Showing papers in "IEEE Transactions on Smart Grid in 2020"
TL;DR: This article provides an overview of the key features of peer-to-peer trading and its benefits of relevance to the grid and prosumers, and systematically classify the existing research in terms of the challenges that the studies address in the virtual and the physical layers.
Abstract: Peer-to-peer trading is a next-generation energy management technique that economically benefits proactive consumers (prosumers) transacting their energy as goods and services. At the same time, peer-to-peer energy trading is also expected to help the grid by reducing peak demand, lowering reserve requirements, and curtailing network loss. However, large-scale deployment of peer-to-peer trading in electricity networks poses a number of challenges in modeling transactions in both the virtual and physical layers of the network. As such, this article provides a comprehensive review of the state-of-the-art in research on peer-to-peer energy trading techniques. By doing so, we provide an overview of the key features of peer-to-peer trading and its benefits of relevance to the grid and prosumers. Then, we systematically classify the existing research in terms of the challenges that the studies address in the virtual and the physical layers. We then further identify and discuss those technical approaches that have been extensively used to address the challenges in peer-to-peer transactions. Finally, the paper is concluded with potential future research directions.
443 citations
TL;DR: An intensive summary of several detection algorithms for false data injection attacks by categorizing them and elaborating on the pros and cons of each category is provided.
Abstract: Cyber-physical attacks are the main substantial threats facing the utilization and development of the various smart grid technologies. Among these attacks, false data injection attack represents a main category with its widely varied types and impacts that have been extensively reported recently. In addressing this threat, several detection algorithms have been developed in the last few years. These were either model-based or data-driven algorithms. This paper provides an intensive summary of these algorithms by categorizing them and elaborating on the pros and cons of each category. The paper starts by introducing the various cyber-physical attacks along with the main reported incidents in history. The significance and the impacts of the false data injection attacks are then reported. The concluding remarks present the main criteria that should be considered in developing future detection algorithms for the false data injection attacks.
362 citations
TL;DR: Under Stackelberg equilibrium (SE), the costs incurred by a consumer for procuring either the RES or nRES are significantly reduced while the derived utility by producer is maximized and the CO2 emission cost and consequently the energy cost are minimized.
Abstract: Traditionally, energy consumers pay non-commodity charges (e.g., transmission, environmental and network costs) as a major component of their energy bills. With the distributed energy generation, enabling energy consumption close to producers can minimize such costs. The physically constrained energy prosumers in power networks can be logically grouped into virtual microgrids (VMGs) using telecommunication systems. Prosumer benefits can be optimised by modelling the energy trading interactions among producers and consumers in a VMG as a Stackelberg game in which producers lead and consumers follow. Considering renewable (RES) and non-renewable energy (nRES) resources, and given that RES are unpredictable thus unschedulable, we also describe cost and utility models that include load uncertainty demands of producers. The results show that under Stackelberg equilibrium (SE), the costs incurred by a consumer for procuring either the RES or nRES are significantly reduced while the derived utility by producer is maximized. We further show that when the number of prosumers in the VMG increases, the CO2 emission cost and consequently the energy cost are minimized at the SE. Lastly, we evaluate the peer-to-peer (P2P) energy trading scenario involving noncooperative energy prosumers with and without Stackelberg game. The results show that the P2P energy prosumers attain 47% higher benefits with Stackelberg game.
196 citations
TL;DR: A data-driven method based on neural network (NN) and Q -learning algorithm is developed, which achieves superior performance on cost-effective schedules for HEM system, and demonstrates the effectiveness of the newly developed framework.
Abstract: This paper proposes a novel framework for home energy management (HEM) based on reinforcement learning in achieving efficient home-based demand response (DR). The concerned hour-ahead energy consumption scheduling problem is duly formulated as a finite Markov decision process (FMDP) with discrete time steps. To tackle this problem, a data-driven method based on neural network (NN) and ${Q}$ -learning algorithm is developed, which achieves superior performance on cost-effective schedules for HEM system. Specifically, real data of electricity price and solar photovoltaic (PV) generation are timely processed for uncertainty prediction by extreme learning machine (ELM) in the rolling time windows. The scheduling decisions of the household appliances and electric vehicles (EVs) can be subsequently obtained through the newly developed framework, of which the objective is dual, i.e., to minimize the electricity bill as well as the DR induced dissatisfaction. Simulations are performed on a residential house level with multiple home appliances, an EV and several PV panels. The test results demonstrate the effectiveness of the proposed data-driven based HEM framework.
