This paper proposes a framework and its mathematical model for optimal routing charging of an electric vehicle fleet high-efficiency dynamic transit systems, while taking into account energy efficiency price. Based on extended pickup delivery problem, optimization is formulated from the service providers’ perspective applied to (EV) with economically efficient but small batteries in very urbanized areas. It aims determine best route origin final destination each EV satisfy welfare all...

In this paper, we explore the role of emerging energy brokers (middlemen) in a localized event-driven market (LEM) at distribution level for facilitating indirect customer-to-customer trading. This proposed LEM does not aim to replace any existing service or become best model; but instead diversify ecosystem edge networks. light philosophy, mechanism will provide additional options customers and prosumers who have willingness directly participate retail electricity occasionally, on top using...

In this paper, we model prosumers' energy trading behavior, with the operation of an storage system, in a proposed event-driven local market. Through modeling strategies prosumer holistic market model, prosumer's decision-making process will be built as Markov decision many continuous variables. Then, participation solved by deep reinforcement learning technology experience replay mechanism. Specifically, Q-learning for algorithm is modified from Q-network to facilitate such within...

With the development of Internet Things (IoT) technologies, implementing intelligent controls in buildings to reduce energy consumption is becoming increasingly popular. Building climate control strong research interest due high savings potentials associated with heating, ventilation, and air-conditioning (HVAC) controls. Because operation HVAC systems directly influences occupant thermal comfort, building-specific models are needed for proper control. Such describe how indoor temperature...

The increasing of grid-connected variable renewable energy (VRE) on the demand side causes balance problems in power system. Thus, dealing with uncertainty, variability, and consequently, flexibility requirement is becoming an urgent challenge to system operators. Virtual plant (VPP), which bundles different types small-scale distributed resources (DERs) into a single unit for optimization will effectively mitigate those uncertainties. An optimal VPP management method proposed this article...

With development of mobile internet and finance, fraud risk comes in all shapes sizes. This paper is to introduce the Fraud Risk Management at Alibaba under big data. has built a monitoring management system based on real-time data processing intelligent models. It captures signals directly from huge amount user behaviors network, analyzes them using machine learning, accurately predicts bad users transactions. To extend prevention ability external customers, also up product called...

Due to the rapidly-changing technologies in power industry, many new references addressing frameworks and business models of next-generation retail electricity market are entering research community. In particular, considering customers with considerable demand response awareness so-called prosumers localized generation based on distributed energy resources (DERs), infrastructure will be a level playing field for local transactions, strategic pricing scheme design, model design building an...

This paper proposes a novel consensus-based distributed control algorithm for solving the economic dispatch problem of generators. A legacy central controller can be eliminated in order to avoid single point failure, relieve computational burden, maintain data privacy, and support plug-and-play functionalities. The optimal is achieved by allowing iterative coordination local agents (consumers generators). As information, estimation power mismatch shared among generators through communication...

Abstract In this paper, the optimal demand response strategy of a commercial building‐based virtual power plant with real‐world implementation in heavily urbanised area is studied. Instead modelling decision‐making process as an optimisation problem, reinforcement learning method used to seek strategy, which could update its performance minimal manpower manipulation. Specifically, data collection from several buildings, including hotel, shopping mall and office, Huangpu district, Shanghai...

Abstract The intermittency and volatility of renewable energy have been major challenges in modern power systems. This paper proposes a self‐adaptive management strategy based on deep reinforcement learning (DRL) to integrate sources into system comprising compressed air storage, battery storage systems, solid oxide fuel cells. However, the basic deterministic policy gradient algorithm lacks sensitivity environmental changes, particularly when there is mismatch module capacity within system....

The power consumption of inverter air conditioners (IACs) can be regulated flexibly by adjusting the compressor's operating frequency, which has been proven suitable for providing regulation capacities to systems. Considering rapid phasing out traditional generating units, massive IACs create huge alternative potential. However, impact on system's stability is rarely studied. To address this issue, article proposes modeling and control methods provide On basis, a novel system model with loop...

This paper proposes an innovative economic and engineering coupled framework to encourage typical flexible loads or load aggregators, such as parking lots with high penetration of electric vehicles, participate directly in the real-time retail electricity market based on integrated eVoucher program. The program entails demand side management, either positive negative direction, following a popular customer-centric design principle. It provides extra benefit end-users reduces risk associated...

Currently, critical peak load caused by residential customers has attracted utility companies and policymakers to pay more attention demand response (RDR) programs. In typical RDR programs, react the price or incentive-based signals, but actions can fall behind flexible market situations. For those equipped with smart meters, they may contribute DR loads if participate in events a proactive way. this paper, we propose comprehensive framework which provide day-ahead (DAM). We model evaluate...

This paper presents an open-circuit (OC) fault diagnosis method of three-phase voltage-source inverters (VSIs) for permanent magnet synchronous motor (PMSM) drive systems based on the hybrid system model (HSM). On basis phase voltage analysis, HSM PMSM-inverter was established, which can describe more accurately. To quickly diagnose whether occurs, a current estimator constructed healthy HSM. Different types VSI be simulated synchronously by HSM, and similarity between each type actual one...

With the rapid development of demand-side management technologies, load serving entities (LSEs) may offer demand response (DR) programs to improve flexibility power system operation. Reliable aggregation is critical for LSEs profits in electricity markets. Due uncertainty, actual aggregated loads obtained by conventional methods can experience significant deviations from bidding value, making it difficult develop an optimal and scheduling strategy. In this paper, a bi-level model proposed...