Search

In this paper, we propose a neural network with an encoder-decoder architecture that incorporates atrous spatial pyramid pooling (ASPP) and convolutional block attention module (CBAM). We evaluated our approach by using the ISIC 2018 dataset. The results demonstrate that the proposed framework significantly enhances segmentation performance.

The effective pricing of electric vehicle (EV) charging by aggregators constitutes a key problem toward the realization of the significant EV flexibility potential in deregulated electricity systems and has been addressed by previous work through bi-level optimization formulations. However, the solution approach adopted in previous work cannot capture the discrete nature of the EV charging/discharging levels. Although reinforcement learning (RL) can tackle this challenge, state-of-the-art RL methods require discretization of state and/or action spaces and thus exhibit limitations in terms of solution optimality and computational requirements. This article proposes a novel deep reinforcement learning (DRL) method to solve the examined EV pricing problem, combining deep deterministic policy gradient (DDPG) principles with a prioritized experience replay (PER) strategy and setting up the problem in multi-dimensional continuous state and action spaces. Case studies demonstrate that the proposed method outperforms state-of-the-art RL methods in terms of both solution optimality and computational requirements and comprehensively analyze the economic impacts of smart-charging and vehicle-to-grid (V2G) flexibility on both aggregators and EV owners.

Multi-energy systems (MES) are attracting increasing attention driven by its potential to offer significant flexibility in future smart grids. At the residential level, the roll-out of smart meters and rapid deployment of smart energy devices call for autonomous multi-energy management systems which can exploit real-time information to optimally schedule the usage of different devices with the aim of minimizing end-users’ energy costs. This paper proposes a novel real-time autonomous energy management strategy for a residential MES using a model-free deep reinforcement learning (DRL) based approach, combining state-of-the-art deep deterministic policy gradient (DDPG) method with an innovative prioritized experience replay strategy. This approach is tailored to align with the nature of the problem by posing it in multi-dimensional continuous state and action spaces, facilitating more cost-effective control strategies to be devised. The superior performance of the proposed approach in reducing end-user’s energy cost while coping with the MES uncertainties is demonstrated by comparing it against state-of-the-art DRL methods as well as conventional stochastic programming and robust optimization methods in numerous case studies in a real-world scenario.

The investigation of the effects of demand flexibility on the pricing strategies and the profits of electricity retailers has recently emerged as a highly interesting research area. However, the state-of-the-art, bi-level optimisation modelling approach makes the unrealistic assumption that retailers treat wholesale market prices as exogenous, fixed parameters. This study proposes a tri-level optimisation model, which drops this assumption and represents the wholesale market clearing process endogenously, thus capturing the realistic implications of a retailer's pricing strategies and the resulting demand response on the wholesale market prices. The scope of the examined case studies is three-fold. First of all, they demonstrate the interactions between the retailer, the flexible consumers and the wholesale market and analyse the fundamental effects of the consumers’ time-shifting flexibility on the retailer's revenue from the consumers, its cost in the wholesale market and its overall profit. Furthermore, they analyse how these effects of demand flexibility depend on the retailer's relative size in the market and the strictness of the regulatory framework. Finally, they highlight the added value of the proposed tri-level model by comparing its outcomes against the state-of-the-art bi-level modelling approach.

With increasing prosumers employed with distributed energy resources (DER), advanced energy management has become increasingly important. To this end, integrating demand-side DER into electricity market is a trend for future smart grids. The double-side auction (DA) market is viewed as a promising peer-to-peer (P2P) energy trading mechanism that enables interactions among prosumers in a distributed manner. To achieve the maximum profit in a dynamic electricity market, prosumers act as price makers to simultaneously optimize their operations and trading strategies. However, the traditional DA market is difficult to be explicitly modelled due to its complex clearing algorithm and the stochastic bidding behaviors of the participants. For this reason, in this paper we model this task as a multi-agent reinforcement learning (MARL) problem and propose an algorithm called DA-MADDPG that is modified based on MADDPG by abstracting the other agents’ observations and actions through the DA market public information for each agent’s critic. The experiments show that 1) prosumers obtain more economic benefits in P2P energy trading w.r.t. the conventional electricity market independently trading with the utility company; and 2) DA-MADDPG performs better than the traditional Zero Intelligence (ZI) strategy and the other MARL algorithms, e.g., IQL, IDDPG, IPPO and MADDPG.

