This page has only limited features, please log in for full access.
Multi-microgrids (MMGs) interconnect microgirds (MGs) with geographical adjacency and improve the overall efficiency, stability, and reliability of a regional energy system. The uncertainty brought by renewable energy resources (RESs) is one of the challenges facing the schedule of MMGs. To cope with it, a multi-timescale schedule strategy is proposed. Specifically, in day-ahead schedule, the on/off states of the units are determined. Then, based on the day-ahead plan and the more accurate estimation of RESs, the refined schedule is achieved in the intraday. And to enhance the flexibility of the MMGs system, multienergy complementarity is considered in this work. Moreover, how to achieve the coordinated schedule between MGs owned by different parties is another problem facing the MMGs system operation. To solve this, a distributed algorithm, namely predictor corrector proximal multiplier, is introduced. During the solution process, each MG only needs to reveal the exchange power to the virtual controller, which protects the privacy and reduces communication burden. Numerical simulation of an MMGs system with four MGs is carried out. The results show that the proposed distributed method has good convergence performance. Besides, the absolute relative differences of objective function results obtained using the proposed method with the centralized counterpart are less than 2% in the day-ahead timescale and which can be less than 0.08% in the intraday timescale. Therefore, the economy and flexibility of the system can be achieved.
Zhaoyu Li; Qian Ai; Yufan Zhang. A multi‐timescale schedule strategy for multi‐microgrids: A distributed approach. International Transactions on Electrical Energy Systems 2021, e12994 .
AMA StyleZhaoyu Li, Qian Ai, Yufan Zhang. A multi‐timescale schedule strategy for multi‐microgrids: A distributed approach. International Transactions on Electrical Energy Systems. 2021; ():e12994.
Chicago/Turabian StyleZhaoyu Li; Qian Ai; Yufan Zhang. 2021. "A multi‐timescale schedule strategy for multi‐microgrids: A distributed approach." International Transactions on Electrical Energy Systems , no. : e12994.
In this study a novel cooperative controller design is developed to tackle the consensus tracking problem of Multi-Agent systems (MAS) based on multilayer perceptron neural network (MLPNN), applied on a distributed synchronous generator (SG) Multi-Agent system in presence of model uncertainties and external disturbances. Application of MLPNN in controller design can lead to smoother system response and can neutralize the impacts of model uncertainties. Furthermore, the proposed method benefits from a novel algorithm formerly known as error backpropagation (BP) algorithm to update and to regulate the weights of MLPNN adaptively based on the principles of consensus error. The proposed strategy can be very effective in control of the distributed SG Multi-Agent system due to its ability for system identification, parameter estimation, and disturbance approximation. Moreover, the utilization of neural networks can meet the criterion to make the consensus error uniformly ultimately bounded. Ultimately, simulation results illustrate the applicability and effectiveness of the novel MLPNN controller to model the system uncertainties and to deal with external disturbances of the distributed SG Multi-Agent system.
Alireza Sharifi; Amin Sharafian; Qian Ai. Adaptive MLP neural network controller for consensus tracking of Multi-Agent systems with application to synchronous generators. Expert Systems with Applications 2021, 184, 115460 .
AMA StyleAlireza Sharifi, Amin Sharafian, Qian Ai. Adaptive MLP neural network controller for consensus tracking of Multi-Agent systems with application to synchronous generators. Expert Systems with Applications. 2021; 184 ():115460.
Chicago/Turabian StyleAlireza Sharifi; Amin Sharafian; Qian Ai. 2021. "Adaptive MLP neural network controller for consensus tracking of Multi-Agent systems with application to synchronous generators." Expert Systems with Applications 184, no. : 115460.
Under the digitalization trend in the energy sector, utilities are devoted to providing better service to their customers by mining knowledge in fine-grained electricity consumption data. Understanding the group behaviour of customers by clustering method is essential to achieving this end. Different from shape-based clustering methods, an f-divergence based hierarchical clustering model is proposed to group customers by their dynamic electricity consumption patterns. Modelling the electricity consumption by Markov chains, the customers’ consumption patterns are first summarized into transition probability matrixes. Then, dissimilarity measures based on f-divergence are calculated. Specifically, due to their superiority, squared Hellinger distance and total variation distance are used. The hierarchical clustering is then conducted based on the obtained distance matrixes. Using real-world smart meter dataset, the proposed method is compared with other dynamic clustering candidates by using the revised silhouette score. And consumers’ dynamic consumption patterns are not only analysed from the global to local levels, but also the relationship between clustering results and external factors are delved into. The results show that the proposed method can produce highly representative clusters, and is able to provide insights on the implementation of the demand-side management program.
