In the development of linear quadratic regulator(LQR) algorithms, the Riccati equation approach offers two important characteristics——it is recursive and readily meets the existence condition. However, these attribu...In the development of linear quadratic regulator(LQR) algorithms, the Riccati equation approach offers two important characteristics——it is recursive and readily meets the existence condition. However, these attributes are applicable only to transformed singular systems, and the efficiency of the regulator may be undermined if constraints are violated in nonsingular versions. To address this gap, we introduce a direct approach to the LQR problem for linear singular systems, avoiding the need for any transformations and eliminating the need for regularity assumptions. To achieve this goal, we begin by formulating a quadratic cost function to derive the LQR algorithm through a penalized and weighted regression framework and then connect it to a constrained minimization problem using the Bellman's criterion. Then, we employ a dynamic programming strategy in a backward approach within a finite horizon to develop an LQR algorithm for the original system. To accomplish this, we address the stability and convergence analysis under the reachability and observability assumptions of a hypothetical system constructed by the pencil of augmented matrices and connected using the Hamiltonian diagonalization technique.展开更多
Predicting comfort levels in cities is challenging due to the many metric assessment.To overcome these challenges,much research is being done in the computing community to develop methods capable of generating outdoor...Predicting comfort levels in cities is challenging due to the many metric assessment.To overcome these challenges,much research is being done in the computing community to develop methods capable of generating outdoor comfort data.Machine Learning(ML)provides many opportunities to discover patterns in large datasets such as urban data.This paper proposes a data-driven approach to build a predictive and data-generative model to assess outdoor thermal comfort.The model benefits from the results of a study,which analyses Computational Fluid Dynamics(CFD)urban simulation to determine the thermal and wind comfort in Tallinn,Estonia.The ML model was built based on classification,and it uses an opaque ML model.The results were evaluated by applying different metrics and show us that the approach allows the implementation of a data-generative ML model to generate reliable data on outdoor comfort that can be used by urban stakeholders,planners,and researchers.展开更多
Smart control techniques have been implemented to address fluctuating power levels within isolated crogrids,mi-mitigating the risk of unstable frequencies and the potential degradation of power supply quality.However,...Smart control techniques have been implemented to address fluctuating power levels within isolated crogrids,mi-mitigating the risk of unstable frequencies and the potential degradation of power supply quality.However,a challenge lies in the fact that employing these computationally complex methods without stability preservation might not suffice to handle the rapid changes of this highly dynamic environment in real-world scenarios over communication delays.This study introduces a flexible real-time approach for the frequency control problem using an artificial neural network(ANN)constrained to stabilized regions.Our solution integrates stabilizing PID controllers,computed through small-signal analysis and tuned via an automated search for optimal ANN weights and reinforcement learning(RL)-based selected constraints.First,we design stabilizing PID controllers by applying the stability boundary locus method and the Mikhailov criterion,specifically addressing communication delays.Next,we refine the controller parameters online through an automated process that identifies optimal coefficient combinations,leveraging a constrained ANN to manage frequency deviations within a restricted parameter range.Our approach is further enhanced by employing the RL technique,which trains the tuning system using an interpolated stability boundary curve to ensure both stability and performance.This one-of-a-kind combination of ANN,RL,and advanced PID tuning methods is a big step forward in how we handle frequency control problems in isolated AC microgrids.The experiments show that our solution outperforms traditional methods due to its reduced parameter search space.In particular,the proposed method reduces transient and steady-state frequency deviations more than semi-and unconstrained methods.The improved metrics and stability analysis show that the method improves system performance and stability under changing conditions.展开更多
Despite widespread adoption and outstanding performance, machine learning models are considered as ‘‘blackboxes’’, since it is very difficult to understand how such models operate in practice. Therefore, in the po...Despite widespread adoption and outstanding performance, machine learning models are considered as ‘‘blackboxes’’, since it is very difficult to understand how such models operate in practice. Therefore, in the powersystems field, which requires a high level of accountability, it is hard for experts to trust and justify decisionsand recommendations made by these models. Meanwhile, in the last couple of years, Explainable ArtificialIntelligence (XAI) techniques have been developed to improve the explainability of machine learning models,such that their output can be better understood. In this light, it is the purpose of this paper to highlight thepotential of using XAI for power system applications. We first present the common challenges of using XAI insuch applications and then review and analyze the recent works on this topic, and the on-going trends in theresearch community. We hope that this paper will trigger fruitful discussions and encourage further researchon this important emerging topic.展开更多
