The optimized operation of a building energy management system (BEMS) is great significance to its security, economy, and efficiency. This paper proposes day-ahead multiobjective optimization model for the BEMS under time-of-use price-based demand response (DR), which integrates integrated photovoltaic with other generations optimize economy occupants' comfort by synergetic dispatch source-load-storage. contains three aspects indoor environment: visual comfort; thermal air quality comfort....

The motion of cloud over a photovoltaic (PV) power station will directly cause the change solar irradiance, which indirectly affects prediction minute-level PV power. Therefore, calculation speed is very crucial for forecasting. However, due to influence complex process, it difficult achieve accurate result using single traditional algorithm. In order improve computation accuracy, pattern classification and particle swarm optimization optimal weights based sky images method forecasting...

We study cascading transmission line outages recorded over nine years in an electric power system with approximately 200 lines. The average amount of propagation the is estimated from data. distribution total number predicted and initial using a Galton-Watson branching process model failure.

Regional photovoltaic(PV) power forecasting provides a foundation for grid management and trading in the markets. To tackle deficiency of conventional regional PV modeling methods, such as problem challenging to select useful meteorological information that single model cannot fully learn complex diverse fluctuation characteristics curves, an ultrashort-term framework assembled by fusing pattern recognition (FPR) deep learning under prediction (FPP) was proposed. First all, curves were...

Aggregators, as the interface of electric vehicles (EVs) and distribution system, are market agents EVs to participate in demand response (DR) other balancing services. Aggregators can enlarge its benefit room from vehicle-to-grid (V2G) by providing flexible V2G price EV users long they secure a certain amount energy. There is need study Aggregator's pricing strategy due fact that companies, aggregators, have their own independent maximization objectives entities, decision variables...

A dc microgrid is a low inertia system dominated by power converters. As result, the change rate of voltage very fast under variation. In this study, distributed virtual control proposed to enhance and decrease voltage. The can be enhanced kinetic energy in rotor permanent magnet synchronous generators (PMSG)-based wind turbine, stored batteries from utility grid. By introducing coefficient, general expression inertial provided each controllable sources defined. simply first-order loop...

The optimal dispatching model for a stand-alone microgrid (MG) is of great importance to its operation reliability and economy. This paper aims at addressing the difficulties in improving operational economy maintaining power balance under uncertain load demand renewable generation, which could be even worse such abnormal conditions as storms or abnormally low high temperatures. A new two-time scale multi-objective optimization model, including day-ahead cursory scheduling real-time finer...

Participant recruitment based on unstructured medical texts such as clinical notes and radiology reports has been a challenging yet important task for the cohort establishment in research. Recently, Large Language Models (LLMs) ChatGPT have achieved tremendous success various downstream tasks thanks to their promising performance language understanding, inference, generation. It is then natural test feasibility solving task, which involves classification of given paragraph text into disease...

Several episodes of sudden large scale disruptions in electrical service deeply impacted both the social stability and economic development affected countries. The prevention such catastrophic incidents poses huge challenges for reliability study operational practices power systems. Studies other scientific fields show that, upon reaching a tipping point, complex dynamical systems can experience transitions into contrasting state. These may be predicted through behavioral changes some...

Abstract To address the problems of slow convergence and inefficiency in existing adaptive PID controllers, we propose a new controller using asynchronous advantage actor–critic (A3C) algorithm. Firstly, can train multiple agents structures parallel exploiting multi-thread learning characteristics A3C structure. Secondly, order to achieve best control effect, each agent uses multilayer neural network approach strategy function value search parameter-tuning continuous action space. The...

Abstract In order to improve the reliability and performance of photovoltaic systems, a fault diagnosis method for modules based on infrared images improved MobileNet‐V3 is proposed. Firstly, defect open‐source their existing problems are analysed; problems, image enhancement data performed modules, so that meet requirements availability sample quantity. Finally, basic network realize classification modules. The experimental results show that, compared with traditional CNN MobileNet V3,...

Solar photovoltaic (PV) power generation has strong intermittency and volatility due to its high dependence on solar radiation other meteorological factors. Therefore, the negative impact of grid-connected PV systems become one constraints in development large scale systems. Accurate forecasting flexible planning operational measures are great significance ensure safe, stable, economical operation a system with penetration at transmission distribution levels. In this paper, studies following...

A robust low-carbon economic optimal scheduling method that considers source-load uncertainty and hydrogen energy utilization is developed. The proposed overcomes the challenge of random fluctuations in integrated systems (IESs) operation problem production units (IEPUs). First, to solve inaccurate prediction renewable output, an improved kernel density estimation construct a data-driven output set sources statistically build typical scenario load using stochastic reduction. Subsequently,...

This paper addresses itself to evaluate quantitatively the severity of broken rotor bar (BRB) fault, i.e., number BRBs in induction motors. Sideband components are induced stator current if BRB fault is present and commonly used for diagnosis purposes. Filippetti criterion has been proposed developed literature quantify by using sideband components, however, with unsatisfactory universality/accuracy. briefly analyzes criterion, mathematically derives a new quantification BRBs, based on...

The optimized operation of building energy management system (BEMS) is great significance to its security, economy and efficiency. This paper proposed a multi-objective optimization model for BEMS under time-of-use (TOU) price based demand response (DR), which integrates integrated photovoltaic (BIPV) with other generations optimize the occupants' comfort by synergetic dispatch source-load-storage. contains three aspects indoor environment: visual comfort, thermal air quality comfort. With...

Alzheimer's disease (AD) is a common form of dementia that severely impacts patient health. As AD impairs the patient's language understanding and expression ability, speech patients can serve as an indicator this disease. This study investigates various methods for detecting using patients' transcripts data from DementiaBank Pitt database. The proposed approach involves pre-trained models Graph Neural Network (GNN) constructs graph transcript, extracts features GNN detection. Data...

To address the static voltage stability issue and suppress fluctuation caused by increasing integration of wind farms solar photovoltaic (PV) power plants, a two-tier reactive control strategy based on ARMA forecasting models for plants is proposed in this paper. Firstly, are established to forecast output PV plants. Secondly, discrete equipment pre-regulated single-step prediction information from according optimization result. Thirdly, multi-objective model presented solved particle swarm...