Yufan Zhang; Qian Ai; Zhaoyu Li. Grouping of dynamic electricity consumption behaviour: An f ‐divergence based hierarchical clustering model. IET Generation, Transmission & Distribution 2021, 1 .
AMA StyleYufan Zhang, Qian Ai, Zhaoyu Li. Grouping of dynamic electricity consumption behaviour: An f ‐divergence based hierarchical clustering model. IET Generation, Transmission & Distribution. 2021; ():1.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Zhaoyu Li. 2021. "Grouping of dynamic electricity consumption behaviour: An f ‐divergence based hierarchical clustering model." IET Generation, Transmission & Distribution , no. : 1.
This paper considers the problem of distributed online economic dispatch (DOED) from sequential data using reinforcement learning. Learning operation behavior in high-dimension environments with constraints is a major challenge for the DOED of networked microgrids (MGs), where insufficient exploration disables agents to build complex policies. Therefore, this paper develops a hierarchical reinforcement learning (HRL) to handle the DOED problem, where radial basis function (RBF) approximation is incorporated to make policies in continuous space. Based on the hierarchical framework, the HRL algorithm increases the training efficiency and reduces computational cost. The online HRL achieves distributed selfadaption and better performance of real-time dispatch by a modest number of interacting variables. In addition, guided by domain knowledge, the HRL algorithm avoids onerous additional learning beyond feasible action space. In the case of an actual networked MGcluster in Qingdao with real operation data, simulation is conducted to verify that the proposed learning framework can reduce longterm operation costs and enhance operation stability. To explore the learning process, we also provide its convergence condition andanalyze the sensitivity of the learning parameters.
Ran Hao; Tianguang Lu; Qian Ai; Hongying He. Distributed Online Dispatch For Microgrids Using Hierarchical Reinforcement Learning Embedded With Operation Knowledge. IEEE Transactions on Power Systems 2021, PP, 1 -1.
AMA StyleRan Hao, Tianguang Lu, Qian Ai, Hongying He. Distributed Online Dispatch For Microgrids Using Hierarchical Reinforcement Learning Embedded With Operation Knowledge. IEEE Transactions on Power Systems. 2021; PP (99):1-1.
Chicago/Turabian StyleRan Hao; Tianguang Lu; Qian Ai; Hongying He. 2021. "Distributed Online Dispatch For Microgrids Using Hierarchical Reinforcement Learning Embedded With Operation Knowledge." IEEE Transactions on Power Systems PP, no. 99: 1-1.
Integrated energy system (IES) is a viable and effective solution for improving energy utilization efficiency and promoting renewable penetration via aggregating independent systems into an integrated management scheme. The water system management problem has been widely investigated. However, the interdependencies between water and energy systems are significant and the effective co-optimization is required considering strong interconnections. This paper proposes a two-stage distributionally robust operation model for integrated water-energy nexus systems (IWENS) including power, gas and water systems networked with energy hub systems at a distribution level considering wind uncertainty. The presence of wind power uncertainty inevitably leads to risks in the optimization model. Accordingly, a coherent risk measure, i.e., conditional value-at-risk, is combined with the optimization objective to determine risk-averse operation schemes. This two-stage mean-risk distributionally robust optimization is solved by Bender's decomposition method. Both the day-ahead and real-time operation cost are minimized with an optimal set of scheduling the multi-energy infrastructures. Case studies focus on investigating the strong interdependencies among the four interconnected energy systems. The proposed model can provide system operators a powerful two-stage operation scheme to minimise operation cost under water-energy nexus considering risk caused by renewable uncertainties, thus benefiting customers with lower utility bill
Pengfei Zhao; Chenghong Gu; Zhidong Cao; Qian Ai; Yue Xiang; Tao Ding; Xi Lu; Xinlei Chen; Shuangqi Li. Water-Energy Nexus Management for Power Systems. IEEE Transactions on Power Systems 2021, 36, 2542 -2554.
