Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
In modern complex physical systems, advanced sensing technologies extend the sensor coverage but ... more In modern complex physical systems, advanced sensing technologies extend the sensor coverage but also increase the difficulties of improving system monitoring capabilities based on real-time data availability. Traditional model-based methods of sensor management are limited to specific systems/settings, which can be challenged when system knowledge is intractable. Fortunately, the large amount of data collected in real-time allows machine learning methods to be a complement. Especially, reinforcement learning-based control is recognized for its capability to dynamically interact with systems. However, the direct implementation of learning methods easily overfits and results in inaccurate physics modeling for sensor management. Although physical regularization is a popular direction to bridge the gap, learning-based sensor control still suffers from convergence failure under highly complex and uncertain scenarios. This paper develops physics-embedded and self-supervised reinforcement learning for sensor management using an intrinsic reward. Specifically, the intrinsic-motivated sensor management (IMSM) constructs the local surprise information from the physical latent features, which captures hidden states in observations, and thus intrinsically motivates the agent to speed-up exploration. We show that the designs can not only relieve the lack of consistency with underlying physics/physical dynamics, but also adapt the global objective of maximizing monitoring capabilities to local environment changes. We demonstrate its effectiveness by experiments on physical system sensor control. The proposed model is implemented for the sensor management of unmanned vehicles and sensor rescheduling in complex/settled power systems, with or without observability constraints. Numerical results show that our model provides consistently higher threat detection accuracy and better observability recovery, as compared to existing methods. CCS CONCEPTS • Computer systems organization → Sensor networks; • Theory of computation → Sequential decision making; • Hardware → Smart grid. This work is licensed under a Creative Commons Attribution International 4.0 License.
The widespread use of distributed energy sources (DERs) raises significant challenges for power s... more The widespread use of distributed energy sources (DERs) raises significant challenges for power system design, planning, and operation, leading to wide adaptation of tools on hosting capacity analysis (HCA). Traditional HCA methods conduct extensive power flow analysis. Due to the computation burden, these time-consuming methods fail to provide online hosting capacity (HC) in large distribution systems. To solve the problem, we first propose a deep learning-based problem formulation for HCA, which conducts offline training and determines HC in real time. The used learning model, long short-term memory (LSTM), implements historical time-series data to capture periodical patterns in distribution systems. However, directly applying LSTMs suffers from low accuracy due to the lack of consideration on spatial information, where location information like feeder topology is critical in nodal HCA. Therefore, we modify the forget gate function to dual forget gates, to capture the spatial correlation within the grid. Such a design turns the LSTM into the Spatial-Temporal LSTM (ST-LSTM). Moreover, as voltage violations are the most vital constraints in HCA, we design a voltage sensitivity gate to increase accuracy further. The results of LSTMs and ST-LSTMs on feeders, such as IEEE 34-, 123-bus feeders, and utility feeders, validate our designs.
The past few years have witnessed significant growth on the possession rate of electric vehicles ... more The past few years have witnessed significant growth on the possession rate of electric vehicles (EV). Such growth urgently requires well-designed plans on charging station placement for sustainable EV growth. Existing solutions ignore many practical factors and lack a systematic method prioritizing them. Through constructive learning, we propose an urban EV charging station planning method with the deployment of levelized cost. This method incorporates four practical costs, considering the convexification of the constraints, economic parameter variation, and the interconnected electric and transportation networks. To better quantify the charging demand, the nested logit model is deployed. Meanwhile, we relate the public information of house prices with EV growth when assigning the weights. Furthermore, we also design the software that enables EV charging station placement. Numerical results reveal the trade-off in EV charger planning, as well as a promising system-level optimization performance.
Increasing renewable penetration in distribution grids calls for improved monitoring and control,... more Increasing renewable penetration in distribution grids calls for improved monitoring and control, where power flow (PF) model is the basis for many advanced functionalities. However, unobservability makes the traditional way infeasible to construct PF analysis via admittance matrix for many distribution grids. While data-driven approaches can approximate PF mapping, direct machine learning (ML) applications may suffer from several drawbacks. First, complex ML models like deep neural networks lack the degradability and explainability to the true system model, leading to overfitting. There are also asynchronization issues among different meters without GPS chips. Last but not least, bad data is quite common in the distribution grids. To resolve these problems all at once, we propose a variational support matrix regression (SMR). It provides structural learning to (1) embed kernels to regularize physical form in observable area while achieving good approximation at unobservable area, (2) integrate temporal information into matrix regression for asynchronized data imputation, and (3) define support matrix for margins to be robust against bad data. We test the performance for mapping rule learning via IEEE test systems and a utility distribution grid. Simulation results show high accuracy, degradability from data-driven model to physical model, and robustness to data quality issues.
