Search

With the expansion of system scale and data size in power systems, data-driven methods are gradually becoming widely used. However, compared with traditional methods, data-driven methods face more threats in data security and algorithm security. This paper proposes a black box data injection attack method against data-driven strategies in power systems. To obtain a stealthy attack scheme with the greatest impact, an attack vector generator based on deep convolutional neural networks (DCNN) is designed. The generator includes a node selector, a filter, an encoder, and a decoder. The node selector is used to select the most likely successful attack scheme for the filter, the encoder is used to extract sample features, and the decoder is used to generate disturbances based on the features. The proposed generator is trained with an improved generative adversarial network (GAN) and can generate minimal disturbances in real time based on measurement data from the power grid. The effectiveness of the proposed method is demonstrated with an attack experiment on an online transient stability application. [ABSTRACT FROM AUTHOR]

Peer-to-peer (P2P) transactive energy trading has emerged as a promising paradigm towards maximizing the flexibility value of prosumers’ distributed energy resources (DERs). Despite reinforcement learning constitutes a well-suited model-free and data-driven methodological framework to optimize prosumers’ energy management decisions, its application to the large-scale coordinated management and P2P trading among multiple prosumers within an energy community is still challenging, due to the scalability, non-stationarity and privacy limitations of state-of-the-art multi-agent deep reinforcement learning (MADRL) approaches. This paper proposes a novel P2P transactive trading scheme based on the multi-actor-attention-critic (MAAC) algorithm, which addresses the above challenges individually. This method is complemented by a P2P trading platform that incentivizes prosumers to engage in local energy trading while also penalizes each prosumer’s addition to rebound peaks. Case studies involving a real-world, large-scale scenario with 300 residential prosumers demonstrate that the proposed method significantly outperforms the state-of-the-art MADRL methods in reducing the community’s cost and peak demand. [ABSTRACT FROM AUTHOR]

Distributed, consensus-based algorithms have emerged as a promising approach for the coordination of distributed energy resources (DER) due to their communication, computation, privacy and reliability advantages over centralized approaches. However, state-of-the-art consensus-based algorithms address the DER coordination problem in independent time periods and therefore are inherently unable to capture the time-coupling operating characteristics of flexible demand (FD) and energy storage (ES) resources. This paper demonstrates that state-of-the-art algorithms fail to converge when these time-coupling characteristics are considered. In order to address this fundamental limitation, a novel consensus-based algorithm is proposed which includes additional consensus variables. These variables express relative maximum power limits imposed on the FD and ES resources which effectively mitigate the concentration of the FD and ES responses at the same time periods and steer the consensual outcome to a feasible and optimal solution. The convergence and optimality of the proposed algorithm are theoretically proven while case studies numerically demonstrate its convergence, optimality, robustness to initialization and information loss, and plug-and-play adaptability. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Bi-level optimization constitutes the most popular mathematical methodology for modeling the deregulated electricity market. However, state-of-the-art models neglect the physical non-convex operating characteristics of market participants, due to their inherent inability to capture binary decision variables in their representation of the market clearing process, rendering them problematic in modeling markets with complex bidding and unit commitment (UC) clearing mechanisms. This paper addresses this fundamental limitation by proposing a novel modeling approach enabling incorporation of these non-convexities into bi-level optimization market models, which is based on the relaxation and primal-dual reformulation of the original, non-convex lower level problem and the penalization of the associated duality gap. Case studies demonstrate the ability of the proposed approach to closely approximate the market clearing solution of the actual UC clearing algorithm and devise more profitable bidding decisions for strategic producers than the state-of-the-art bi-level optimization approach, and reveal the potential of strategic behavior in terms of misreporting non-convex operating characteristics. [ABSTRACT FROM AUTHOR]

Decarbonization of the electricity system will require significant and continued investment in low-carbon energy sources and electrification of the heat and transport sectors. With diminishing output and shorter operating hours of conventional large-scale fossil-fueled generators, there is a growing need and opportunity for distributed energy resources (DERs) to contribute to the provision of system balancing and security services and support a cost-effective transition to a lower-carbon energy system. Emerging smart technologies will open new opportunities for millions of users to participate actively in the trading of electricity and various ancillary services through alternative mechanisms, such as dynamic pricing, local energy markets, security markets, and peer-to-peer (P2P) trading. [ABSTRACT FROM AUTHOR]

Previous work on the role of the demand side in imperfect electricity markets has demonstrated that its self-price elasticity reduces electricity producers’ ability to exercise market power. However, the concept of self-price elasticity cannot accurately capture consumers’ flexibility, as the latter mainly involves shifting of loads’ operation in time. This paper provides for the first time theoretical and quantitative analysis of the beneficial impact of demand shifting (DS) in mitigating market power by the generation side. Quantitative analysis is supported by a multiperiod equilibrium programming model of the imperfect electricity market, accounting for the time-coupling operational constraints of DS as well as network constraints. The decision making process of each strategic producer is modeled through a bi-level optimization problem, which is solved after converting it to a Mathematical Program with Equilibrium Constraints (MPEC) and linearizing the latter through suitable techniques. The oligopolistic market equilibria resulting from the interaction of multiple independent producers are determined by employing an iterative diagonalization method. Case studies on a test market reflecting the general generation and demand characteristics of the GB system quantitatively demonstrate the benefits of DS in mitigating producers’ market power, by employing relevant indexes from the literature. [ABSTRACT FROM AUTHOR]

Uniform marginal pricing cannot generally support competitive equilibrium solutions in markets with non-convexities, yielding surplus sub-optimality effects. Previous work has identified non-convexities associated with the generation side of electricity markets and proposed different approaches to address surplus sub-optimality. This paper extends this concept to incorporate the demand side. Non-convexities of flexible demand (FD) are identified, including options to forgo demand activities as well as discrete and minimum power levels, and resulting surplus sub-optimality effects are demonstrated through simple examples and a larger case study. Generalized uplift and convex hull pricing approaches addressing these effects are extended to account for FD non-convexities. Concerning the former, generalized uplift functions for FD participants are proposed, and a new rule is introduced for equitable distribution of the total surplus loss compensation among market participants. Regarding the latter, it is demonstrated that convex hull prices are flattened at periods when FD is scheduled to eliminate surplus sub-optimality associated with the FD ability to redistribute energy requirements across time. [ABSTRACT FROM PUBLISHER]