AMA StylePengfei Zhao, Chenghong Gu, Zhidong Cao, Qian Ai, Yue Xiang, Tao Ding, Xi Lu, Xinlei Chen, Shuangqi Li. Water-Energy Nexus Management for Power Systems. IEEE Transactions on Power Systems. 2021; 36 (3):2542-2554.
Chicago/Turabian StylePengfei Zhao; Chenghong Gu; Zhidong Cao; Qian Ai; Yue Xiang; Tao Ding; Xi Lu; Xinlei Chen; Shuangqi Li. 2021. "Water-Energy Nexus Management for Power Systems." IEEE Transactions on Power Systems 36, no. 3: 2542-2554.
Demand response(DR) has become an effective means to deal with renewable energy integration and load fluctuations in the power system. This article first analyzes the classification and characteristics of controllable resources used in DR. Secondly, taking into consideration the transferable load, interruptible load and the energy storage system in DR, an intra-day scheduling model is then established based on safety constraints. Finally, a case is studied to analyze the role of DR in improving system safety and reducing operating costs. Results show the effectiveness of this model.
Ziru Sun; Minyu Chen; Qian Ai; Long Zhao; XiaoMing Liu; Donglei Sun. An Optimization Strategy for Intra-day Demand Response Based on Security Constraints. Journal of Physics: Conference Series 2021, 1754, 012211 .
AMA StyleZiru Sun, Minyu Chen, Qian Ai, Long Zhao, XiaoMing Liu, Donglei Sun. An Optimization Strategy for Intra-day Demand Response Based on Security Constraints. Journal of Physics: Conference Series. 2021; 1754 (1):012211.
Chicago/Turabian StyleZiru Sun; Minyu Chen; Qian Ai; Long Zhao; XiaoMing Liu; Donglei Sun. 2021. "An Optimization Strategy for Intra-day Demand Response Based on Security Constraints." Journal of Physics: Conference Series 1754, no. 1: 012211.
With the liberalization of the retail market, new parties such as load aggregators are participating in the demand response (DR). Aggregated baseline load (ABL) estimation provides a basis for aggregators to quantify the total responsiveness. This paper aims to improve the ABL estimation accuracy by using Gaussian mixture model (GMM). Modeling the distribution of consumption patterns by Gaussian distributions, GMM first divides the customers into several groups. Then, support vector regression (SVR) is utilized to estimate the baseline load over each group. And the estimated loads are summed up to form the final result. We make comprehensive comparisons in the case study. The results prove that the proposed method can improve the ABL estimation accuracy. And it is better than similar day, exponential moving average, and other regression model-based estimation methods.
Yufan Zhang; Qian Ai; Zhaoyu Li. Improving aggregated baseline load estimation by Gaussian mixture model. Energy Reports 2020, 6, 1221 -1225.
AMA StyleYufan Zhang, Qian Ai, Zhaoyu Li. Improving aggregated baseline load estimation by Gaussian mixture model. Energy Reports. 2020; 6 ():1221-1225.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Zhaoyu Li. 2020. "Improving aggregated baseline load estimation by Gaussian mixture model." Energy Reports 6, no. : 1221-1225.
Interaction between microgrid (MG) and active distribution network (ADN) can effectively improve the operating economics and reliability of power system. A bi-level interactive optimization model for ADN with MGs is studied in this paper. The upper level is a multi-objective problem that minimizes both the operation cost and voltage deviation of each node. The lower level aims to minimize the operation cost of MG. The interaction between adjacent MGs ensures a relatively lower electricity price. To achieve a low-carbon system, carbon trading cost is also considered at both levels. And the model is decoupled into several subproblems and solved using a distributed method. Therefore, the privacy of each entity is ensured. The results prove the effectiveness of the proposed method.
Zhaoyu Li; Hao Wang; Qian Ai; Yufan Zhang. Interactive optimization between active distribution network with multi-microgrids based on distributed algorithm. Energy Reports 2020, 6, 385 -391.
AMA StyleZhaoyu Li, Hao Wang, Qian Ai, Yufan Zhang. Interactive optimization between active distribution network with multi-microgrids based on distributed algorithm. Energy Reports. 2020; 6 ():385-391.
