and the aggregation frequency need to be carefully chosen, to guarantee the model accuracy and security at the same time. In order to achieve this goal, we maximize the secrecy rate with the system/user power and model performance constraints. To make this problem tractable, we derive two bounds of the secrecy rate and loss function, which allows us to obtain closed-form expressions for the power of AN and the aggregation frequency. Furthermore, in order to make our analysis more realistic, we consider the FL model with channel fading and additive white Gaussian noise (AWGN) over uplink and downlink, respectively. Specifically, we discuss the convergence of FL over noisy multiple access channels (MACs). Simulation results confirm the convergence and the effectiveness of the proposed algorithm.

Summary Internet of things (IoT) is applied to water inrush source monitoring network for overcoming complexity and uncertainty of coal mines in monitoring. This study starts from the idea of sensory mines and the architecture of IoT, and describes key techniques in IoT‐based mine water inrush source sensing. In the sensing layer, networked and intelligent sensors are employed for constructing the distributed monitoring system; in the network service layer, data mining, 3D geoscience simulation system and cloud computing are combined for establishing the cloud service platform so as to comprehensively analyze water inrush sources; in the application layer, a novel maximum/minimum‐margin‐based hierarchical‐SVM model for the identification of water‐inrush sources is proposed. Test results demonstrate that, owing to the application of mine IoT, both information collection efficiency and processing capability of water‐inrush source monitoring can be effectively enhanced, and the established water source identification system exhibits low false alarm rate and mis‐detection ratio, thereby significantly improving the prediction reliability.