Previously works on analysing imperfect electricity markets have employed conventional game-theoretic approaches. However, such approaches necessitate that each strategic market player has full knowledge of the operating parameters and the strategies of its rivals as well as the computational algorithm of the market clearing process. This unrealistic assumption, along with the modeling and computational complexities, renders such approaches less applicable for conducting practical multi-period and multi-spatial equilibrium analysis. This paper proposes a novel multi-agent deep reinforcement learning (MA-DRL) based methodology, combining multi-agent intelligence, the deep policy gradient (DPG) method, and an innovative long short term memory (LSTM) based representation network for optimizing the offering strategies of multiple self-interested generation companies (GENCOs) as well as exploring the market outcome stemming from their interactions. The proposed approach is tailored to align with the nature of the examined problem by posing it, for the first time, in multi-dimensional continuous state and action spaces, enabling GENCOs to receive accurate feedback regarding the impact of their offering strategies on the market clearing outcome, and devise more profitable bidding decisions by exploiting the entire action domain, and thereby facilitates more accurate equilibrium analysis. The proposed LSTM-based representation network extracts discriminative features which further improves the learning performance and thus promises more profitable offerings strategies for each GENCO. Case studies demonstrate that the proposed method i) achieves a significantly higher profit than state-of-the-art RL methods for a single GENCO's optimal offering strategy problem and ii) outperforms the state-of-the-art equilibrium programming models in efficiently identifying an imperfect market equilibrium with/without network congestion. Quantitative economic analysis is carried out on the obtained equilibrium.

With the roll-out of smart meters and the increasing prevalence of distributed energy resources (DERs) at the residential level, end-users rely on home energy management systems (HEMSs) that can harness real-time data and employ artificial intelligence techniques to optimally manage the operation of different DERs, which are targeted toward minimizing the end-user’s energy bill. In this respect, the performance of the conventional model-based demand response (DR) management approach may deteriorate due to the inaccuracy of the employed DER operating models and the probabilistic modeling of uncertain parameters. To overcome the above drawbacks, this paper develops a novel real-time DR management strategy for a residential household based on the twin delayed deep deterministic policy gradient (TD3) learning approach. This approach is model-free, and thus does not rely on knowledge of the distribution of uncertainties or the operating models and parameters of the DERs. It also enables learning of neural-network-based and fine-grained DR management policies in a multi-dimensional action space by exploiting high-dimensional sensory data that encapsulate the uncertainties associated with the renewable generation, appliances’ operating states, utility prices, and outdoor temperature. The proposed method is applied to the energy management problem for a household with a portfolio of the most prominent types of DERs. Case studies involving a real-world scenario are used to validate the superior performance of the proposed method in reducing the household’s energy costs while coping with the multi-source uncertainties through comprehensive comparisons with the state-of-the-art deep reinforcement learning (DRL) methods.

Coronavirus disease 2019 (COVID-19) has spread rapidly around the world. In order to diagnose COVID-19 more quickly, in this paper, a depthwise separable DenseNet was proposed. The paper constructed a deep learning model with 2 905 chest X-ray images as experimental dataset. In order to enhance the contrast, the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to preprocess the X-ray image before network training, then the images were put into the training network and the parameters of the network were adjusted to the optimal. Meanwhile, Leaky ReLU was selected as the activation function. VGG16, ResNet18, ResNet34, DenseNet121 and SDenseNet models were used to compare with the model proposed in this paper. Compared with ResNet34, the proposed classification model of pneumonia had improved 2.0%, 2.3% and 1.5% in accuracy, sensitivity and specificity respectively. Compared with the SDenseNet network without depthwise separable convolution, number of parameters of the proposed model was reduced by 43.9%, but the classification effect did not decrease. It can be found that the proposed DWSDenseNet has a good classification effect on the COVID-19 chest X-ray images dataset. Under the condition of ensuring the accuracy as much as possible, the depthwise separable convolution can effectively reduce number of parameters of the model.新型冠状病毒肺炎肆虐全球，为了更加快速地诊断新型冠状病毒肺炎（COVID-19），本文提出一种深度可分离稠密网络 DWSDenseNet，以 2 905 例 COVID-19 胸部 X 线平片影像作为实验数据集，在网络训练前使用限制对比度自适应直方图均衡化（CLAHE）算法对图像进行预处理，增强图像的对比度，将预处理之后的图像放入训练网络中，采用 Leaky ReLU 作为激活函数，调整参数以达到最优。本文引入 VGG16、ResNet18、ResNet34、DenseNet121 和 SDenseNet 模型进行比较，所提出的网络在三分类实验中相较于 ResNet34 在准确率、灵敏度和特异性上分别提高了 2.0%、2.3%、1.5%。相对于改进前的 SDenseNet 网络，本文模型的参数量减少了 43.9%，但分类效果并未下降。通过对比实验可以发现，本文所提出的深度可分离稠密网络对 COVID-19 胸部 X 线平片影像数据集具有良好的分类效果，在保证准确率的情况下，深度可分离卷积能够有效地降低模型参数量。.