194 citations
TL;DR: The simulation results from the proposed data-driven deep learning method, as well as comparisons with conventional model-based methods, substantiate the effectiveness of the proposed approach in solving power system problems with partial or uncertain information.
Abstract: In this paper, an intelligent multi-microgrid (MMG) energy management method is proposed based on deep neural network (DNN) and model-free reinforcement learning (RL) techniques. In the studied problem, multiple microgrids are connected to a main distribution system and they purchase power from the distribution system to maintain local consumption. From the perspective of the distribution system operator (DSO), the target is to decrease the demand-side peak-to-average ratio (PAR), and to maximize the profit from selling energy. To protect user privacy, DSO learns the MMG response by implementing a DNN without direct access to user’s information. Further, the DSO selects its retail pricing strategy via a Monte Carlo method from RL, which optimizes the decision based on prediction. The simulation results from the proposed data-driven deep learning method, as well as comparisons with conventional model-based methods, substantiate the effectiveness of the proposed approach in solving power system problems with partial or uncertain information.
190 citations
TL;DR: A model-free approach based on safe deep reinforcement learning (SDRL) is proposed to solve the EV charging/discharging scheduling problem as a constrained Markov Decision Process (CMDP) to minimize the charging cost as well as guarantee the EV can be fully charged.
Abstract: Electric vehicles (EVs) have been popularly adopted and deployed over the past few years because they are environment-friendly. When integrated into smart grids, EVs can operate as flexible loads or energy storage devices to participate in demand response (DR). By taking advantage of time-varying electricity prices in DR, the charging cost can be reduced by optimizing the charging/discharging schedules. However, since there exists randomness in the arrival and departure time of an EV and the electricity price, it is difficult to determine the optimal charging/discharging schedules to guarantee that the EV is fully charged upon departure. To address this issue, we formulate the EV charging/discharging scheduling problem as a constrained Markov Decision Process (CMDP). The aim is to find a constrained charging/discharging scheduling strategy to minimize the charging cost as well as guarantee the EV can be fully charged. To solve the CMDP, a model-free approach based on safe deep reinforcement learning (SDRL) is proposed. The proposed approach does not require any domain knowledge about the randomness. It directly learns to generate the constrained optimal charging/discharging schedules with a deep neural network (DNN). Unlike existing reinforcement learning (RL) or deep RL (DRL) paradigms, the proposed approach does not need to manually design a penalty term or tune a penalty coefficient. Numerical experiments with real-world electricity prices demonstrate the effectiveness of the proposed approach.
166 citations
TL;DR: A decentralized market clearing mechanism for the P2P energy trading considering the privacy of the agents, power losses as well as the utilization fees for using the third party owned network is proposed.
Abstract: Peer-to-peer (P2P) energy trading is one of the promising approaches for implementing decentralized electricity market paradigms. In the P2P trading, each actor negotiates directly with a set of trading partners. Since the physical network or grid is used for energy transfer, power losses are inevitable, and grid-related costs always occur during the P2P trading. A proper market clearing mechanism is required for the P2P energy trading between different producers and consumers. This paper proposes a decentralized market clearing mechanism for the P2P energy trading considering the privacy of the agents, power losses as well as the utilization fees for using the third party owned network. Grid-related costs in the P2P energy trading are considered by calculating the network utilization fees using an electrical distance approach. The simulation results are presented to verify the effectiveness of the proposed decentralized approach for market clearing in P2P energy trading.
161 citations
TL;DR: In this paper, a peer-to-peer (P2P) energy trading scheme that can help a centralized power system to reduce the total electricity demand of its customers at the peak hour is proposed.
