How to manage the building energy effectively is an urgent but challenging issue to be investigated. In this paper, a real project located in Wuhan, China is taken as a typical example to analyze the network architecture of the energy management system and equipment management strategies of the building electromechanical equipment. Focusing on the prominent issues in current energy-saving control of air conditioning systems and lighting systems, corresponding technical improvement strategies are proposed. These strategies effectively reduce the energy consumption of building electromechanical equipment and systems, enhance energy utilization efficiency and management levels, and contribute to the realization of China's "dual carbon" goals. This paper can provide a reference for the design and application of energy conservation and carbon reduction in large public buildings.

Clustering user devices (UDs) with similar traffic flows enables more effective transmission scheduling and resource allocation in wireless networks, especially for Internet of Things (IoT) with dominant demands for machine-to-machine (M2M) data communications. In this paper, we propose an experience-driven spatial-temporal graph attention network (Exp-STGAN) for UDs’ clustering, by exploiting the spatial-temporal correlations from UDs’ historical traffic flows. Considering the UDs’ heterogeneity, we first characterize each UD’s out-going traffic flows by a dynamic radiation pattern, which reflects the UD’s spatial distribution of traffic demands and its targeted receivers in different directions. We aim to explore UDs’ clustering based on traffic flows’ radiation patterns and propose a spatial-temporal graph attention to aggregate information from different UDs correlated in space and time domains. Without true labels for the UDs’ clustering, we formulate a flow similarity metric based on Kullback-Leibler (KL) divergence to quantify the clustering performance. Moreover, to improve the learning efficiency, we integrate salient human experience into the graph attention module and also continuously update the experience during the training process. Experiments demonstrate that the Exp-STGAN framework can effectively cluster similar UDs by their dynamic traffic flows, highlighting the potential for flow-aware network performance maximization in large-scale IoT systems.

Ensuring safe, real-time motion planning in arbitrary environments requires a robotic manipulator to avoid collisions, obey joint limits, and account for uncertainties in the mass and inertia of objects and the robot itself. This paper proposes Autonomous Robust Manipulation via Optimization with Uncertainty-aware Reachability (ARMOUR), a provably-safe, receding-horizon trajectory planner and tracking controller framework for robotic manipulators to address these challenges. ARMOUR first constructs a robust controller that tracks desired trajectories with bounded error despite uncertain dynamics. ARMOUR then uses a novel recursive Newton-Euler method to compute all inputs required to track any trajectory within a continuum of desired trajectories. Finally, ARMOUR over-approximates the swept volume of the manipulator; this enables one to formulate an optimization problem that can be solved in real-time to synthesize provably-safe motions. This paper compares ARMOUR to state of the art methods on a set of challenging manipulation examples in simulation and demonstrates its ability to ensure safety on real hardware in the presence of model uncertainty without sacrificing performance. Project page:https://roahmlab.github.io/armour/.

Synthetic aperture radar (SAR) images are inherently affected by speckle noise. Deep learning-based methods have shown good potential in image denoising task. Most deep learning methods for denoising focus on additive Gaussian noise removal. However, SAR images are usually contaminated by non-Gaussian multiplicative speckle noise. In this paper, we propose a novel deep unrolling network named SAR-DURNet to deal with the SAR image despeckling problem. We establish optimization problem of speckle noise removal by using the priori of noise distribution, which can be sovled by half-quadratic splitting (HQS) method with iterative steps. We unroll the iterative process into a trainable deep unrolling network(SAR-DURNet). The parameters of the SAR-DURNet are trained end-to-end with simulated SAR image dataset. Experimental results on simulated test data and real SAR data show that the proposed approach has superior results in terms of quantitative performance metrics and the preservation of intricate visual details, compared to several well-known SAR image despeckling methods.

In this paper, we aim to improve the throughput capacity of a wireless powered network by allowing user devices (UDs) to adapt channel access strategies. A base station (BS) can receive data and provide RF energy for UDs simultaneously in a full duplex mode. Each UD can choose a flexible access mode to transmit its data with the non-orthogonal multiple access technique or assist the other UDs' data transmissions via backscattering when it has less urgent data demands or insufficient energy supply. We maximize the sum throughput by optimizing the UDs' channel access mode, time allocation and beamforming strategies, according to the UDs' channel conditions and energy status. Practically, maximizing throughput is a challenging problem due to the uncertain channel information, the UDs' dynamic traffic demands and limited energy storages. Therefore, we propose a hierarchical learning approach to decompose the access mode selection and transmission control in two steps. We first employ a multi-agent deep reinforcement learning approach to update each UD's channel access strategy by interacting with the uncertain network environment. Then, we efficiently update the UDs' time allocation and the BS's beamforming strategies to further enhance the sum throughput. The simulation results verify a significant improvement in terms of the throughput and the learning efficiency compared to the benchmark methods.

