Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency. In addition to dynamic voltage frequency scaling (DVFS) technique, edge-cloud architecture provides a collaborative approach for efficient DNN inference. However, current edge-cloud collaborative inference methods have not optimized various compute resources on edge devices. Thus, we propose DVFO, a novel DVFS-enabled edge-cloud collaborative inference framework, which co-optimizes DVFS and offloading parameters via deep reinforcement learning (DRL). Specifically, DVFO automatically co-optimizes 1) the CPU, GPU and memory frequencies of edge devices, and 2) the offloaded feature map. In addition, it leverages a thinking-while-moving concurrent mechanism to accelerate the DRL learning process, and a spatial-channel attention mechanism to identify the less important DNN feature map for efficient offloading. This approach improves inference performance for different DNN models under various edge-cloud network conditions. Extensive evaluations using two datasets and six widely-deployed DNN models on five heterogeneous edge devices show that DVFO significantly reduces the energy consumption by 33% on average, compared to state-of-the-art schemes. Moreover, DVFO achieves up to 28.6%∼59.1% end-to-end latency reduction, while maintaining accuracy within 1% loss on average.

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.

As deep neural networks (DNNs) are increasingly used in a broad spectrum of edge intelligent applications, it is often necessary to provide multi-DNN model inference services, and it is nontrivial for edge inference platforms to simultaneously deliver high-throughput and low-latency. Such edge devices with multi-DNN model pose new challenges for scheduler designs. First, edge devices should be capable of efficiently scheduling multiple heterogeneous DNN models in order to optimize system utilization. Second, each inference request may have different service level objectives (SLOs) to improve quality of service (QoS). To address these challenges, this paper proposes BCEdge, a novel learning-based scheduling framework that incorporates adaptive batching and concurrent execution of DNN inference services on edge devices.We first propose a shared memory policy to reduce the memory contention among multiple DNN models. Afterwards, a utility function is defined to evaluate the tradeoff between throughput and latency. The scheduler in BCEdge leverages branch-based deep reinforcement learning (DRL) to maximize utility by 1) optimizing batch size, 2) automatically identifying the number of concurrent instances for multiple DNN models, and 3) determining the shared memory configuration among multiple DNN models. Besides, the lightweight DNNbased prediction model in BCEdge can achieve SLO awareness by reducing the performance interference among multiple DNN models. Our prototype implemented on various edge devices illustrates that BCEdge enhances utility by up to 37.6% and reduces memory usage by up to 38% on average, compared to state-of-the-art schemes, while maintaining the SLO violation rate within 5%.

Deep neural network (DNN) models are increasingly popular in edge video analytic applications. However, the computeintensive nature of DNN models pose challenges for energyefficient inference on resource-constrained edge devices. Most existing solutions focus on optimizing DNN inference latency and accuracy, often overlooking energy efficiency. They also fail to account for the varying complexity of video frames, leading to sub-optimal performance in edge video analytics. In this paper, we propose an EnergyEfficient Early-Exit (E4) framework that enhances DNN inference efficiency for edge video analytics by integrating a novel early-exit mechanism with dynamic voltage and frequency scaling (DVFS) governors. It employs an attentionbased cascade module to analyze video frame diversity and automatically determine optimal DNN exit points. Additionally, E4 features a just-in-time (JIT) profiler that uses coordinate descent search to co-optimize CPU and GPU clock frequencies for each layer before the DNN exit points. Extensive evaluations demonstrate that E4 outperforms current state-of-the-art methods, achieving up to 2.8× speedup and 26% average energy saving while maintaining high accuracy.