Abstract: This paper proposes a peer-to-peer (P2P) energy trading scheme that can help a centralized power system to reduce the total electricity demand of its customers at the peak hour. To do so, a cooperative Stackelberg game is formulated, in which the centralized power system acts as the leader that needs to decide on a price at the peak demand period to incentivize prosumers to not seek any energy from it. The prosumers, on the other hand, act as followers and respond to the leader’s decision by forming suitable coalitions with neighboring prosumers in order to participate in P2P energy trading to meet their energy demand. The properties of the proposed Stackelberg game are studied. It is shown that the game has a unique and stable Stackelberg equilibrium, as a result of the stability of prosumers’ coalitions. At the equilibrium, the leader chooses its strategy using a derived closed-form expression, while the prosumers choose their equilibrium coalition structure. An algorithm is proposed that enables the centralized power system and the prosumers to reach the equilibrium solution. Numerical case studies demonstrate the beneficial properties of the proposed scheme.
155 citations
TL;DR: An open-source platform named Reinforcement Learning for Grid Control (RLGC) has been designed for the first time to assist the development and benchmarking of DRL algorithms for power system control.
Abstract: Power system emergency control is generally regarded as the last safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived “worst” case scenario or a few typical operation scenarios. These schemes are facing significant adaptiveness and robustness issues as increasing uncertainties and variations occur in modern electrical grids. To address these challenges, this paper developed novel adaptive emergency control schemes using deep reinforcement learning (DRL) by leveraging the high-dimensional feature extraction and non-linear generalization capabilities of DRL for complex power systems. Furthermore, an open-source platform named Reinforcement Learning for Grid Control (RLGC) has been designed for the first time to assist the development and benchmarking of DRL algorithms for power system control. Details of the platform and DRL-based emergency control schemes for generator dynamic braking and under-voltage load shedding are presented. Robustness of the developed DRL method to different simulation scenarios, model parameter uncertainty and noise in the observations is investigated. Extensive case studies performed in both the two-area, four-machine system and the IEEE 39-bus system have demonstrated excellent performance and robustness of the proposed schemes.
152 citations
TL;DR: A novel deep reinforcement learning (DRL) based methodology, combining a deep deterministic policy gradient (DDPG) method with a prioritized experience replay (PER) strategy is proposed, enabling market participants to receive accurate feedback regarding the impact of their bidding decisions on the market clearing outcome.
Abstract: 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.
151 citations
TL;DR: This paper studies the low-carbon operation of MESs by coordinating the transmission-level and distribution-level via the energy-carbon integrated prices by illustrating the effectiveness and benefit of the proposed carbon pricing method in reducing carbon emissions more efficiently than current methods.
Abstract: The interdependence of different energy forms in multiple energy systems (MESs) could leverage their synergies to reduce carbon emissions. However, such synergies cannot be exploited without the right incentives. This paper studies the low-carbon operation of MESs by coordinating the transmission-level and distribution-level via the energy-carbon integrated prices. Energy prices are decided by locational marginal pricing principles in the transmission-level MES. At the same time, the carbon emissions of different energy systems are uniformly priced using a carbon emission flow (CEF) model based on the consumers’ actual emission contributions by tracing the embedded flow of CO2. Various distribution-level MESs modeled by energy hubs (EHs) are independently operated in response to the variation in the integrated prices. The whole bi-level model formulates an equilibrium problem and is solved iteratively. Case studies based on two MESs at different scales illustrate the effectiveness and benefit of the proposed carbon pricing method in reducing carbon emissions more efficiently than current methods.
TL;DR: This work proposes a safe off-policy deep reinforcement learning algorithm to solve Volt-VAR control problems in a model-free manner, and outperforms the existing reinforcement learning algorithms and conventional optimization-based approaches on a large feeder.
Abstract: Volt-VAR control is critical to keeping distribution network voltages within allowable range, minimizing losses, and reducing wear and tear of voltage regulating devices. To deal with incomplete and inaccurate distribution network models, we propose a safe off-policy deep reinforcement learning algorithm to solve Volt-VAR control problems in a model-free manner. The Volt-VAR control problem is formulated as a constrained Markov decision process with discrete action space, and solved by our proposed constrained soft actor-critic algorithm. Our proposed reinforcement learning algorithm achieves scalability, sample efficiency, and constraint satisfaction by synergistically combining the merits of the maximum-entropy framework, the method of multiplier, a device-decoupled neural network structure, and an ordinal encoding scheme. Comprehensive numerical studies with the IEEE distribution test feeders show that our proposed algorithm outperforms the existing reinforcement learning algorithms and conventional optimization-based approaches on a large feeder.
