Deep learning detects inaccurate smart meters for resource savings.
problem Detecting and replacing inaccurate smart meters to save resources.
method Developed a deep-learning method using LSTM and CNN to predict electricity usage trajectories.
result High accuracy in detecting inaccurate meters for practical usage.
Clusters energy usage patterns from smart meters.
problem Identify and group similar energy usage profiles.
method Clustering time-series data from smart meters.
result Accurate grouping of similar energy usage patterns.
This work improves grid observability using smart meter data.
problem Limited metering infrastructure leads to observability issues in distribution grids.
method Developed a coupled formulation of the power flow problem (CPF) and a coupled power system state estimation (CPSSE) problem to infer grid state.
result A necessary and sufficient criterion for local observability in radial networks was identified.
Paper assesses the market value of sharing privacy-protected smart meter data.
problem Value of sharing privacy-protected smart meter data between consumers and load serving entities.
method Discounted differential privacy model, ANN-based load forecasting, optimal procurement problem.
result Significant value in sharing smart meter data while retaining individual consumer privacy.
Hierarchical clustering models capture electricity load patterns from smart meters.
problem Improving efficiency and sustainability of electricity systems.
method Quantile autocovariances and autocorrelations for summarizing time series.
result Clusters identify relevant consumption behaviors and capture geo-demographic segmentation.
This paper proposes a joint energy and data market to handle uncertainty in energy procurement.
problem Handling uncertainty in energy markets through data markets.
method Modeling a day-ahead retailer energy procurement problem with uncertain demand, integrating forecasting and optimisation, and using differential privacy.
result The value of joint energy and data clearing is highlighted through numerical case studies.
New method identifies distribution grid outages using smart meter data.
problem Outages in urban distribution grids due to DERs and smart meters' last gasp signals.
method Data-driven approach based on stochastic time series analysis and maximum likelihood estimation.
result Proves optimal performance in identifying distribution grid outages using smart meter data.
Smart inverters probe grids to infer non-metered loads.
problem Lack of real-time metering in distribution grids.
method Probing inverters to record voltage responses and infer loads.
result Grid probing can infer non-metered loads under certain conditions.
Active learning reduces smart meter data needs for better electric load predictions.
problem Inaccurate and costly electric load predictions due to insufficient data.
method Active learning to collect more informative data subsets.
result Electric load predictions can be made with about half the data using active learning.
New method predicts propagation losses at 169 MHz for smart metering.
problem Radio planning for 169 MHz smart metering networks.
method Support Vector Machine techniques for classification and regression.
result Good accuracy achieved at low computational cost and minimal measurement effort.
Deep learning detects cyber-attacks in smart grid systems.
problem Cyber-attacks on smart grid systems.
method Deep learning-based intrusion detection system trained on industrial dataset.
result Proposed system outperforms Naive Bayes, SVM, and Random Forest.
CROCS clusters consumer behaviour from smart meters, capturing variability and robustness.
problem Insufficient consumer segmentation in existing clustering methods.
method Two-stage clustering framework: first stage clusters daily load profiles, second stage uses WSMD for set-to-set comparison.
result CROCS captures intra-consumer variability and robustness to anomalies and missing data.
Paper uses DNN to improve power generation efficiency by analyzing smart meter data.
problem Reduction of energy losses in power generation, distribution, and transmission.
method Uses Deep Neural Networks (DNN) to forecast electrical network loading from smart meter readings.
result DNN methods outperform traditional methods in load forecasting, with potential for cloud resource optimization.
Data-driven method estimates urban MV and LV grid topology using smart meter data.
problem Reliability issues in urban distribution grids due to distributed energy resources.
method Probabilistic graphical model with group lasso regularization.
result Highly accurate topology estimation in various grid configurations.
Hybrid approach protects privacy while analyzing smart meter data.
problem Privacy concerns in AMI data analysis under CPUC regulations.
method Anonymization, differential privacy, federated learning, synthetic data, cryptography.
result Comprehensive privacy-preserving analytics framework for AMI data.
The paper proposes a method to estimate individual behavioral profiles using smart meter data.
problem Estimating individual behavioral profiles with granular temporal data.
method Gaussian Process-based models for segmenting and clustering time series data.
result The method can predict individual behavioral patterns with high accuracy.
New indicator detects financial strain through smart meter data.
problem Fuel poverty in households, affecting millions.
method Smart meters and machine learning for behavior measurement.
result Early detection of financial strain in households.
