Power load forecasting is the foundation of maintaining power grid stability, and can assist in decision-making to reduce operating costs. Fine-grained long sequence load forecasting contributes to formulating plans f...
详细信息
Power load forecasting is the foundation of maintaining power grid stability, and can assist in decision-making to reduce operating costs. Fine-grained long sequence load forecasting contributes to formulating plans for power purchase, electricity consumption, energy storage, etc. Long sequence load forecasting requires models to effectively store memory and to accurately capture the long-term complex mapping between output and input. Therefore, this paper converts load sequences into three-dimensional (3D) continuous video frames and presents a model based on long short-term memory (LSTM) named the Improved 3D LSTM (I3D-LSTM) for predicting video frames. It contains two 3D LSTM units: For highly periodic load data, a Long-memory 3D LSTM unit is proposed, which has stronger long-term memory and removes short-term memory;On weakly periodic datasets, a Simplified 3D LSTM unit without the scoring parts exhibits excellent performance. I3D-LSTM also contains a 3D recurrent neural network architecture with residual. Dropblock and batch normalization are integrated into the I3D-LSTM, which are analyzed as excellent solutions for overfitting in 3D LSTM. Comprehensive tests are conducted on different sequence lengths in multiple real-world datasets. Comparison results indicate that I3D-LSTM outperforms various advanced models.
Privacy preservation is a challenging problem in decentralized nonconvex optimization containing sensitive data. Prior approaches to decentralized nonconvex optimization are either not strong enough to protect privacy...
详细信息
Privacy preservation is a challenging problem in decentralized nonconvex optimization containing sensitive data. Prior approaches to decentralized nonconvex optimization are either not strong enough to protect privacy or exhibit low utility under a high privacy guarantee. To address these issues, we propose a differentially private linearized alternating direction method of multipliers (DP-LADMM), which achieves fast convergence property for nonconvex objective functions while achieving saddle/maximum avoidance under differential privacy guarantee. We also apply the Analytic Gaussian Mechanism to track the cumulative privacy loss and provide a tight global differential privacy guarantee for DP-LADMM. The theoretical analysis offers an explicit convergence rate for our algorithm. To the best of our knowledge, this is the first paper to provide explicit convergence for decentralized nonconvex optimization with differential privacy and saddle/maximum avoidance. Numerical simulations and comparison studies on decentralized estimation confirm the superiority of the algorithm and the effectiveness of global privacy preservation.
Recent advancements in unsupervised person re-identification (re-ID) methods have demonstrated high performance by leveraging fine-grained local context, often referred to as part-based methods. However, many existing...
详细信息
Recent advancements in unsupervised person re-identification (re-ID) methods have demonstrated high performance by leveraging fine-grained local context, often referred to as part-based methods. However, many existing part-based methods rely on horizontal division to obtain local contexts, leading to misalignment issues caused by various human poses. Moreover, misalignment of semantic information within part features hampers the effectiveness of metric learning, thereby limiting the potential of part-based methods. These challenges result in under-utilization of part features in existing approaches. To address these issues, we introduce the Spatial Cascaded Clustering and Weighted Memory (SCWM) method. SCWM aims to parse and align more accurate local contexts for different human body parts while allowing the memory module to balance hard example mining and noise suppression. Specifically, we first analyze the issues of foreground omissions and spatial confusions in previous methods. We then propose foreground and space corrections to enhance the completeness and reasonableness of human parsing results. Next, we introduce a weighted memory and utilize two weighting strategies. These strategies address hard sample mining for global features and enhance noise resistance for part features, enabling better utilization of both global and part features. Extensive experiments conducted on Market-1501, DukeMTMC-reID and MSMT17 datasets validate the effectiveness of the proposed method over numerous state-of-the-art methods.
Kalman filter (KF) is increasingly attracted for sensorless control of surface permanent magnet synchronous motors (SPMSMs) due to its strong robustness against measurement and system noise. However, conventional meth...
详细信息
The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also det...
详细信息
The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: (i) considering both the encoder and decoder feature in upsampling kernel generation;(ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator;and (iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://***/poppinace/fade
This study proposes a distributed secondary control scheme based on distributed robust iterative learning control (DRILC) for islanded alternating current (AC) microgrids subjected to external disturbances. By employi...