TL;DR: A peer-to-peer (P2P) local electricity market model incorporating both energy trading and uncertainty trading simultaneously and enables more PV uncertainty to be balanced locally rather than propagating to the upper layer system is proposed.
Abstract: In the future power system, an increasing number of distributed energy resources will be integrated including intermittent generation like photovoltaic (PV) and flexible demand like electric vehicles (EVs). It has been long thought to utilize the flexible demand to absorb the PV output locally with the technical solution proposed while an effective commercial arrangement is yet to be developed due to the significant uncertainty associated with local generation. This paper proposes a peer-to-peer (P2P) local electricity market model incorporating both energy trading and uncertainty trading simultaneously. The novelty is to match the forecast power with demand having time flexibility and the uncertain power with demand having power flexibility. This market enables more PV uncertainty to be balanced locally rather than propagating to the upper layer system. In the test case, 55.3% of PV forecast error can be balanced locally in the proposed joint market. In comparison, 43.6% of PV forecast error is balanced locally when the forecast power and uncertain power are traded separately in a day-ahead market and a real-time market. The proposed P2P market can also motivate PV owners to improve forecast accuracy.
TL;DR: A distributed operation strategy using double deep LaTeX notation, capable of dealing with uncertainties in the system in both grid-connected and islanded modes is applied to managing the operation of a community battery energy storage system (CBESS) in a microgrid system.
Abstract: $Q$ -learning-based operation strategies are being recently applied for optimal operation of energy storage systems, where, a $Q$ -table is used to store $Q$ -values for all possible state-action pairs. However, $Q$ -learning faces challenges when it comes to large state space problems, i.e., continuous state space problems or problems with environment uncertainties. In order to address the limitations of $Q$ -learning, this paper proposes a distributed operation strategy using double deep $Q$ -learning method. It is applied to managing the operation of a community battery energy storage system (CBESS) in a microgrid system. In contrast to $Q$ -learning, the proposed operation strategy is capable of dealing with uncertainties in the system in both grid-connected and islanded modes. This is due to the utilization of a deep neural network as a function approximator to estimate the $Q$ -values. Moreover, the proposed method can mitigate the overestimation that is the major drawback of the standard deep $Q$ -learning. The proposed method trains the model faster by decoupling the selection and evaluation processes. Finally, the performance of the proposed double deep $Q$ -learning-based operation method is evaluated by comparing its results with a centralized approach-based operation.
TL;DR: This paper makes a review on the above mentioned aspects, including the emerging frequency regulation services, updated grid codes and grid-scale ESS projects, and some key technical issues are discussed and prospects are outlined.
Abstract: Electric power systems foresee challenges in stability due to the high penetration of power electronics interfaced renewable energy sources. The value of energy storage systems (ESS) to provide fast frequency response has been more and more recognized. Although the development of energy storage technologies has made ESSs technically feasible to be integrated in larger scale with required performance, the policies, grid codes and economic issues are still presenting barriers for wider application and investment. Recent years, a few regions and countries have designed new services to meet the upcoming grid challenges. A number of grid-scale ESS projects are also implemented aiming to trial performance, demonstrate values, and gain experience. This paper makes a review on the above mentioned aspects, including the emerging frequency regulation services, updated grid codes and grid-scale ESS projects. Some key technical issues are also discussed and prospects are outlined.
TL;DR: This paper addresses this problem by using a model-free deep reinforcement learning (DRL) method to optimize the battery energy arbitrage considering an accurate battery degradation model and a hybrid Convolutional Neural Network and Long Short Term Memory model is adopted to predict the price for the next day.
Abstract: Accurate estimation of battery degradation cost is one of the main barriers for battery participating on the energy arbitrage market. This paper addresses this problem by using a model-free deep reinforcement learning (DRL) method to optimize the battery energy arbitrage considering an accurate battery degradation model. Firstly, the control problem is formulated as a Markov Decision Process (MDP). Then a noisy network based deep reinforcement learning approach is proposed to learn an optimized control policy for storage charging/discharging strategy. To address the uncertainty of electricity price, a hybrid Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) model is adopted to predict the price for the next day. Finally, the proposed approach is tested on the historical U.K. wholesale electricity market prices. The results compared with model based Mixed Integer Linear Programming (MILP) have demonstrated the effectiveness and performance of the proposed framework.