New LSTM model predicts disaggregated electricity loads accurately.
problem Forecasting disaggregated electricity loads from smart meters.
method Single complex LSTM model capturing individual consumption patterns.
result Model accurately predicts future loads of new consumers.
Paper addresses privacy threats in real-time SMs data.
problem Privacy threats from real-time SMs data.
method Information-theoretic privacy measure, deep learning adversarial framework.
result Proposes a privatization mechanism with minimal distortion.
Smart meters detect dementia patients' daily activities to prevent crises.
problem Monitoring dementia patients' daily activities without intruding.
method Machine learning and signal processing for smart meter load disaggregation.
result SVM and Decision Forest models accurately detect ADLs and routine changes.
Paper proposes a new method for hourly load forecasting using smart meter data.
problem Challenges in short-term load forecasting at fine granularity.
method Forecasting using Matrix Factorization (fmf) for hourly load forecasting.
result Significantly outperforms state-of-the-art methods in load forecasting.
Paper uses smart meter data to accurately estimate multi-phase topology and identify bus phases in unbalanced distribution grids.
problem Accurate topology knowledge is needed for monitoring and controlling uncertainties in unbalanced distribution grids.
method Converts multi-phase unbalanced systems into symmetrical components and uses information theory, power flow equations, and conditional independence relationships to estimate topology and identify bus phases.
result The algorithm accurately estimates multi-phase topology and identifies bus phases in unbalanced distribution grids, even with strong load unbalancing and DERs.
Adversarial attacks can fool ML energy theft detection models.
problem Vulnerability of ML-based energy theft detection models to adversarial attacks.
method Design of an adversarial measurement generation algorithm.
result ML models can be significantly fooled by adversarial attacks, reducing their detection accuracy.
The paper proposes a new method for probabilistic load forecasting using Bernstein-Polynomial Normalizing Flows.
problem High variability in short-term load forecasting at the low-voltage level due to fluctuating demand and increasing electrification.
method Flexible conditional density forecasting based on Bernstein polynomial normalizing flows with neural network control.
result Density predictions outperform traditional methods for 24h-ahead load forecasting.
New methods improve electricity load forecasting using hierarchical transfer learning.
problem Improving electricity load forecasts at national scale using smart meter data.
method Developed two hierarchical transfer learning methods based on stacking and aggregation of experts.
result Significant improvement in predictions compared to benchmark algorithms.
Designing probing injections for smart inverters to infer non-metered loads.
problem Inferring non-metered loads from electric grid probing.
method Designing probing injections that adhere to inverter and network constraints, using a library of candidate vectors and SDP relaxation for noisy data.
result Improved load estimates through optimal probing design.
Deep neural networks predict electricity consumption accurately.
problem Predicting future electricity consumption for better management.
method Used Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM) networks to predict electricity consumption based on past data.
result Both RNN and LSTM achieved an average Root Mean Square error of 0.1.
This paper analyzes load predictability at different aggregation levels and improves forecasting accuracy.
problem Challenges in short-term load forecasting, especially at low aggregation levels.
method Characterized SME and residential loads, quantified predictability using approximate entropy, compared various STLF techniques.
result Improved forecasting accuracy for low-aggregation loads, validated with data processing techniques.
Paper proposes a novel optimization method for disaggregating smart meter data.
problem Energy disaggregation, inferring appliance-specific energy consumption from aggregate meter data.
method Two-stage optimization approach: first phase uses mixed integer programming, second phase binary quadratic optimization with penalty terms and appliance constraints.
result Proposed method successfully reconstructs appliance signatures, overcoming previous optimization-based methods' limitations.
Consumers with low demand, like households, are generally supplied single-phase power by connecting their service mains to one of the phases of a distribution transformer. The distribution companies face the problem of keeping a record of consumer connectivity to a phase due to uninformed changes that happen. The exact…
Smart grid uses deep learning to optimize household energy use.
problem Optimizing household energy use under real-time pricing schemes.
method Multi-agent deep actor-critic learning for decentralized agents with partial observability.
result Deep reinforcement learning reduces peak-to-average energy consumption and costs.
Deep RNN detects electricity theft in smart grids.
problem Electricity theft in smart grids.
method Generalized deep recurrent neural network (RNN) with gated recurrent unit (GRU) and random hyper-parameter tuning.
result Superior performance compared to existing detectors.
