Bi-level optimization and reinforcement learning (RL) constitute the state-of-the-art frameworks for modeling strategic bidding decisions in deregulated electricity markets. However, former neglects market participants' physical non-convex operating characteristics, while conventional RL methods require discretization of state and/or action spaces thus suffer from curse dimensionality. This paper proposes a novel deep (DRL) based methodology, combining deterministic policy gradient (DDPG)...

Decarbonization of electricity systems drives significant and continued investments in distributed energy sources to support the cost-effective transition low-carbon systems. However, rapid integration photovoltaic (PV) generation presents great challenges obtaining reliable secure grid operations because its limited visibility intermittent nature. Under this reality, net load forecasting is facing unprecedented difficulty answering following question: How can we accurately predict while...

With the prevalence of smart meters, fine-grained subprofiles reveal more information about aggregated load and further help improve forecasting accuracy. Ensemble is an effective approach for forecasting. It either generates multiple training datasets or applies models to produce forecasts. In this letter, a novel ensemble method proposed forecast with where forecasts are produced by different groupings subprofiles. Specifically, first clustered into groups conducted on grouped profiles...

In industrial applications, nearly half the failures of motors are caused by degradation rolling element bearings (REBs). Therefore, accurately estimating remaining useful life (RUL) for REBs crucial importance to ensure reliability and safety mechanical systems. To tackle this challenge, model-based approaches often limited complexity mathematical modeling. Conventional data-driven approaches, on other hand, require massive efforts extract features construct health index. paper, a novel...

Nowadays, smart meters are deployed in millions of residential households to gain significant insights from fine-grained electricity consumption data. The information extracted meter data enables utilities identify the socio-demographic characteristics consumers and then offer them diversified services. Traditionally, this task is implemented a centralized manner with assumption that have access all However, measured owned by different retailers retail market who may not be willing share...

Solar and wind resources are vital for the sustainable energy transition. Although renewable potentials have been widely assessed in existing literature, few studies examined statistical characteristics of inherent uncertainties arising from natural randomness, which is inevitable stochastic-aware research applications. Here we develop a rule-of-thumb learning model solar power prediction generate year-long dataset hourly errors 30 provinces China. We reveal diversified spatiotemporal...

The rapid development of information and communications technology has enabled the use digital-controlled software-driven distributed energy resources (DERs) to improve flexibility efficiency power supply, support grid operations. However, this evolution also exposes geographically-dispersed DERs cyber threats, including hardware software vulnerabilities, communication issues, personnel errors, etc. Therefore, enhancing cyber-resiliency DER-based smart -the ability survive successful...

The ongoing decarbonisation of modern electricity systems has led to a substantial increase operational uncertainty, particularly due the large-scale integration renewable energy generation. However, expanding space possible operating points renders necessary development novel security assessment approaches. In this paper we focus on use rules where classifiers are trained offline characterize previously unseen as safe or unsafe. This proposes deep learning-based feature extraction framework...

The ongoing deployment of residential smart meters in numerous jurisdictions has led to an influx electricity consumption data. This information presents a valuable opportunity suppliers for better understanding their customer base and designing more effective tariff structures. In the past, various clustering methods have been proposed meaningful partitioning. paper novel finite mixture modeling framework based on C-vine copulas (CVMM) carrying out consumer categorization. superiority lies...

Demand response (DR) is one of the most cost-effective solutions for providing flexibility to power systems. The extensive deployment DR trials and roll-out smart meters enable quantification consumer responsiveness price signals via baseline estimation. traditional deterministic estimation approach can provide only a single value without consideration uncertainty. This paper proposes novel probabilistic framework that consists daily load profile pool construction stage, deep learning-based...

In responseto low-carbon requirements, a large amount of renewable energy resources (RESs) have been deployed in power systems; nevertheless, the intermittency RESs raises system vulnerability and even causes severe damage under extreme events. Electric vehicles (EVs), owing to their mobility flexibility characteristics, can provide various ancillary services meanwhile enhancing resilience. The distributed control EVs such scenarios power-transportation network becomes complex...

The wide popularity of smart meters enables the collection massive amounts fine-grained electricity consumption data. Extracting typical patterns from these data supports retailers in their understanding consumer behaviors. In this way, diversified services such as personalized price design and demand response targeting can be provided. Various clustering algorithms have been studied for pattern extraction. These methods to implemented a centralized assuming that all meter accessed. However,...

Extreme events are greatly impacting the normal operations of microgrids, which can lead to severe outages and affect continuous supply energy customers, incurring substantial restoration costs. Repair crews (RCs) regarded as crucial resources provide system resilience owing their mobility flexibility characteristics in handling both transportation systems. Nevertheless, effectively coordinating dispatch RCs towards is a complex decision-making problem, especially context multi-energy...

The large-scale integration of distributed energy resources into the industry enables fast transition to a decarbonized future but raises some potential challenges insecure and unreliable operations. Multi-energy Microgrids (MEMGs), as localized small multi-energy systems, can effectively integrate variety components with multiple sectors, which have been recently recognized valid solution improve operational security reliability. As result, massive amount research has conducted investigate...

Microgrids (MGs), as localized small power systems, can effectively provide voltage regulation services for distribution networks by integrating and managing various distributed energy resources. Existing literature employs model-based optimization approaches to formulate the problem of multi-MGs, which require complete system models. However, this assumption is normally impractical due time-varying environment privacy issues. To fill research gap, paper suggests a data-driven decentralized...

Adequate capacity planning of substations and feeders primarily depends on an accurate estimation the future peak electricity demand. Traditional coincident demand is carried out based empirical metric, after diversity maximum demand, indicating individual consumption levels diversification across multiple residents. With privilege smart meters in cities, this paper proposes a data-driven probabilistic framework using fine-grained meter data sociodemographic consumers, which drive...

Power system investment planning problems become intractable due to the vast variability that characterizes operation and increasing complexity of optimization model capture characteristics renewable energy sources. In this context, making optimal decisions by considering every operating period is unrealistic inefficient. The conventional solution address computational issue select a limited number representative periods clustering input demand-generation patterns while preserving key...

This work proposes a novel deep reinforcement learning (DRL)-based demand response algorithm for smart facilities energy management to minimize electricity costs while maintaining satisfaction index. Specifically, accommodate the characteristics of decision-making problem, long short-term memory (LSTM) units are adopted extract discriminative features from past price sequences and fed into fully connected multi-layer perceptrons (MLPs) with measured time information, then Q-network is...

Dynamic Security Assessment (DSA) for the future power system is expected to be increasingly complicated with higher level penetration of renewable energy sources (RES) and widespread deployment electronic devices, which drive new dynamic phenomena. As a result, increasing complexity severe computational bottleneck in real-time operation encourage researchers exploit machine learning extract offline security rules online assessment. However, traditional methods lack providing information on...

With the growing penetration of distributed renewable energy, control approaches are widely utilized in voltage active distribution networks (ADNs), suffering from limited applicability for devices or heavy communication burden. This paper develops an innovative strategy ADNs with global sensitivities (DVC-GS), which integrates network information a optimization view to coordinate energy storages, PV inverters and OLTC little computing time. The violations across all buses respect nodal...