In motion estimation,illumination change is always a troublesome obstacle,which often causes severely per-formance reduction of optical flow computation.The essential reason is that most of estimation methods fail to ...In motion estimation,illumination change is always a troublesome obstacle,which often causes severely per-formance reduction of optical flow computation.The essential reason is that most of estimation methods fail to formalize a unified definition in color or gradient domain for diverse environmental changes.In this paper,we propose a new solution based on deep convolutional networks to solve the key issue.Our idea is to train deep convolutional networks to represent the complex motion features under illumination change,and further predict the final optical flow fields.To this end,we construct a training dataset of multi-exposure image pairs by performing a series of non-linear adjustments in the traditional datasets of optical.flow estimation.Our multi-exposure flow networks(MEFNet)model consists of three main components:low-level feature network,fusion feature network,and motion estimation network.The former two components belong to the contracting part of our model in order to extract and represent the multi-exposure motion features;the third component is the expanding part of our model in order to learn and predict the high-quality optical flow.Compared with many state-of-the-art methods,our motion estimation method can eliminate the obstacle of illumination change and yield optical flow results with competitive accuracy and time efficiency.Moreover,the good performance of our model is also demonstrated in some multi-exposure video applications,like HDR(high dynamic range)composition and flicker removal.展开更多
In the last two decades,motor operation monitoring tools have become a necessity,and many studies focus on the detection and diagnosis of motor electrical faults.However,at present,a core obstacle that prevents the di...In the last two decades,motor operation monitoring tools have become a necessity,and many studies focus on the detection and diagnosis of motor electrical faults.However,at present,a core obstacle that prevents the direct comparison of such classification techniques is the lack of a standard database that can be used as a benchmark.In view of this,we offer here a public experimental data-set that has beendesigned specifically for the comparison of synchronous motor electrical fault classifiers.The data-set comprises five types of motor electrical faults:open phase between inverter and motor;short circuit/leakage current between two phases;short circuit/leakage current in phase-to-neutral;rotor excitation voltage disconnection;and variation of rotor excitation current.In addition,each fault has been recorded as a four-dimensional signal:three phase voltages;three phase currents;motor speed;and motor current.The package includes two deep-learning reference classifiers that are based on a convolutional neural network(CNN)and long short term memory(LSTM).Due to the good performance of these classifiers,we suggest that they can be used by the community as benchmarks for the development of new and better motor electrical fault classification algorithms.The database and the reference classifiers are examined and insights regarding different combinations of features and lengths of recording points are provided.The developed code is available online,and is free to use.展开更多
Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substant...Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during training.This is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,etc.While the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a manner.Such uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF models.Therefore,it becomes essential to identify whether or not the model prediction at a given instance is trustworthy.In this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence techniques.The suggested algorithm generates trust scores that reflect the model’s prediction quality for each new input.These scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different features.Such score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed algorithm.Results show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training dataset.In the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.展开更多
基金supported by the European Union’s Horizon Europe research and innovation programme (101120657)project ENFIELD (European Lighthouse to Manifest Trustworthy and Green AI), the Estonian Research Council (PRG658, PRG1463)the Estonian Centre of Excellence in Energy Efficiency, ENER (TK230) funded by the Estonian Ministry of Education and Research。
文摘In the development of linear quadratic regulator(LQR) algorithms, the Riccati equation approach offers two important characteristics——it is recursive and readily meets the existence condition. However, these attributes are applicable only to transformed singular systems, and the efficiency of the regulator may be undermined if constraints are violated in nonsingular versions. To address this gap, we introduce a direct approach to the LQR problem for linear singular systems, avoiding the need for any transformations and eliminating the need for regularity assumptions. To achieve this goal, we begin by formulating a quadratic cost function to derive the LQR algorithm through a penalized and weighted regression framework and then connect it to a constrained minimization problem using the Bellman's criterion. Then, we employ a dynamic programming strategy in a backward approach within a finite horizon to develop an LQR algorithm for the original system. To accomplish this, we address the stability and convergence analysis under the reachability and observability assumptions of a hypothetical system constructed by the pencil of augmented matrices and connected using the Hamiltonian diagonalization technique.
基金This work has been supported by the European Commission through the H2020 project Finest Twins(grant No.856602).
文摘Predicting comfort levels in cities is challenging due to the many metric assessment.To overcome these challenges,much research is being done in the computing community to develop methods capable of generating outdoor comfort data.Machine Learning(ML)provides many opportunities to discover patterns in large datasets such as urban data.This paper proposes a data-driven approach to build a predictive and data-generative model to assess outdoor thermal comfort.The model benefits from the results of a study,which analyses Computational Fluid Dynamics(CFD)urban simulation to determine the thermal and wind comfort in Tallinn,Estonia.The ML model was built based on classification,and it uses an opaque ML model.The results were evaluated by applying different metrics and show us that the approach allows the implementation of a data-generative ML model to generate reliable data on outdoor comfort that can be used by urban stakeholders,planners,and researchers.
基金supported by the European Union’s Horizon Europe research and innovation programme under the grant agreement No 101120657project ENFIELD(European Lighthouse to Manifest Trust-worthy and Green AI)+1 种基金by the Estonian Research Council through the grants PRG658 and PRG1463and by the Estonian Centre of Excellence in Energy Efficiency,ENER(grant TK230)funded by the Estonian Ministry of Education and Research.