TL;DR: A cooperative secondary voltage and frequency control strategy to reduce the number of controller updates by using an event-triggered approach to offset primary control deviations in islanded microgrids with limited computation resources is proposed.
Abstract: This study proposes a cooperative secondary voltage and frequency control strategy to reduce the number of controller updates by using an event-triggered approach. The proposed approach is applied to the secondary control that will offset primary control deviations in islanded microgrids with limited computation resources. The controller updating mechanism considered here is event-triggered which judges whether a certain measurement error has reached the event-triggered condition (ETC) associated with the norm of a function with a standard state. We consider two secondary control options to form an ETC, which include a centralized strategy in which an auxiliary controller would collect all agents’ states, and a distributed control strategy which only require the neighboring agents information. The corresponding stability and convergence analyses are presented and simulation results for an islanded microgrid test system consisting of four distributed generators (DGs) are provided. The simulation results validate the effectiveness of the proposed control strategies and show that the proposed strategies based on an event-triggered approach can dramatically reduce controller updates.
TL;DR: A deep reinforcement learning (DRL)-based EV charging navigation, aiming at minimizing the total travel time and the charging cost at EVCS, and can adaptively learn the optimal strategy without any prior knowledge of uncertainties.
Abstract: A coordinated operation of smart grid (SG) and intelligent transportation system (ITS) provides electric vehicle (EV) owners with a myriad of power and transportation network data for EV charging navigation. However, the optimal charging navigation would be a challenging task owing to the randomness of traffic conditions, charging prices and waiting time at EV charging station (EVCS). In this paper, we propose a deep reinforcement learning (DRL)-based EV charging navigation, aiming at minimizing the total travel time and the charging cost at EVCS. First, we utilize the deterministic shortest charging route model (DSCRM) to extract feature states out of collected stochastic data and then formulate EV charging navigation as a Markov Decision Process (MDP) with an unknown transition probability. The proposed DRL-based approach will approximate the solution, which can adaptively learn the optimal strategy without any prior knowledge of uncertainties. Case studies are carried out within a practical zone in Xi’an city, China. Numerous experimental results verity the effectiveness of the proposed approach and illustrate its adaptation to EV driver preferences. The coordination effect of SG and ITS on reducing the waiting time and the charging cost in EV charging navigations is also analyzed.
TL;DR: A novel peer-to-peer (P2P) market design is proposed in this work for the distribution grid level imagining that the grid constraints violations are the major challenge for P2P energy sharing and these to be handled through the ancillary service (AS) market.
Abstract: A novel peer-to-peer (P2P) market design is proposed in this work for the distribution grid level. Envisioning that the grid constraints violations are the major challenge for P2P energy sharing, we propose these to be handled through the ancillary service (AS) market. By calculating the decomposable distribution locational marginal prices (DLMPs), the essential price signals of procuring ASs can be recovered to determine the grid usage prices (GUPs) to each P2P transaction. Hence, the GUPs, due to their decomposable properties, act as incentive signals for the P2P market to support the grid operation in terms of loss reduction, voltage support and congestion management. The proposed market design comprises i) an interactive market design of P2P trade & AS and, ii) a fully distributed peer-centric market-clearing model for P2P energy trade. The duality analysis provides the composition of market equilibrium prices of P2P trading and their interpretations. The case studies demonstrate the effectiveness of the proposed P2P trade to support grid operational objectives.
TL;DR: In this article, a rolling integrated service restoration strategy is proposed to minimize the total system cost by coordinating the scheduling of MESS fleets, resource dispatching of microgrids, and network reconfiguration of distribution systems.