Mobile edge computing (MEC) is viewed as a promising technology to address the challenges of intensive computing demands in hotspots (HSs). In this paper, we consider a unmanned aerial vehicle (UAV)-assisted backscattering MEC system. The UAVs can fly from parking aprons to HSs, providing energy to HSs via RF beamforming and collecting data from wireless users in HSs through backscattering. We aim to maximize the long-term utility of all HSs, subject to the stability of the HSs' energy queues. This problem is a joint optimization of the data offloading decision and contract design that should be adaptive to the users' random task demands and the time-varying wireless channel conditions. A deep reinforcement learning based contract incentive (DRLCI) strategy is proposed to solve this problem in two steps. Firstly, we use deep Q-network (DQN) algorithm to update the HSs' offloading decisions according to the changing network environment. Secondly, to motivate the UAVs to participate in resource sharing, a contract specific to each type of UAVs has been designed, utilizing Lagrangian multiplier method to approach the optimal contract. Simulation results show the feasibility and efficiency of the proposed strategy, demonstrating a better performance than the natural DQN and Double-DQN algorithms.

In this paper, we consider a mobile edge computing (MEC) system with multiple unmanned aerial vehicles (UAVs) and stochastic energy harvesting. The UAVs' mobility can help data offloading over a larger geographical area containing multi- hotspots (HSs). If HSs have offloading requests, the dispatch agent (DA) can recruit different types of UAVs to fly close to HSs and help computation. We aim to maximize the long-term utility of all HSs, subject to the stability of energy queue. The proposed problem is a joint optimization problem of offloading strategy and contract design in a dynamic setting over time. We design a deep reinforcement learning based contract incentive (DRLCI) strategy that solves the joint optimization problem in two steps. Firstly, we use an improved deep Q-network (DQN) algorithm to obtain the offloading decision. Secondly, to motivate UAVs to participate in resources sharing, a contract has been designed for asymmetric information scenarios, and Lagrangian multiplier method has been utilized to approach the optimal contract. Simulation results show the feasibility and efficiency of the proposed strategy. It can achieve a very close-to the performance obtained by complete information scenario.

In this paper, we propose a novel dictionary learning model based on the idea of deep unrolling to deal with the synthetic aperture radar (SAR) image change detection problem. Deep unrolling aims at unrolling the iterative algorithm into a trainable neural network. In our proposed method, the idea of unrolling is applied to the Iterative Shrinkage Threshold Algorithm (ISTA), which is one of classic algorithms for dictionary learning. Then, the proposed Unrolling Iterative Shrinkage Threshold Algorithm (UR-ISTA), is utilized to obtain the sparse codes of the difference results. Finally, the change map is computed by k-means clustering algorithm. The advantage of UR-ISTA method is relatively low time cost, which makes it possible to add dictionary updating step to calculate specific feature vectors. Experimental results show that the proposed approach has superior accuracy and precision compared to several well-known change detection techniques. The proposed UR-ISTA algorithm shows more robustness than another sparse representation algorithm.

Fuzz testing is typically carried out by running the target program and the fuzzing engine offline in a lab environment. The environment setup may depend on specialized test harness code to activate the target program and inject the test data. Also, due to the vast program state space, domain knowledge-dependent optimization is often needed in the environment setup to achieve reasonably efficient fuzz testing. We propose In-Vivo Fuzzing to alleviate the burdens by performing online fuzz testing on live programs. In-Vivo Fuzzing hooks I/O library calls in a live program to collect test seeds. Upon request, the In-Vivo Runtime will create a fork of the target program and carry out fuzz testing on the forked process. The runtime states from the live program provide a vantage point to start the fuzzing process, and the test seeds collected from the live workload also facilitate the generation of effective test inputs. We applied In-Vivo Fuzzing to network service programs and implemented a prototype on top of the AFL fuzzer. Experiment results indicate that In-Vivo Fuzzing can reach vulnerabilities in real-world programs much more quickly than the baseline. We also demonstrate the potential application of In-Vivo Fuzzing in detecting unknown attacks, where live attack states are captured and amplified through fuzz testing.