Chicago/Turabian StyleZhaoyu Li; Hao Wang; Qian Ai; Yufan Zhang. 2020. "Interactive optimization between active distribution network with multi-microgrids based on distributed algorithm." Energy Reports 6, no. : 385-391.
With the wide deployment of smart meters in the end-user side, demand response (DR) is gaining prominence. Estimating the potential response is a preliminary step to the DR implementation. However, how to select proper features, how to protect privacy, and how to capture the response uncertainty remains three challenges to the customer response potential estimation. This study provides a detailed response quantity estimation for each customer. The authors proposed a probabilistic response quantity estimation framework and solved the problem by alternating direction method of multipliers (ADMM) in a fully-distributed way. In particular, by utilising a similar consumption pattern matching principle, the feature for each DR day of each customer is selected based on the matched DR participants. Then, the pinball loss-guided ridge regression is formulated, so the quantiles are obtained to cope with the uncertainty. The training process can be solved by each customer at the local site in a fully-distributed way, which protects the privacy and reduces the centralised processing burden. Finally, in the case study, the assumption behind a similar consumption pattern matching principle is validated empirically. Also, the proposed method is confirmed to have good convergence performance and can produce reasonable estimation results.
Yufan Zhang; Qian Ai; Zhaoyu Li. ADMM‐based distributed response quantity estimation: a probabilistic perspective. IET Generation, Transmission & Distribution 2020, 14, 6594 -6602.
AMA StyleYufan Zhang, Qian Ai, Zhaoyu Li. ADMM‐based distributed response quantity estimation: a probabilistic perspective. IET Generation, Transmission & Distribution. 2020; 14 (26):6594-6602.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Zhaoyu Li. 2020. "ADMM‐based distributed response quantity estimation: a probabilistic perspective." IET Generation, Transmission & Distribution 14, no. 26: 6594-6602.
With the development of deregulated retail power markets, it is possible for end users equipped with smart meters and controllers to optimize their consumption cost portfolios by choosing various pricing plans from different retail electricity companies. This paper proposes a reinforcement learning-based decision system for assisting the selection of electricity pricing plans, which can minimize the electricity payment and consumption dissatisfaction for individual smart grid end user. The decision problem is modeled as a transition probability-free Markov decision process (MDP) with improved state framework. The proposed problem is solved using a Kernel approximator-integrated batch Q-learning algorithm, where some modifications of sampling and data representation are made to improve the computational and prediction performance. The proposed algorithm can extract the hidden features behind the time-varying pricing plans from a continuous high-dimensional state space. Case studies are based on data from real-world historical pricing plans and the optimal decision policy is learned without a priori information about the market environment. Results of several experiments demonstrate that the proposed decision model can construct a precise predictive policy for individual user, effectively reducing their cost and energy consumption dissatisfaction.
Tianguang Lu; Xinyu Chen; Michael B. McElroy; Chris P. Nielsen; Qiuwei Wu; Qian Ai. A Reinforcement Learning-Based Decision System for Electricity Pricing Plan Selection by Smart Grid End Users. IEEE Transactions on Smart Grid 2020, 12, 2176 -2187.
AMA StyleTianguang Lu, Xinyu Chen, Michael B. McElroy, Chris P. Nielsen, Qiuwei Wu, Qian Ai. A Reinforcement Learning-Based Decision System for Electricity Pricing Plan Selection by Smart Grid End Users. IEEE Transactions on Smart Grid. 2020; 12 (3):2176-2187.
Chicago/Turabian StyleTianguang Lu; Xinyu Chen; Michael B. McElroy; Chris P. Nielsen; Qiuwei Wu; Qian Ai. 2020. "A Reinforcement Learning-Based Decision System for Electricity Pricing Plan Selection by Smart Grid End Users." IEEE Transactions on Smart Grid 12, no. 3: 2176-2187.