Abstract: Mobile energy storage systems (MESSs) provide promising solutions to enhance distribution system resilience in terms of mobility and flexibility. This paper proposes a rolling integrated service restoration strategy to minimize the total system cost by coordinating the scheduling of MESS fleets, resource dispatching of microgrids, and network reconfiguration of distribution systems. The integrated strategy takes into account damage and repair to both the roads in transportation networks and the branches in distribution systems. The uncertainties in load consumption and the status of roads and branches are modeled as scenario trees using Monte Carlo simulation method. The operation strategy of MESSs is modeled by a stochastic multi-layer time-space network technique. A rolling optimization framework is adopted to dynamically update system damage, and the coordinated scheduling at each time interval over the prediction horizon is formulated as a two-stage stochastic mixed-integer linear program with temporal–spatial and operation constraints. The proposed model is verified on two integrated test systems, one is with Sioux Falls transportation network and four 33-bus distribution systems, and the other is the Singapore transportation network-based test system connecting six 33-bus distribution systems. The results demonstrate the effectiveness of MESS mobility to enhance distribution system resilience due to the coordination of mobile and stationary resources.
TL;DR: This paper proposes a distribution system restoration model which is in response to multiple outages caused by natural disasters and is presented as a mixed-integer linear program which is solved by an auxiliary induce function based algorithm to reduce the computational complexity.
Abstract: This paper proposes a distribution system restoration model which is in response to multiple outages caused by natural disasters. The proposed restoration model includes the coordination of routing repair crews (RRCs), mobile battery-carried vehicles (MBCVs), and networked microgrids (NMGs) formed by soft open points (SOPs). The travel and repair time constraints are modeled for each RRC; travel path and charging strategy are modeled for each MBCV; and the network reconfiguration is developed considering the optimal operation of SOP-based NMGs. The proposed model is presented as a mixed-integer linear program which is solved by an auxiliary induce function based algorithm to reduce the computational complexity. The modified IEEE 33-bus and 69-bus distribution systems are tested with multiple outages. The presented results demonstrate the effectiveness of the proposed model.
TL;DR: Zhang et al. as discussed by the authors proposed two transfer learning schemes, appliance transfer learning (ATL) and cross-domain transfer learning(CTL), to recover source appliances from only the recorded mains in a household.
Abstract: Non-intrusive load monitoring (NILM) is a technique to recover source appliances from only the recorded mains in a household. NILM is unidentifiable and thus a challenge problem because the inferred power value of an appliance given only the mains could not be unique. To mitigate the unidentifiable problem, various methods incorporating domain knowledge into NILM have been proposed and shown effective experimentally. Recently, among these methods, deep neural networks are shown performing best. Arguably, the recently proposed sequence-to-point (seq2point) learning is promising for NILM. However, the results were only carried out on the same data domain. It is not clear if the method could be generalised or transferred to different domains, e.g., the test data were drawn from a different country comparing to the training data. We address this issue in the paper, and two transfer learning schemes are proposed, i.e., appliance transfer learning (ATL) and cross-domain transfer learning (CTL). For ATL, our results show that the latent features learnt by a ‘complex’ appliance, e.g., washing machine, can be transferred to a ‘simple’ appliance, e.g., kettle. For CTL, our conclusion is that the seq2point learning is transferable. Precisely, when the training and test data are in a similar domain, seq2point learning can be directly applied to the test data without fine tuning; when the training and test data are in different domains, seq2point learning needs fine tuning before applying to the test data. Interestingly, we show that only the fully connected layers need fine tuning for transfer learning. Source code can be found at https://github.com/MingjunZhong/transferNILM .
TL;DR: A numerical method to identify the topology and estimate line parameters without the information of voltage angles is proposed and can provide an accurate estimation of the topological and line parameters based on limited samples of measurement without voltage angles.
Abstract: The energy management system becomes increasingly indispensable with the extensive penetration of new players in the distribution networks, such as renewable energy, storage, and controllable load. Also, the operation optimization of the active distribution system requires information on operation state monitoring. Smart measuring equipment enables the topology identification and branch line parameters estimation from a data-driven perspective. Nevertheless, many current methods require the nodal voltage angles measured by phasor measurement units (PMUs), which might be unrealistic for conventional distribution networks. This paper proposes a numerical method to identify the topology and estimate line parameters without the information of voltage angles. We propose a two-step framework: the first step applies a data-driven regression method to provide a preliminary estimation on the topology and line parameter; the second step utilizes a joint data-and-model-driven method, i.e., a specialized Newton-Raphson iteration and power flow equations, to calculate the line parameter, recover voltage angle and further correct the topology. We test the method on IEEE 33 and 123-bus looped networks with load data from 1000 users in Ireland. The results demonstrate that the proposed method can provide an accurate estimation of the topology and line parameters based on limited samples of measurement without voltage angles.