This paper reviews low voltage load forecasting methods and applications.
problem Reliable forecasting for low voltage networks is needed for decarbonization.
method Comprehensive survey of current approaches, challenges, and trends.
result Established an open list of low voltage datasets for further research.
This thesis tackles NILM challenges with a new dataset and efficient edge deployment techniques.
problem Limited datasets and high computational power for NILM deployment.
method Developed an interoperable data collection framework and introduced model compression techniques.
result Efficient edge deployment of NILM models for global scalability and sustainability.
Study develops a machine learning-based ramp metering model to improve freeway efficiency.
problem Improving ramp metering to maintain freeway efficiency under various traffic conditions.
method Machine learning approach using historical data to predict and manage traffic flow.
result The novel model outperforms a baseline traffic-responsive ramp metering algorithm.
Detects non-technical electricity losses using image representations of time-series data.
problem Detecting anomalies in large-scale, unlabelled data for non-technical losses.
method Transformed time-series data into image representations, used semi-supervised deep learning.
result Significant improvement in detecting abnormal electricity consumption patterns.
RNN models classify poem meters from plain text with high accuracy.
problem Classifying poem meters from plain text.
method Character-level encoding, RNN models, no feature handcrafting.
result 96.38% accuracy for Arabic poems, 82.31% for English poems.
We propose a new framework for single-channel source separation that lies between the fully supervised and unsupervised setting. Instead of supervision, we provide input features for each source signal and use convex methods to estimate the correlations between these features and the unobserved signal decomposition. We…
Develops efficient algorithms for data science, tackling the curse of dimensionality.
problem Tackles the curse of dimensionality in large datasets.
method Focuses on feature extraction techniques and meta-heuristic algorithms, including evolutionary algorithms.
result Evolutionary algorithms are effective in solving optimization problems with a curse of dimensionality.
System detects overfitting in ML apps, improving quality and efficiency.
problem Overfitting in ML applications during continuous development.
method ease. ml/meter system for automated overfitting detection and measurement.
result Probabilistic overfitting signals for developers to take actions.
The paper develops a multi-unit soft sensing model for virtual flow meters that improves few-shot learning.
problem Improving soft sensor performance for new wells with limited data.
method Formulates a probabilistic, hierarchical model using a deep neural network for multi-unit soft sensing.
result Multi-unit models trained on many wells can perform well on new wells with just a few data points.
Deep learning identifies QCD transition properties from particle spectra.
problem Detecting the nature of the QCD transition from heavy-ion collision data.
method Supervised deep learning with a convolutional neural network.
result A neural network acts as an 'EoS-meter' for QCD transition properties.
Project uses machine learning to identify skiers' techniques from power meter data.
problem Identifying skiers' techniques from power meter data.
method Machine learning, specifically LSTM neural networks, applied to time-series data.
result 95% accuracy in classifying skiers' techniques with a subset of data.
Deep neural network improves NILM with attention mechanism.
problem Energy disaggregation of individual appliance power demands from aggregate meter readings.
method Regression and classification subnetworks with attention mechanism.
result Proposed model outperforms state-of-the-art on REDD and UK-DALE datasets.
Paper introduces Privacy Mining Approach (PMA) to reveal privacy from smart homes.
problem Privacy disclosure from IoT-based smart homes for elders.
method Conducts deductions and analyses on sensor datasets to reveal privacy.
result PMA can deduce a global sensor topology and disclose elders' privacy.
This work addresses privacy issues in IoT data sharing by balancing information disclosure and user privacy.
problem Balancing privacy and utility in time-series data sharing from IoT devices.
method Formulated as POMDPs, solved using A2C DRL, evaluated with synthetic and real data.
result Proposed policies achieve a good balance between privacy and utility.
Proposes a probabilistic framework for smart contract risk quantification.
problem Quantifying financial risk of smart contract cyber attacks and failures.
method Probabilistic graph-theoretical framework using bond percolation models.
result Analytical results and numerical examples for aggregate loss distribution.
Study shows Bitcoin mining with surplus electricity can boost KEPCO's financial stability.
problem Improving energy resource efficiency and reducing KEPCO's debt.
method Utilized surplus electricity for Bitcoin mining using Antminer S21 XP Hyd, analyzed with Random Forest Regressor and Long Short-Term Memory models.
result Bitcoin mining with surplus electricity generates economic revenue, minimizes energy loss, and resolves payment issues for KEPCO.