This paper proposes a multiagent-based adaptive wide-area current differential protection system. A power grid is divided into primary and backup zones dynamically online with the help of developed expert system, relay agents these cooperate to perform relaying function. Predictive self-healing strategies have been proposed prevent misoperation agent, communication system has simulated. The performance based on computer simulation presented in this paper.

This paper proposes an agent-based paradigm for self-healing protection systems. Numerical relays implemented with intelligent electronic devices are designed as a relay agent to perform protective relaying function in cooperation other agents. A graph-theory-based expert system, which can be integrated supervisory control and data acquisition has been developed divide the power grid into primary backup zones online all agents assigned specific according system topological configuration. In...

With the development of a substation automation system, it is now feasible for intelligent electronic devices-based protection system to collect its measurements from instrument transformers through communication network such as an Ethernet-based local-area network. The application wide-area broadband in power utilities introduces underlying danger systems maloperate when receiving fake data packages intruder. This paper proposes identifying vicious fault by using context information,...

Many mine power systems operate with a floating neutral or are high-resistance grounded, and earth fault current is no more than few tens of amperes. Traditional earth-fault-detection methods based on zero-sequence have poor sensitivity in this case. For improvement, fault-detection scheme fault-current fault-resistance measurement presented paper, which capable detecting high-impedance ground faults. The has been verified by electromagnetic-transient-program simulation, prototype developed...

The construction of smart cities contributes to promoting residents' life convenience and sustainable energy development. Despite these advancements, the challenge fully analyzing understanding usage behaviors leads inefficient use potential economic losses. Current resident anomaly detection technologies rely on single-source data, lacking detailed behavior pattern analysis. Hence, this paper proposes a method detect abnormal residential water electricity by incorporating multi-source...

ABSTRACT Wiring errors, caused by improper connections between neutral lines and protective earth (PE) due to negligence electrical technicians, are a prevalent type of fault in low‐voltage distribution systems (LVDS). These errors can cause the load current affected users flow back transformer's point via PE line as residual current, leading nuisance tripping devices (RCDs). To maintain normal power supply, may disable RCDs, which compromises safety result severe hazards such electric...

As a result of deregulation, distributed generation (DG) systems with generators installed in the middle or low voltage networks become popular distribution systems. Traditional protections developed radial are difficult coordination and protecting against high impedance fault (HIF), sometimes it may cause nuisance tripping DG A decentralized multi-agent based protection capability HIF detection, location load shedding for is proposed paper. Digital relay designed as agent which capable...

The charging load of electric vehicles (EVs) has a strong spatiotemporal randomness. Predicting the dynamic distribution EVs is great significance for grid to cope with access large-scale EVs. Existing studies lack prediction model that can accurately describe dual changes time and space. Therefore, spatial-temporal forecasting model, dilated causal convolution-2D neural network (DCC-2D), proposed. First, hole factor added dimension three-dimensional convolutional convolution kernel form...

Aiming at the wind power prediction problem, a probability method based on quantile regression of dilated causal convolutional neural network is proposed. With developed model, Adam stochastic gradient descent technique utilized to solve cavity parameters under different conditions and obtain density distribution various times within following 200 hours. The presented can more useful information than conventional point interval predictions. Moreover, future complete be realized. According...

This paper proposes an optimal power management approach to reduce the operating costs by managing flows in a photovoltaic (PV)-diesel generator hybrid nanogrid with batteries. The proposed algorithm utilizes dynamic programming (DP) technique optimize system meet load demand, achieve maximum utilization of solar energy available, minimize fuel consumption and increase battery life cycle, simultaneously. Results are demonstrated compared rule-based superiorities verified.

A multi–objective evolutionary algorithm is proposed to solve the routing problem in wireless sensor network. Two performance metrics, which consist of maximisation remaining lifetime network and minimisation transmission delay, are considered. Dominating relationship similarity between solutions used compute fitness a solution population. An energy–saving combination operator executed independently by sink node presented create new solutions. exploitation exploration investigated find...

Aiming at the problems of excessive dependence on manual work, low detection accuracy and poor real-time performance current probe flow anomaly in power system network security detection, a method for calculating information entropy random forest classificat ion is proposed. Firstly, stream data are captured aggregated to extract metadata. Secondly, by Pearson correlation coefficient maximum mutual coefficient, feature selection metadata carried out. Finally, stochastic algorithm combined...

Compare to outside threats, insider threats that originate within targeted systems are more destructive and invisible. More importantly, it is difficult detect mitigate these which poses significant cyber security challenges an industry control system (ICS) tightly coupled with today's information technology infrastructure. Currently, power utilities rely mainly on the authentication mechanism prevent threats. If internal intruder breaks protection barrier, hard identify intervene in time...

This letter analyses time series of two distribution system (DS) fault records to find their probability distribution. Observation indicates that the complementary cumulative function (CCDF) number per day has a power law tail and location an exponential tail. The data add knowledge is fundamental basis for developing methods maintenance reliability.

This paper proposes an economically optimal energy management approach for grid-connected photovoltaic microgrid. The is derived based on the dynamic programming algorithm and grid Input/Output (grid I/O) strategy, to satisfy load demand, fully utilize solar energy, minimize battery lifecycle losses, maximize economic benefits end-users, simultaneously. performances of this are explored different weather scenarios (including sunny cloudy weather) with forecast measured (PV) power profiles....

A modular plug-and-play photovoltaic (PV) converter system for portable PV applications is proposed. Small subpanel of cells have individual dc/dc converters performing distributed maximum power point tracking. The submodules are connected in parallel to a DC bus. Challenges the proposed accommodate diverse types loads addressed. Based on scenario analysis, operating mode and range illustrated. peer-to-peer control strategy developed maintain stable supply automatically with and/or load...