TL;DR: This paper presents a practical and effective non-intrusive load monitoring (NILM) solution to estimate the energy consumption for common multi-functional home appliances (type II appliances) that includes a novel post-processing technique that boost the performance significantly on type II home appliances.
Abstract: This paper presents a practical and effective non-intrusive load monitoring (NILM) solution to estimate the energy consumption for common multi-functional home appliances (type II appliances). Type II home appliances are usually the most challenging cases in load disaggregation because they usually have multiple power consumption states, complex state transitions, and multiple operational modes. The practicality of the proposed deep convolutional neural networks-based approach comes from the minimum prerequisite information from the previously unseen customers. That means no sub-metered information for the target appliances in the NILM service subscriber’s house is needed to provide appliance level identification and estimate under the proposed architecture. Our solution also includes a novel post-processing technique that boost the performance significantly on type II home appliances. The effectiveness of the solution is evaluated on a public dataset to allow comparison with the previous works.
TL;DR: In the proposed approach, an approximate optimal policy based on neural network is designed to learn the optimal DR scheduling strategy and can directly learn from high-dimensional sensory data of the appliance states, real-time electricity price, and outdoor temperature.
Abstract: This paper presents a real-time demand response (DR) strategy for optimal scheduling of home appliances. The uncertainty of the resident’s behavior, real-time electricity price, and outdoor temperature is considered. An efficient DR scheduling algorithm based on deep reinforcement learning (DRL) is proposed. Unlike traditional model-based approaches, the proposed approach is model-free and does not need to know the distribution of the uncertainty. Besides, unlike conventional RL-based methods, the proposed approach can handle both discrete and continuous actions to jointly optimize the schedules of different types of appliances. In the proposed approach, an approximate optimal policy based on neural network is designed to learn the optimal DR scheduling strategy. The neural network based policy can directly learn from high-dimensional sensory data of the appliance states, real-time electricity price, and outdoor temperature. A policy search algorithm based upon trust region policy optimization (TRPO) is used to train the neural network. The effectiveness of our proposed approach is validated by simulation studies where the real-world electricity price and outdoor temperature are used.
TL;DR: A single-input–single-output model is developed to explicitly reveal how the PLL interacts with the other parts of the converter system in terms of grid synchronization and demonstrates how the loop shaping of PLL takes effect in increasing the stability margin and eventually preventing the converter from GSI.
Abstract: Power converters may lose synchronization with the remaining network when integrated in a weak power grid. Such an instability phenomenon [known as grid-synchronization instability (GSI)] features the frequency divergence of phase-locked loop (PLL) and oscillations of the converter’s power output. In this paper, we focus on the influences of reactive power control (RPC) methods on GSI. We develop a single-input–single-output model to explicitly reveal how the PLL interacts with the other parts of the converter system in terms of grid synchronization. Then, after deriving the open-loop transfer function and sensitivity function of the entire converter system, we compare the stability margins for different RPC methods. Furthermore, we elaborate on the interactions among RPC, PLL, and voltage feedforward (VFF), and then demonstrate that different design methods of RPC and VFF will lead to different stability margins. The subsequent stability analysis provides insightful guidelines for coordinating the design of multiple control loops, i.e., RPC, VFF, and PLL. In particular, we demonstrate how the loop shaping of PLL takes effect in increasing the stability margin and eventually preventing the converter from GSI. The validity of the stability analysis is verified through simulations in MATLAB/Simulink.
TL;DR: This paper proposes a control strategy that includes a linear voltage controller with capacitor current feedback as an input to the voltage controller, and modified droop control to emulate the inertia response of a synchronous generator to achieve a smooth transition to islanding mode and mitigate disturbance effect.
