Search

The deployment of renewable energy in power systems may raise serious voltage instabilities. Electric vehicles (EVs), owing to their mobility and flexibility characteristics, can provide various ancillary services including active and reactive power. However, the distributed control of EVs under such scenarios is a complex decision-making problem with enormous dynamics and uncertainties. Most existing literature employs model-based approaches to formulate the active and reactive power control problems, which require full models and are time-consuming. This paper proposes a multi-agent reinforcement learning method featuring actor-critic networks and a parameter sharing framework to solve the EVs coordinated active and reactive power control problem towards both demand-side response and voltage regulations. The proposed method can further enhance the learning stability and scalability with privacy perseverance via the location marginal prices. Simulation results based on a modified IEEE 15-bus network are developed to validate its effectiveness in providing system charging and voltage regulation services.

Coronavirus disease2019 (COVID-19)has become a global pandemic. Many recognition approaches based on convolutional neural networks have been proposed for COVID-19 chest X-ray images. However, only a few of them make good use of the potential inter- and intra-relationships of feature maps. Considering the limitation mentioned above, this paper proposes an attention-based convolutional neural network, called PCXRNet, for diagnosis of pneumonia using chest X-ray images. To utilize the information from the channels of the feature maps, we added a novel condense attention module (CDSE) that comprised of two steps: condensation step and squeeze-excitation step. Unlike traditional channel attention modules, CDSE first downsamples the feature map channel by channel to condense the information, followed by the squeeze-excitation step, in which the channel weights are calculated. To make the model pay more attention to informative spatial parts in every feature map, we proposed a multi-convolution spatial attention module (MCSA). It reduces the number of parameters and introduces more nonlinearity. The CDSE and MCSA complement each other in series to tackle the problem of redundancy in feature maps and provide useful information from and between feature maps. We used the ChestXRay2017 dataset to explore the internal structure of PCXRNet, and the proposed network was applied to COVID-19 diagnosis. As a result, the network achieves an accuracy of 94.619%, recall of 94.753%, precision of 95.286%, and F1-score of 94.996% on the COVID-19 dataset.

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.

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.

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.

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.