Topology identification is a key task for SE in distribution grids, especially the one with high-penetration renewables. The renewables-derived uncertainties, without a proper treatment, will almost certainly lead to bad TI results. These uncertainties are analytically intractable under conventional framework--they are usually jointly spatial-temporal dependent, and hence cannot be simply treated as white noise. For this purpose, a hybrid framework is suggested to handle these uncertainties in a systematic and theoretical way; in particular big data analytics are studied to harness the jointly spatial-temporal statistical properties of those randomness. With some prior knowledge, a model bank is built first to store the countable typical models of network configurations. And thus the difference is capable of being defined as a random matrix. In order to gain insight into the random matrix, AR model, FA, and RMT are tied together for the metric space design, followed by jointly temporal-spatial analysis of those matrices which is conducted in a high-dimensional (vector) space. Under the proposed framework, some big data analytics and theoretical results are obtained as a by-product to improve the TI performance. Our framework is validated using IEEE standard distribution network with some field data in practice.
Xing He; Robert C. Qiu; Qian Ai; Tianyi Zhu. A Hybrid Framework for Topology Identification of Distribution Grid With Renewables Integration. IEEE Transactions on Power Systems 2020, 36, 1493 -1503.
AMA StyleXing He, Robert C. Qiu, Qian Ai, Tianyi Zhu. A Hybrid Framework for Topology Identification of Distribution Grid With Renewables Integration. IEEE Transactions on Power Systems. 2020; 36 (2):1493-1503.
Chicago/Turabian StyleXing He; Robert C. Qiu; Qian Ai; Tianyi Zhu. 2020. "A Hybrid Framework for Topology Identification of Distribution Grid With Renewables Integration." IEEE Transactions on Power Systems 36, no. 2: 1493-1503.
In this paper, a novel energy pricing and sharing strategy is proposed to solve the energy management and market bidding problems of a virtual energy station (VES) in multi-carrier energy systems. First, the energy cell-tissue-based group interaction framework and the multiagent-based communication and control architecture are established in the VES. Second, the general model of an energy cell is built, in which the integrated demand response process and the automatic generation control mode of a combined heat and power unit are designed. Third, according to the classification of energy cells, the aggregation rules of the VES without the participation of third-party agents are proposed, and the internal trading mechanism of the VES led by a higher energy cell is designed based on a Stackelberg game. Moreover, a three-stage hybrid stochastic robust optimization strategy is proposed to address uncertainties in market prices and renewable energy output. Finally, the optimization model is linearized and solved by duality theory, KKT conditions, and column-and-constraint generation (CC&G) algorithm. Simulation results prove the rationality and effectiveness of the framework and business model for the VES.
Shuangrui Yin; Qian Ai; Jiamei Li; Zhaoyu Li; Songli Fan. Energy Pricing and Sharing Strategy Based on Hybrid Stochastic Robust Game Approach for a Virtual Energy Station With Energy Cells. IEEE Transactions on Sustainable Energy 2020, 12, 772 -784.
AMA StyleShuangrui Yin, Qian Ai, Jiamei Li, Zhaoyu Li, Songli Fan. Energy Pricing and Sharing Strategy Based on Hybrid Stochastic Robust Game Approach for a Virtual Energy Station With Energy Cells. IEEE Transactions on Sustainable Energy. 2020; 12 (2):772-784.
Chicago/Turabian StyleShuangrui Yin; Qian Ai; Jiamei Li; Zhaoyu Li; Songli Fan. 2020. "Energy Pricing and Sharing Strategy Based on Hybrid Stochastic Robust Game Approach for a Virtual Energy Station With Energy Cells." IEEE Transactions on Sustainable Energy 12, no. 2: 772-784.
Distributed energy management of multi-microgrids (MMGs) system is essential to achieving energy coordination in a large area while protecting the privacy. Compared with existing work, we consider the detailed modeling of demand-side resources and aim to reduce carbon emission. Concretely, we propose a bi-level distributed day-ahead schedule model for the islanded MMGs under a carbon trading market. The upper level minimizes the operation and carbon trading cost of the cluster. The nonlinear power flow constraints are relaxed by second order cone constraints. The distributed modeling method for the introduced variables is proposed on the basis of the tie lines splitting method, and the upper level model is solved by alternating direction method of multipliers (ADMM); the lower level is a mixed-integer linear programming (MILP) problem and aims to achieve the self-organizing of each microgrid (MG). During the iteration, each MG communicates with its neighbors and solves the problem separately, which protects the privacy and reduces the communication burden. Finally, a case study of the MMGs with four MGs is carried out. The proposed method is confirmed to have good convergence performance and can produce reasonable results. And the effect of the carbon trading price on the system is analyzed.
