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.
Decarbonization of electricity systems drives significant and continued investments in distributed energy sources to support the cost-effective transition to low-carbon energy systems. However, the ...rapid integration of distributed photovoltaic (PV) generation presents great challenges in obtaining reliable and secure grid operations because of its limited visibility and intermittent nature. Under this reality, net load forecasting is facing unprecedented difficulty in answering the following question: How can we accurately predict the net load while capturing the massive uncertainties arising from distributed PV generation and load, especially in the context of high PV penetration? This paper proposes a novel probabilistic day-ahead net load forecasting method to capture both epistemic uncertainty and aleatoric uncertainty using Bayesian deep learning, which is a new field that combines Bayesian probability theory and deep learning. The proposed methodological framework employs clustering in subprofiles and considers residential rooftop PV outputs as input features to enhance the performance of aggregated net load forecasting. Numerical experiments have been carried out based on fine-grained smart meter data from the Australian grid with separately recorded measurements of rooftop PV generation and loads. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and indicate the importance and effectiveness of subprofile clustering and high PV visibility.
This paper considers the impact of uncertain wind forecasts on the value of stored energy (such as pumped hydro) in a future U.K. system, where wind supplies over 20% of the energy. Providing more of ...the increased requirement for reserves from standing reserve sources could increase system operation efficiency, enhance wind power absorption, achieve fuel cost savings, and reduce CO 2 emissions. Generally, storage-based standing reserve's value is driven by the amount of installed wind and by generation system flexibility. Benefits are more significant in systems with low generation flexibility and with large installed wind capacity. Storage is uniquely able to stock up generated excesses during high-wind/low-demand periods, and subsequently discharge this energy as needed. When storage is combined with standing reserve provided from conventional generation (e.g., open-cycle gas turbines), it is valuable in servicing the highly frequent smaller imbalances
In the deregulated power systems setting, the realization of the significant demand flexibility potential should be coupled with its integration in electricity markets. Centralized market mechanisms ...raise communication, computational and privacy issues while existing dynamic pricing schemes fail to realize the actual value of demand flexibility. In this two-part paper, a novel day-ahead pool market mechanism is proposed, combining the solution optimality of centralized mechanisms with the decentralized demand participation structure of dynamic pricing schemes and based on Lagrangian relaxation (LR) principles. Part I presents the theoretical background, algorithmic approaches and suitable examples to address challenges associated with the application of the mechanism and provides an implementation framework. Non-convexities in reschedulable demand participants' price response and their impacts on the ability of the basic LR structure to reach feasible market clearing solutions are identified and a simple yet effective LR heuristic method is developed to produce both feasible and high quality solutions by limiting the concentrated shift of reschedulable demand to the same low-priced time periods.
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.
This paper presents an alternative approach to pseudo measurement modeling in the context of distribution system state estimation (DSSE). In the proposed approach, pseudo measurements are generated ...from a few real measurements using artificial neural networks (ANNs) in conjunction with typical load profiles. The error associated with the generated pseudo measurements is made suitable for use in the weighted least squares (WLS) state estimation by decomposition into several components through the Gaussian mixture model (GMM). The effect of ANN-based pseudo measurement modeling on the quality of state estimation is demonstrated on a 95-bus section of the U.K. generic distribution system (UKGDS) model.
•The economic and environmental benefits of smart EVs/HPs are quantified.•This paper implements an advanced stochastic analytical framework.•Operating patterns and potential flexibility of EVs/HPs ...are sourced from UK trials.•A comprehensive set of case studies across UK future scenarios are carried out.
This paper presents an advanced stochastic analytical framework to quantify the benefits of smart electric vehicles (EVs) and heat pumps (HPs) on the carbon emission and the integration cost of renewable energy sources (RES) in the future UK electricity system. The typical operating patterns of EVs/HPs as well as the potential flexibility to perform demand shifting and frequency response are sourced from recent UK trials. A comprehensive range of case studies across several future UK scenarios suggest that smart EVs/HPs could deliver measurable carbon reductions by enabling a more efficient operation of the electricity system, while at the same time making the integration of electrified transport and heating demand significantly less carbon intensive. The second set of case studies establish that smart EVs/HPs have significant potential to support cost-efficient RES integration by reducing: (a) RES balancing cost, (b) cost of required back-up generation capacity, and (c) cost of additional low-carbon capacity required to offset lower fuel efficiency and curtailed RES output while achieving the same emission target. Frequency response provision from EVs/HPs could significantly enhance both the carbon benefit and the RES integration benefit of smart EVs/HPs.
In this paper, the major benefits and challenges of electricity demand side management (DSM) are discussed in the context of the UK electricity system. The relatively low utilisation of generation ...and networks (of about 50%) means that there is significant scope for DSM to contribute to increasing the efficiency of the system investment. The importance of the diversity of electricity load is discussed and the negative effects of DSM on load diversity illustrated. Ageing assets, the growth in renewable and other low-carbon generation technologies and advances in information and communication technologies are identified as major additional drivers that could lead to wider applications of DSM in the medium term. Potential benefits of DSM are discussed in the context of generation and of transmission and distribution networks. The provision of back-up capacity by generation may not be efficient as it will be needed relatively infrequently, and DSM may be better placed to support security. We also present an analysis of the value of DSM in balancing generation and demand in a future UK electricity system with significant variable renewable generation. We give a number of reasons for the relatively slow uptake of DSM, particularly in the residential, commercial and small business sectors. They include a lack of metering, information and communication infrastructure, lack of understanding of the benefits of DSM, problems with the competitiveness of DSM when compared with traditional approaches, an increase in the complexity of system operation and inappropriate market incentives.
Interacting subsystems are commonly described by networks, where multimodal behaviour found in most natural or engineered systems found recent extension in form of multilayer networks. Since ...multimodal interaction is often not dictated by network topology alone and may manifest in form of cross-layer information exchange, multilayer network flow becomes of relevant further interest. Rationale can be found in most interacting subsystems, where a form of multimodal flow across layers can be observed in e.g., chemical processes, energy networks, logistics, finance, or any other form of conversion process relying on the laws of conservation. To this end, the formal notion of heterogeneous network flow is proposed, as a multilayer flow function aligned with the theory of network flow. Furthermore, dynamic equivalence is established with the framework of Petri nets, as the baseline model of concurrent event systems. Application of the resulting multilayer Laplacian flow and flow centrality is presented, along with graph learning based inference of multilayer relationships over multimodal data. On synthetic data the proposed framework demonstrates benefits of multimodal flow derivation in critical component identification. It also displays applicability in relationship inference (learning based function approximation) on multimodal time series. On real-world data the proposed framework provides, among others, multimodal flow interpretation of U.S. economic activity, uncovering underlying empirical steady state probability distribution, as well as inherent network (economic) robustness.