Abstract: One of the main features of Microgrids is the ability to operate in both grid-connected mode and islanding mode. In each mode of operation, distributed energy resources (DERs) can be operated under grid-forming or grid-following control strategies. In grid-connected mode, DERs usually work under grid-following control strategy, while at least one of the DERs must operate in grid-forming strategy in islanding mode. A microgrid may experience remarkable fluctuations in voltage and current due to an unintentional islanding event. To achieve a smooth transition to islanding mode and mitigate disturbance effect, this paper proposes a control strategy includes a) a linear voltage controller with capacitor current feedback as an input to the voltage controller and output current feedforward as an input to current controller, and b) modified droop control to emulate the inertia response of a synchronous generator. The proposed controller can suppress voltage, current and frequency fluctuations and also guarantee a smooth transition. A small signal analysis of the proposed control strategy is developed to design its coefficients as well as the destabilizing effect of constant power load (CPL). Experimental results are provided to verify the effectiveness of the proposed control strategy.
TL;DR: The proposed line impedance cooperative stability region identification method is more effective and less conservative than the norm-based stability criteria and can provide guidance for system planning and stabilization method researches with simplified computational process.
Abstract: Although the low-frequency/harmonic oscillation of grid-tied inverters under weak grids has been widely researched, the classical impedance-based approach focuses more on the identification of stable operating points and the stability margin of return-ratio matrix. Furthermore, it cannot provide stability regions of system parameters. Therefore, this paper proposes a line impedance cooperative stability region identification method. Firstly, the output impedance matrix and the input admittance matrix are respectively built in $d-q$ axis. Secondly, a novel stability forbidden region is proposed. It is less conservative than the forbidden region criteria in existing literatures. Based on the stability forbidden region, the stability operation region is established via mirror, translation and rotation mappings. It is less conservative compared with the norm-based stability criteria. The solving of stability operation region is first transformed into the eigenvalue identification problem in this paper. Furthermore, the detailed line impedance cooperative stability region is solved by guardian map theory. It can provide guidance for system planning and stabilization method researches with simplified computational process. Finally, the simulation and experimental results show that the proposed line impedance cooperative stability region identification method is more effective and less conservative.
TL;DR: Investigation of electricity thefts at the distributed generation domain revealed that integrating various data from the DG smart meters, meteorological reports, and SCADA metering points in the training of a deep convolutional-recurrent neural network offers the highest detection rate and lowest false alarm.
Abstract: Unlike the existing research that focuses on detecting electricity theft cyber-attacks in the consumption domain, this paper investigates electricity thefts at the distributed generation (DG) domain. In this attack, malicious customers hack into the smart meters monitoring their renewable-based DG units and manipulate their readings to claim higher supplied energy to the grid and hence falsely overcharge the utility company. Deep machine learning is investigated to detect such a malicious behavior. We aim to answer three main questions in this paper: a) What are the cyber-attack functions that can be applied by malicious customers to the generation data in order to falsely overcharge the utility company? b) What sources of data can be used in order to detect these cyber-attacks by the utility company? c) Which deep machine learning-model should be used in order to detect these cyber-attacks? Our investigation revealed that integrating various data from the DG smart meters, meteorological reports, and SCADA metering points in the training of a deep convolutional-recurrent neural network offers the highest detection rate (99.3%) and lowest false alarm (0.22%).
TL;DR: This paper presents a new and fair peer-to-peer energy sharing framework to realize an economic and sustainable building community, and proposes a non-cooperative energy sharing game for the selfish buildings.
Abstract: With the rapid development of energy buildings, advanced energy management is urgently demanded for a green society. In this paper, focusing on the coordinated energy management for a building community, we present a new and fair peer-to-peer energy sharing framework to realize an economic and sustainable building community. Specifically, in the building-centric peer-to-peer mode, buildings directly share their energy supplies/demands and offer the related payments within the community under the constraints of community energy and payment balance. We propose a non-cooperative energy sharing game for the selfish buildings, and we further show that a generalized Nash equilibrium of the game is independent of the energy sharing payments. Consequently, we firstly derive the energy sharing profiles by seeking the equilibrium. Since the buildings’ energy sharing payments are mutually coupled and influenced, we propose a cost reduction ratio distribution model to determine the payments to ensure the fairness in the sense that buildings can get as large cost reductions and similar cost reduction ratios as possible. Simulation results show that all buildings can reduce their energy costs and have smoother and smaller net demand profiles on the main grid, thus making the proposed schemes and algorithms promising in real applications.