Yufan Zhang; Qian Ai; Hao Wang; Zhaoyu Li; Kaiyi Huang. Bi-level distributed day-ahead schedule for islanded multi-microgrids in a carbon trading market. Electric Power Systems Research 2020, 186, 106412 .
AMA StyleYufan Zhang, Qian Ai, Hao Wang, Zhaoyu Li, Kaiyi Huang. Bi-level distributed day-ahead schedule for islanded multi-microgrids in a carbon trading market. Electric Power Systems Research. 2020; 186 ():106412.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Hao Wang; Zhaoyu Li; Kaiyi Huang. 2020. "Bi-level distributed day-ahead schedule for islanded multi-microgrids in a carbon trading market." Electric Power Systems Research 186, no. : 106412.
With the fast development of industrial Internet of Things (IoT) for smart energy, data processing and storing are closer to the end used side. Edge data center, an intermediate platform between end data source and centralized data center, can reduce the data transmission pressure and processing time. To provide dependable data source for decision making and to reduce property loss, energy theft detection is important to an edge data center. In this work, we propose a threshold-based abnormality detector for energy theft detection in an edge data center. The framework includes training feature extractor based on VAE-GAN, implementing k-means clustering to determine the representative features of normal load profiles, and finally formulating a threshold-based abnormality detector based on defined abnormality degree. We demonstrate that when VAE-GAN converges, it can grasp the temporal relationship and statistical distribution of real data. The encoder of VAE-GAN has good feature extraction performance and the distribution of normal and abnormal data can be easily separated. Also, we prove that the proposed feature representation is better than the feature extracted by other advanced feature extractors. By comparison with state-of-the-art detection models, the proposed detector is more computationally efficient and robust against the attack type changes.
Yufan Zhang; Qian Ai; Hao Wang; Zhaoyu Li; Xiaoqian Zhou. Energy theft detection in an edge data center using threshold-based abnormality detector. International Journal of Electrical Power & Energy Systems 2020, 121, 106162 .
AMA StyleYufan Zhang, Qian Ai, Hao Wang, Zhaoyu Li, Xiaoqian Zhou. Energy theft detection in an edge data center using threshold-based abnormality detector. International Journal of Electrical Power & Energy Systems. 2020; 121 ():106162.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Hao Wang; Zhaoyu Li; Xiaoqian Zhou. 2020. "Energy theft detection in an edge data center using threshold-based abnormality detector." International Journal of Electrical Power & Energy Systems 121, no. : 106162.
Numerous underlying causes of power-quality (PQ) disturbances have enhanced the application of situational awareness to power systems. This application provides an optimal overall response for contingencies. With measurement data acquired by a multi-source PQ monitoring system, we propose an interactive visualization tool for PQ disturbance data based on a geographic information system (GIS). This tool demonstrates the spatio–temporal distribution of the PQ disturbance events and the cross-correlation between PQ records and environmental factors, leveraging Getis statistics and random matrix theory. A methodology based on entity matching is also introduced to analyze the underlying causes of PQ disturbance events. Based on real-world data obtained from an actual power system, offline and online PQ data visualization scenarios are provided to verify the effectiveness and robustness of the proposed framework.
Fei Xiao; Tianguang Lu; Qian Ai; Xiaolong Wang; Xinyu Chen; Sidun Fang; Qiuwei Wu. Design and Implementation of a Data-Driven Approach to Visualizing Power Quality. IEEE Transactions on Smart Grid 2020, 11, 4366 -4379.
AMA StyleFei Xiao, Tianguang Lu, Qian Ai, Xiaolong Wang, Xinyu Chen, Sidun Fang, Qiuwei Wu. Design and Implementation of a Data-Driven Approach to Visualizing Power Quality. IEEE Transactions on Smart Grid. 2020; 11 (5):4366-4379.
Chicago/Turabian StyleFei Xiao; Tianguang Lu; Qian Ai; Xiaolong Wang; Xinyu Chen; Sidun Fang; Qiuwei Wu. 2020. "Design and Implementation of a Data-Driven Approach to Visualizing Power Quality." IEEE Transactions on Smart Grid 11, no. 5: 4366-4379.