2021 IEEE International Conference on Data Mining (ICDM), 2021
The large amount of data collected in complex physical systems allows machine learning models to ... more The large amount of data collected in complex physical systems allows machine learning models to solve a variety of prediction problems. However, the directly applied learning approaches, especially deep neural networks (DNN), are difficult to balance between universal approximation to minimize error and the interpretability to reveal underlying physical law. Their performance drops even faster with system unobservability (of measurements) issues due to limited measurements. In this paper, we construct the novel physics interpretable shallow-deep neural networks to integrate exact physical interpretation and universal approximation to address the concerns in previous methods. We show that not only the shallow layer of the structural DNN extracts interpretable physical features but also the designed physical-input convex property of the DNN guarantees the true physical function recovery. While input convexity conditions are strict, the proposed model retains the representation capability to universally approximate for the unobservable system regions. We demonstrate its effectiveness by experiments on physical systems. In particular, we implement the proposed model on the forward kinematics and complex power flow reproduction tasks, with or without observability issues. We show that, besides the physical interpretability, our model provides consistently smaller or similar prediction error for system identification, compared to the state-of-art learning methods.
Power systems face increasing challenges on reliable operations due to the widespread distributed... more Power systems face increasing challenges on reliable operations due to the widespread distributed generators (DGs), e.g., rooftop PV system in the low voltage (LV) distribution grids. Characterizing the hosting capacity (HC) is vital for assessing the total amount of distributed generations that a grid can hold before upgrading. For analyzing HC, some methods conduct extensive simulations, lacking theoretical guarantees and can time-consuming. Therefore, there are also methods employing optimization over all necessary operation constraints. But, the complexity and inherent non-convexity lead to non-optimal solutions. To solve these problems, this paper provides a constructive model for HC determination. Based on geometrically obtained globally optimal HC, we construct HC solutions sequentially according to realistic constraints, so that we can obtain optimal solution even with non-convex model. For practical adaption, we also consider three-phase unbalance condition and parallel com...
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
In modern complex physical systems, advanced sensing technologies extend the sensor coverage but ... more In modern complex physical systems, advanced sensing technologies extend the sensor coverage but also increase the difficulties of improving system monitoring capabilities based on real-time data availability. Traditional model-based methods of sensor management are limited to specific systems/settings, which can be challenged when system knowledge is intractable. Fortunately, the large amount of data collected in real-time allows machine learning methods to be a complement. Especially, reinforcement learning-based control is recognized for its capability to dynamically interact with systems. However, the direct implementation of learning methods easily overfits and results in inaccurate physics modeling for sensor management. Although physical regularization is a popular direction to bridge the gap, learning-based sensor control still suffers from convergence failure under highly complex and uncertain scenarios. This paper develops physics-embedded and self-supervised reinforcement learning for sensor management using an intrinsic reward. Specifically, the intrinsic-motivated sensor management (IMSM) constructs the local surprise information from the physical latent features, which captures hidden states in observations, and thus intrinsically motivates the agent to speed-up exploration. We show that the designs can not only relieve the lack of consistency with underlying physics/physical dynamics, but also adapt the global objective of maximizing monitoring capabilities to local environment changes. We demonstrate its effectiveness by experiments on physical system sensor control. The proposed model is implemented for the sensor management of unmanned vehicles and sensor rescheduling in complex/settled power systems, with or without observability constraints. Numerical results show that our model provides consistently higher threat detection accuracy and better observability recovery, as compared to existing methods. CCS CONCEPTS • Computer systems organization → Sensor networks; • Theory of computation → Sequential decision making; • Hardware → Smart grid. This work is licensed under a Creative Commons Attribution International 4.0 License.