Local energy markets (LEM) have recently attracted great interest as they enable effective coordination of small-scale distributed energy resources (DER) at the customer side, and avoidance of distribution network reinforcements. However, the introduction of LEM has also significant implications on the strategic interactions between the customers and incumbent electricity retailers. This paper explores for the first time these interactions by proposing a novel multi-period bi-level optimization model, which captures the pricing decisions of a strategic retailer in the upper level (UL) and the response of both independent customers and the LEM (both including flexible consumers, micro-generators and energy storages) in the lower level (LL). Since the LL problem representing the LEM is non-convex, a new analytical approach is employed for solving the developed bi-level problem. The examined case studies demonstrate that the introduction of an LEM reduces the customers’ energy dependency on the retailer and limits the retailer’s strategic potential of exploiting the customers through large differentials between buy and sell prices. As a result, the profit of the retailer is significantly reduced while the customers, primarily the LEM participants and to a lower extent non-participating customers, achieve significant economic benefits.

Bi-level optimization and reinforcement learning (RL) constitute the state-of-the-art frameworks for modeling strategic bidding decisions in deregulated electricity markets. However, the former neglects the market participants’ physical non-convex operating characteristics, while conventional RL methods require discretization of state and / or action spaces and thus suffer from the curse of dimensionality. This paper proposes a novel deep reinforcement learning (DRL) based methodology, combining a deep deterministic policy gradient (DDPG) method with a prioritized experience replay (PER) strategy. This approach sets up the problem in multidimensional continuous state and action spaces, enabling market participants to receive accurate feedback regarding the impact of their bidding decisions on the market clearing outcome, and devise more profitable bidding decisions by exploiting the entire action domain, also accounting for the effect of non-convex operating characteristics. Case studies demonstrate that the proposed methodology achieves a significantly higher profit than the alternative state-of-the-art methods, and exhibits a more favorable computational performance than benchmark RL methods due to the employment of the PER strategy.

The problem of real-time autonomous energy management is an application area that is receiving unprecedented attention from consumers, governments, academia, and industry. This paper showcases the first application of deep reinforcement learning (DRL) to real-time autonomous energy management for a multi-carrier energy system. The proposed approach is tailored to align with the nature of the energy management problem by posing it in multi-dimensional continuous state and action spaces, in order to coordinate power flows between different energy devices, and to adequately capture the synergistic effect of couplings between different energy carriers. This fundamental contribution is a significant step forward from earlier approaches that only sought to control the power output of a single device and neglected the demand-supply coupling of different energy carriers. Case studies on a real-world scenario demonstrate that the proposed method significantly outperforms existing DRL methods as well as model-based control approaches in achieving the lowest energy cost and yielding a representation of energy management policies that adapt to system uncertainties.

Bi-level optimization and reinforcement learning (RL) constitute the state-of-the-art frameworks for modeling strategic bidding decisions in deregulated electricity markets. However, the former neglects the market participants' physical non-convex operating characteristics, while conventional RL methods require discretization of state and / or action spaces and thus suffer from the curse of dimensionality. This paper proposes a novel deep reinforcement learning (DRL) based methodology, combining a deep deterministic policy gradient (DDPG) method with a prioritized experience replay (PER) strategy. This approach sets up the problem in multi-dimensional continuous state and action spaces, enabling market participants to receive accurate feedback regarding the impact of their bidding decisions on the market clearing outcome, and devise more profitable bidding decisions by exploiting the entire action domain, also accounting for the effect of non-convex operating characteristics. Case studies demonstrate that the proposed methodology achieves a significantly higher profit than the alternative state-of-the-art methods, and exhibits a more favourable computational performance than benchmark RL methods due to the employment of the PER strategy.

EV traveling data