Short‐term load forecasting at the distribution transformer level provides a basis for demand‐side aggregators to take part in the power market. However, under the competitive market environment, certain parties might be discriminated and do not have access to enough data and thus the challenge of load forecasting under limited dataset arises. To tackle the small sample forecasting problem at the distribution transformer level, this paper first explores the load unbalance phenomenon and correlation among three‐phase electrical loads. Then, the data augmentation strategy for learning models is proposed. The strategy includes three‐phase datasets fusion and rolling forecast. The aim is to ameliorate overfitting and make sure the distribution of the training and test data as close as possible. The strategy is validated by the realistic data of the distribution transformers from South and East China. Comprehensive case studies demonstrate that, by utilizing the proposed strategy, learning models can achieve better forecast accuracy and the generalization ability is improved. Also, the proposed strategy is proved to boost robustness against the measurement uncertainty.
Yufan Zhang; Qian Ai; Zhaoyu Li; Shuangrui Yin; Kaiyi Huang; Muhammad Yousif; Tianguang Lu. Data augmentation strategy for small sample short‐term load forecasting of distribution transformer. International Transactions on Electrical Energy Systems 2019, 30, 1 .
AMA StyleYufan Zhang, Qian Ai, Zhaoyu Li, Shuangrui Yin, Kaiyi Huang, Muhammad Yousif, Tianguang Lu. Data augmentation strategy for small sample short‐term load forecasting of distribution transformer. International Transactions on Electrical Energy Systems. 2019; 30 (7):1.
Chicago/Turabian StyleYufan Zhang; Qian Ai; Zhaoyu Li; Shuangrui Yin; Kaiyi Huang; Muhammad Yousif; Tianguang Lu. 2019. "Data augmentation strategy for small sample short‐term load forecasting of distribution transformer." International Transactions on Electrical Energy Systems 30, no. 7: 1.
In this paper, a novel two-stage robust Stackelberg game is proposed to solve the problem of day-ahead energy management for aggregate prosumers considering the uncertainty of intermittent renewable energy output and market price. The aggregate prosumers operate in the form of virtual power plant (VPP) and participate in day-ahead (DA) and real-time (RT) market transactions. As the initiator and leader of the VPP, the superior prosumer with thermal units and interruptible loads is responsible for formulating the internal price mechanism and energy management strategy of the aggregate prosumers. Inferior prosumers, including renewable energy and shiftable loads, are responsible for providing renewable energy output information and responding to the price signals from the superior prosumer. The two-stage robust Stackelberg game model is linearized and solved by column-and-constraint generation (CC&G) algorithm. In addition, the thermal unit operating in the automatic generation control (AGC) mode ensures the realization of real-time optimal scheduling of aggregate prosumers for the entire dispatching cycle. Simulation results prove the rationality and validity of the proposed model and method.
Shuangrui Yin; Qian Ai; Zhaoyu Li; Yufan Zhang; Tianguang Lu. Energy management for aggregate prosumers in a virtual power plant: A robust Stackelberg game approach. International Journal of Electrical Power & Energy Systems 2019, 117, 105605 .
AMA StyleShuangrui Yin, Qian Ai, Zhaoyu Li, Yufan Zhang, Tianguang Lu. Energy management for aggregate prosumers in a virtual power plant: A robust Stackelberg game approach. International Journal of Electrical Power & Energy Systems. 2019; 117 ():105605.
Chicago/Turabian StyleShuangrui Yin; Qian Ai; Zhaoyu Li; Yufan Zhang; Tianguang Lu. 2019. "Energy management for aggregate prosumers in a virtual power plant: A robust Stackelberg game approach." International Journal of Electrical Power & Energy Systems 117, no. : 105605.
Invisible units mainly refer to small-scale units that are not monitored by, and thus are not visible to utilities. Integration of these invisible units into power systems does significantly affect the way in which a distribution grid is planned and operated. This paper, based on random matrix theory (RMT), proposes a statistical, data-driven framework to handle the massive grid data, in contrast to its deterministic, model-based counterpart. Combining the RMT-based data-mining framework with conventional techniques, some heuristics are derived as the solution to the invisible units detection and estimation task: linear eigenvalue statistic indicators (LESs) are suggested as the main ingredients of the solution; according to the statistical properties of LESs, the hypothesis testing is formulated to conduct change point detection in the high-dimensional space. The proposed method is promising for anomaly detection and pertinent to current distribution networks-it is capable of detecting invisible power usage and fraudulent behavior while even being able to locate the suspect's location. Case studies, using both simulated data and actual data, validate the proposed method.