The widespread use of distributed energy sources (DERs) raises significant challenges for power s... more The widespread use of distributed energy sources (DERs) raises significant challenges for power system design, planning, and operation, leading to wide adaptation of tools on hosting capacity analysis (HCA). Traditional HCA methods conduct extensive power flow analysis. Due to the computation burden, these time-consuming methods fail to provide online hosting capacity (HC) in large distribution systems. To solve the problem, we first propose a deep learning-based problem formulation for HCA, which conducts offline training and determines HC in real time. The used learning model, long short-term memory (LSTM), implements historical time-series data to capture periodical patterns in distribution systems. However, directly applying LSTMs suffers from low accuracy due to the lack of consideration on spatial information, where location information like feeder topology is critical in nodal HCA. Therefore, we modify the forget gate function to dual forget gates, to capture the spatial correlation within the grid. Such a design turns the LSTM into the Spatial-Temporal LSTM (ST-LSTM). Moreover, as voltage violations are the most vital constraints in HCA, we design a voltage sensitivity gate to increase accuracy further. The results of LSTMs and ST-LSTMs on feeders, such as IEEE 34-, 123-bus feeders, and utility feeders, validate our designs.
The past few years have witnessed significant growth on the possession rate of electric vehicles ... more The past few years have witnessed significant growth on the possession rate of electric vehicles (EV). Such growth urgently requires well-designed plans on charging station placement for sustainable EV growth. Existing solutions ignore many practical factors and lack a systematic method prioritizing them. Through constructive learning, we propose an urban EV charging station planning method with the deployment of levelized cost. This method incorporates four practical costs, considering the convexification of the constraints, economic parameter variation, and the interconnected electric and transportation networks. To better quantify the charging demand, the nested logit model is deployed. Meanwhile, we relate the public information of house prices with EV growth when assigning the weights. Furthermore, we also design the software that enables EV charging station placement. Numerical results reveal the trade-off in EV charger planning, as well as a promising system-level optimization performance.
Increasing renewable penetration in distribution grids calls for improved monitoring and control,... more Increasing renewable penetration in distribution grids calls for improved monitoring and control, where power flow (PF) model is the basis for many advanced functionalities. However, unobservability makes the traditional way infeasible to construct PF analysis via admittance matrix for many distribution grids. While data-driven approaches can approximate PF mapping, direct machine learning (ML) applications may suffer from several drawbacks. First, complex ML models like deep neural networks lack the degradability and explainability to the true system model, leading to overfitting. There are also asynchronization issues among different meters without GPS chips. Last but not least, bad data is quite common in the distribution grids. To resolve these problems all at once, we propose a variational support matrix regression (SMR). It provides structural learning to (1) embed kernels to regularize physical form in observable area while achieving good approximation at unobservable area, (2) integrate temporal information into matrix regression for asynchronized data imputation, and (3) define support matrix for margins to be robust against bad data. We test the performance for mapping rule learning via IEEE test systems and a utility distribution grid. Simulation results show high accuracy, degradability from data-driven model to physical model, and robustness to data quality issues.
2021 IEEE International Conference on Data Mining (ICDM), 2021
The large amount of data collected in complex physical systems allows machine learning models to ... more The large amount of data collected in complex physical systems allows machine learning models to solve a variety of prediction problems. However, the directly applied learning approaches, especially deep neural networks (DNN), are difficult to balance between universal approximation to minimize error and the interpretability to reveal underlying physical law. Their performance drops even faster with system unobservability (of measurements) issues due to limited measurements. In this paper, we construct the novel physics interpretable shallow-deep neural networks to integrate exact physical interpretation and universal approximation to address the concerns in previous methods. We show that not only the shallow layer of the structural DNN extracts interpretable physical features but also the designed physical-input convex property of the DNN guarantees the true physical function recovery. While input convexity conditions are strict, the proposed model retains the representation capability to universally approximate for the unobservable system regions. We demonstrate its effectiveness by experiments on physical systems. In particular, we implement the proposed model on the forward kinematics and complex power flow reproduction tasks, with or without observability issues. We show that, besides the physical interpretability, our model provides consistently smaller or similar prediction error for system identification, compared to the state-of-art learning methods.
Power systems face increasing challenges on reliable operations due to the widespread distributed... more Power systems face increasing challenges on reliable operations due to the widespread distributed generators (DGs), e.g., rooftop PV system in the low voltage (LV) distribution grids. Characterizing the hosting capacity (HC) is vital for assessing the total amount of distributed generations that a grid can hold before upgrading. For analyzing HC, some methods conduct extensive simulations, lacking theoretical guarantees and can time-consuming. Therefore, there are also methods employing optimization over all necessary operation constraints. But, the complexity and inherent non-convexity lead to non-optimal solutions. To solve these problems, this paper provides a constructive model for HC determination. Based on geometrically obtained globally optimal HC, we construct HC solutions sequentially according to realistic constraints, so that we can obtain optimal solution even with non-convex model. For practical adaption, we also consider three-phase unbalance condition and parallel com...
Uploads
Papers by jingyi yuan