文摘Smart control techniques have been implemented to address fluctuating power levels within isolated crogrids,mi-mitigating the risk of unstable frequencies and the potential degradation of power supply quality.However,a challenge lies in the fact that employing these computationally complex methods without stability preservation might not suffice to handle the rapid changes of this highly dynamic environment in real-world scenarios over communication delays.This study introduces a flexible real-time approach for the frequency control problem using an artificial neural network(ANN)constrained to stabilized regions.Our solution integrates stabilizing PID controllers,computed through small-signal analysis and tuned via an automated search for optimal ANN weights and reinforcement learning(RL)-based selected constraints.First,we design stabilizing PID controllers by applying the stability boundary locus method and the Mikhailov criterion,specifically addressing communication delays.Next,we refine the controller parameters online through an automated process that identifies optimal coefficient combinations,leveraging a constrained ANN to manage frequency deviations within a restricted parameter range.Our approach is further enhanced by employing the RL technique,which trains the tuning system using an interpolated stability boundary curve to ensure both stability and performance.This one-of-a-kind combination of ANN,RL,and advanced PID tuning methods is a big step forward in how we handle frequency control problems in isolated AC microgrids.The experiments show that our solution outperforms traditional methods due to its reduced parameter search space.In particular,the proposed method reduces transient and steady-state frequency deviations more than semi-and unconstrained methods.The improved metrics and stability analysis show that the method improves system performance and stability under changing conditions.
基金supported by Israel Science Foundation,grant No.1227/18.
文摘Despite widespread adoption and outstanding performance, machine learning models are considered as ‘‘blackboxes’’, since it is very difficult to understand how such models operate in practice. Therefore, in the powersystems field, which requires a high level of accountability, it is hard for experts to trust and justify decisionsand recommendations made by these models. Meanwhile, in the last couple of years, Explainable ArtificialIntelligence (XAI) techniques have been developed to improve the explainability of machine learning models,such that their output can be better understood. In this light, it is the purpose of this paper to highlight thepotential of using XAI for power system applications. We first present the common challenges of using XAI insuch applications and then review and analyze the recent works on this topic, and the on-going trends in theresearch community. We hope that this paper will trigger fruitful discussions and encourage further researchon this important emerging topic.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos.61303093,61472245,and 61402278the Innovation Program of the Science and Technology Commission of Shanghai Municipality of China under Grant No.16511101300the Gaofeng Film Discipline Grant of Shanghai Municipal Education Commission of China.
文摘In motion estimation,illumination change is always a troublesome obstacle,which often causes severely per-formance reduction of optical flow computation.The essential reason is that most of estimation methods fail to formalize a unified definition in color or gradient domain for diverse environmental changes.In this paper,we propose a new solution based on deep convolutional networks to solve the key issue.Our idea is to train deep convolutional networks to represent the complex motion features under illumination change,and further predict the final optical flow fields.To this end,we construct a training dataset of multi-exposure image pairs by performing a series of non-linear adjustments in the traditional datasets of optical.flow estimation.Our multi-exposure flow networks(MEFNet)model consists of three main components:low-level feature network,fusion feature network,and motion estimation network.The former two components belong to the contracting part of our model in order to extract and represent the multi-exposure motion features;the third component is the expanding part of our model in order to learn and predict the high-quality optical flow.Compared with many state-of-the-art methods,our motion estimation method can eliminate the obstacle of illumination change and yield optical flow results with competitive accuracy and time efficiency.Moreover,the good performance of our model is also demonstrated in some multi-exposure video applications,like HDR(high dynamic range)composition and flicker removal.
基金This work was supported by the Natural Science Foundation of Jilin Province,China(20210101390JC).
文摘In the last two decades,motor operation monitoring tools have become a necessity,and many studies focus on the detection and diagnosis of motor electrical faults.However,at present,a core obstacle that prevents the direct comparison of such classification techniques is the lack of a standard database that can be used as a benchmark.In view of this,we offer here a public experimental data-set that has beendesigned specifically for the comparison of synchronous motor electrical fault classifiers.The data-set comprises five types of motor electrical faults:open phase between inverter and motor;short circuit/leakage current between two phases;short circuit/leakage current in phase-to-neutral;rotor excitation voltage disconnection;and variation of rotor excitation current.In addition,each fault has been recorded as a four-dimensional signal:three phase voltages;three phase currents;motor speed;and motor current.The package includes two deep-learning reference classifiers that are based on a convolutional neural network(CNN)and long short term memory(LSTM).Due to the good performance of these classifiers,we suggest that they can be used by the community as benchmarks for the development of new and better motor electrical fault classification algorithms.The database and the reference classifiers are examined and insights regarding different combinations of features and lengths of recording points are provided.The developed code is available online,and is free to use.
文摘Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during training.This is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,etc.While the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a manner.Such uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF models.Therefore,it becomes essential to identify whether or not the model prediction at a given instance is trustworthy.In this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence techniques.The suggested algorithm generates trust scores that reflect the model’s prediction quality for each new input.These scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different features.Such score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed algorithm.Results show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training dataset.In the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.