Xing He; Lei Chu; Robert Caiming Qiu; Qian Ai; ZeNan Ling; Jian Zhang. Invisible Units Detection and Estimation Based on Random Matrix Theory. IEEE Transactions on Power Systems 2019, 35, 1846 -1855.
AMA StyleXing He, Lei Chu, Robert Caiming Qiu, Qian Ai, ZeNan Ling, Jian Zhang. Invisible Units Detection and Estimation Based on Random Matrix Theory. IEEE Transactions on Power Systems. 2019; 35 (3):1846-1855.
Chicago/Turabian StyleXing He; Lei Chu; Robert Caiming Qiu; Qian Ai; ZeNan Ling; Jian Zhang. 2019. "Invisible Units Detection and Estimation Based on Random Matrix Theory." IEEE Transactions on Power Systems 35, no. 3: 1846-1855.
Interconnected microgrids can enable mutual power support among microgrids (MGs) and improves the utilization of renewable energy sources, especially for CCHP-based (Combined Cooling, Heating, and Power) Microgrid Cluster (MGC). To preserve information privacy and achieve scheduling independence of microgrids, the problem of multi-area economic and environmental dispatch in CCHP plus MGC can be computed by distributed algorithm framework, i.e., generalized benders decomposition (GBD), optimal condition decomposition (OCD) and auxiliary problem principle (APP), respectively for interconnected topology and bus topology. Moreover, chance constrained programming (CCP) is added to address the uncertainty factors of renewable energy, cooling, heating, and electrical loads. A consensus-based distributed fair cost allocation algorithm is proposed to make a comparison with the condition of adding selfish constraints and independent operation, so that guaranteeing the stability of economic coalition of MGC. A case study with four networked CCHP microgrids in two kinds of topology is tested to demonstrate the effectiveness of the proposed approach in summer scenario. In conclusion, distributed algorithms will have a prospective application on MGC as the result of the necessity from different entities in the future.
Xiaoqian Zhou; Qian Ai. Distributed economic and environmental dispatch in two kinds of CCHP microgrid clusters. International Journal of Electrical Power & Energy Systems 2019, 112, 109 -126.
AMA StyleXiaoqian Zhou, Qian Ai. Distributed economic and environmental dispatch in two kinds of CCHP microgrid clusters. International Journal of Electrical Power & Energy Systems. 2019; 112 ():109-126.
Chicago/Turabian StyleXiaoqian Zhou; Qian Ai. 2019. "Distributed economic and environmental dispatch in two kinds of CCHP microgrid clusters." International Journal of Electrical Power & Energy Systems 112, no. : 109-126.
Interconnected microgrids or a microgrid cluster (MGC) can enable mutual power support among microgrids and can improve the utilization of renewable energy sources. However, most of the distributed optimization focuses only on day-ahead or day-in dispatch, and few studies have attempted to study the integrated two-level distributed optimization. On the basis of the alternating direction method of multipliers (ADMM), this paper describes an efficient two-level distributed algorithm framework to solve multi-area ED problems in MGC considering unit commitment and transmission loss. Specifically, to overcome the non-convexity, a choice and comparison approach is introduced to cooperate with power-based ADMM for searching feasible binary variables in the first level, i.e., day-ahead dispatch. Voltage-based ADMM is adopted to obtain the relevant intra-day scheduling plan considering tie-line transmission loss among different areas in the second level. Moreover, a spinning reserve-based chance-constrained progra...
Xiaoqian Zhou; Qian Ai. An integrated two-level distributed dispatch for interconnected microgrids considering unit commitment and transmission loss. Journal of Renewable and Sustainable Energy 2019, 11, 025504 .
AMA StyleXiaoqian Zhou, Qian Ai. An integrated two-level distributed dispatch for interconnected microgrids considering unit commitment and transmission loss. Journal of Renewable and Sustainable Energy. 2019; 11 (2):025504.
Chicago/Turabian StyleXiaoqian Zhou; Qian Ai. 2019. "An integrated two-level distributed dispatch for interconnected microgrids considering unit commitment and transmission loss." Journal of Renewable and Sustainable Energy 11, no. 2: 025504.