详细信息
This study proposes a distributed secondary control scheme based on distributed robust iterative learning control (DRILC) for islanded alternating current (AC) microgrids subjected to external disturbances. By employing the decoupled sliding mode consensus approach, voltage regulation, frequency restoration, and accurate active power sharing can be achieved within a finite time on the proposed novel integral terminal sliding mode (ITSM) manifold. Furthermore, the appropriate iterative update law in the ITSM-based controller is utilized to learn and eliminate external disturbances as effectively as possible. In the proposed control scheme, the iterative learning control and sliding mode control are designed to function in a complementary manner, which enhances the performance of the secondary control scheme for multi-objective regulations. The stability criteria and robustness to external disturbances of the closed-loop microgrid system in the iteration and time domains are also rigorously derived with the help of the Lyapunov direct method. Finally, the effectiveness of the proposed secondary control scheme is validated by case studies of an islanded AC microgrid test system in the MATlab/SimPowerSystems software environment.
In this paper, we investigate leader-follower consensus (LFC) of multiple Euler-Lagrange systems (MELSs) under the case that followers can only measure partial output information of leader system, and the communicatio...
详细信息
In this paper, we investigate leader-follower consensus (LFC) of multiple Euler-Lagrange systems (MELSs) under the case that followers can only measure partial output information of leader system, and the communication network among followers is switching and jointly connected. Firstly, in order to accurately estimate complete state information of the leader system in real time, we propose a distributed reduced-order observer, which is valid over a jointly connected switching network. Then, by applying this distributed reduced-order observer, we further design an observer-based controller for multiple Euler-Lagrange systems (MELSs) to reach leader-follower consensus (LFC). Distinct with the existing controllers for LFC of MELSs, this controller is robust for bounded external disturbances, and independent of the structure and features of Euler-Lagrange (EL) system. At last, a simulation example is given to confirm the effectiveness of the proposed distributed reduced-order observer and robust controller. Note to Practitioners-Many practical engineering applications (such as spacecrafts, mobile robot manipulators) can be modeled as multiple uncertain Euler-Lagrange systems, where each agent suffers external input disturbances, and only a portion of followers can measure partial components of leader's output. However, most relevant works assumed that the dynamic information of each agent is completely known, agents do not suffer external input disturbances, and all follower agents can measure full-dimensional output of leader. How to achieve LFC for such MELSs has become a main focus of control researches. Thus, this paper proposes an adaptive distributed reduced-order observer-based consensus algorithm for such MELSs, whose communication network is switching and jointly connected. Finally, the effectiveness of the proposed algorithm is illustrated by a simulation example.
Interactive portrait matting refers to extracting the soft portrait from a given image that best meets the user’s intent through their inputs. Existing methods often underperform in complex scenarios, mainly due to t...
详细信息
This article focuses on achieving the finite-time synchronization (FTS) for fractional complex dynamical networks (FCDNs) using hybrid impulsive control. Initially, a novel framework for local FTS is developed, buildi...
详细信息
This article focuses on achieving the finite-time synchronization (FTS) for fractional complex dynamical networks (FCDNs) using hybrid impulsive control. Initially, a novel framework for local FTS is developed, building upon the relaxed inequality tkCDt V-alpha ( t ) <= chi V (t)- eta . To expand the attraction domain within the local FTS framework, a piecewise fractional-order differential inequality based on impulsive control systems is proposed. Subsequently, a new hybrid control strategy is designed by integrating a simple feedback controller with an impulsive controller involving a finite number of impulses, which can be accurately calculated using the proposed impulsive degree. Additionally, a set of local/global FTS criteria is formulated, and the settling time can be explicitly estimated. Lastly, an illustrative example is presented to demonstrate the effectiveness of the derived results.
In this paper, the coordination control problem of discrete-time multi-agent systems (MASs) with uncertainties is studied by the output feedback technique, where the uncertainties are unknown disturbances and initial ...
详细信息
In this paper, the coordination control problem of discrete-time multi-agent systems (MASs) with uncertainties is studied by the output feedback technique, where the uncertainties are unknown disturbances and initial states. Firstly, a reduced-order neighborhood framer is constructed by using the boundary information of uncertainties. Secondly, a control protocol that depends on the absolute information of the agent framer is proposed by solving a modified algebraic Riccati equation. The results demonstrate that the control protocol can render a reduced-order neighborhood framer as a reduced-order neighborhood interval observer, which can not only realize the interval-valued estimation on the sum of the relative states between each agent and its neighbors in real time, but also realize the cooperative behavior of MASs under some sufficient conditions involving network synchronization and the instability degree of the agent. In addition, direct and indirect methods are proposed to eliminate the nonnegative constraint. Finally, the theoretical results are verified by two numerical simulations. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
暂无评论