Aiming at the problems of low data fusion precision and poor stability in greenhouse wireless sensor networks (WSNs), a multi-sensor data fusion algorithm based on trust degree and improved genetics is proposed. The original data collected by the sensor nodes are sent to the gateway through the sink node, and data preprocessing based on cubic exponential smoothing is performed at the gateway to eliminate abnormal data and noise data. In fuzzy theory, the range of membership functions is determined, according to this feature, the data fusion algorithm based on exponential trust degree is used to fuse the smooth data to avoid the absolute degree of mutual trust between data. In this paper, we have improved the crossover and mutation operations in the standard genetic algorithm, the variation is separated from the intersection, the chaotic sequence is used to determine the intersection, and the weakest single-point intersection is implemented to improve the convergence accuracy of the algorithm, weaken and avoid jitter problems during optimization. The chaotic sequence is used to mutate multiple genes in the chromosome to avoid premature algorithm maturity. Finally, the improved genetic algorithm is used to optimize the fusion estimation value. The experimental results show that the cubic exponential smoothing can significantly reduce the data fluctuation and improve the stability of the system. Compared with the commonly used data fusion algorithms such as arithmetic average method and adaptive weighting method, the data fusion algorithm based on trust degree and improved genetics has higher fusion precision. At the same time, the execution time of the algorithm is greatly reduced.

No abstract

No abstract

<p>As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time. Such edge platforms with multiple DNN models pose new challenges for scheduler designs. First, each request may have different service level objectives (SLOs) to improve quality of service (QoS). Second, the edge platforms should be able to efficiently schedule multiple heterogeneous DNN models so that system utilization can be improved. To meet these two goals, this paper proposes BCEdge, a novel learning-based scheduling framework that takes adaptive batching and concurrent execution of DNN inference services on edge platforms. We define a utility function to evaluate the trade-off between throughput and latency. The scheduler in BCEdge leverages maximum entropy-based deep reinforcement learning (DRL) to maximize utility by 1) co-optimizing batch size and 2) the number of concurrent models automatically. Our prototype implemented on different edge platforms shows that the proposed BCEdge enhances utility by up to 37.6% on average, compared to state-of-the-art solutions, while satisfying SLOs.</p>

<p>As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time. Such edge platforms with multiple DNN models pose new challenges for scheduler designs. First, each request may have different service level objectives (SLOs) to improve quality of service (QoS). Second, the edge platforms should be able to efficiently schedule multiple heterogeneous DNN models so that system utilization can be improved. To meet these two goals, this paper proposes BCEdge, a novel learning-based scheduling framework that takes adaptive batching and concurrent execution of DNN inference services on edge platforms. We define a utility function to evaluate the trade-off between throughput and latency. The scheduler in BCEdge leverages maximum entropy-based deep reinforcement learning (DRL) to maximize utility by 1) co-optimizing batch size and 2) the number of concurrent models automatically. Our prototype implemented on different edge platforms shows that the proposed BCEdge enhances utility by up to 37.6% on average, compared to state-of-the-art solutions, while satisfying SLOs.</p>