Current Issue

  • Direct Load Control of Thermostatically Controlled Loads Based on Sparse Observations Using Deep Reinforcement Learning

    Abstract

      2019-12-16

    This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of features from these observations is a challenging task and may require substantial domain knowledge. One way to tackle this problem is to store sequences of past observations and actions in the state vector, making it high dimensional, and apply techniques from deep learning. This paper investigates the capabilities of different deep learning techniques, such as convolutional neural networks and recurrent neural networks, to extract relevant features for finding near-optimal policies for a residential heating system and electric water heater that are hindered by sparse observations. Our simulation results indicate that in this specific scenario, feeding sequences of time-series to an Long Short-Term Memory (LSTM) network, which is a specific type of recurrent neural network, achieved a higher performance than stacking these time-series in the input of a convolutional neural network or deep neural network.

     

  • Overview of Mechanism and Mitigation Measures on Multi-frequency Oscillation Caused by Large-scale Integration of Wind Power

    Abstract

      2019-12-16

    In recent years, the large-scale integration of renewable energy sources represented by wind power and the widespread application of power electronic devices in power systems have led to the emergence of multi-frequency oscillation problems covering multiple frequency segments, which seriously threaten system stability and restrict the accommodation of renewable energy. The oscillation problems related to renewable
    energy integration have become one of the most popular topics in the field of wind power integration and power system stability research. It has received extensive attention from both academia and industries with many promising research results achieved to date. This paper first analyzes several typical multi-frequency oscillation events caused by large-scale wind power integration in domestic and foreign projects, then studies the multi-frequency oscillation problems, including wind turbine’s shafting torsional oscillation, sub/super-synchronous oscillation and high frequency resonance. The state of the art is systematically summarized
    from the aspects of oscillation mechanism, analysis methods and mitigation measures, and the future research directions are explored.

  • Mutual Interactions and Stability Analysis of Bipolar DC Microgrids

    Abstract

      2019-12-16

    This paper presents an Multi-Input Multi-Output (MIMO) analysis to investigate the mutual interactions and small-signal stability of bipolar-type dc microgrids. Since bipolar dc microgrid is replete with power-electronic converters, its dynamics can not be understood unless the interactions among control systems of converters are properly investigated. To tackle the challenge, each converter in microgrid is modeled via an
    MIMO transfer matrix. Then, the MIMO models are combined together based on the interactions among the control systems of source and load converters. From this integrative MIMO model, the mutual interactions between various input-output pairs are quantified using Gershgorin Band theorem. Also, Singular Value Decomposition (SVD) analysis is carried out to estimate the frequency of unstable poles. Test results not only successfully validate the effectiveness of the MIMO method but also show that the control system of voltage balancer has a major impact on the overall stability of bipolar dc microgrid, making it a suitable location for applying damping systems. Index Terms—Bipolar dc microgrid, Gershgorin Band

     

  • Comparison and Error Analysis of Off-design and Design Models of Energy Hubs

    Abstract

      2019-12-16

    The accuracy of the simulation model has a profound impact on the optimal operation of the energy hubs (EHs). However, in many articles, the constant model of the efficiency of equipment is adopted to formulate the operation system, which would probably lead to a simplification of the simulation models. But, EHs are typically operated under off-design condition due to the fluctuations in cooling, heating, electricity

     

  • Multi-objective Dynamic Optimal Power Flow of Wind Integrated Power Systems Considering Demand Response

    Abstract

      2019-12-16

    This paper studies the economic environmental energy-saving day-ahead scheduling problem of power systems considering wind generation (WG) and demand response (DR) bymeans of multi-objective dynamic optimal power flow (MDOPF). Within the model, fuel cost, carbon emission and active powerlosses are taken as objectives, and an integrated dispatch mode  of conventional coal-fired generation, WG and DR is utilized.
    The corresponding solution process to the MDOPF is based on a hybrid of a non-dominated sorting genetic algorithm-II (NSGAII) and fuzzy satisfaction-maximizing method, where NSGA-II
    obtains the Pareto frontier and the fuzzy satisfaction-maximizing method is the chosen strategy. Illustrative cases of different scenarios are performed based on an IEEE 6-unitsn30-nodes
    system, to verify the proposed model and the solution process, as well as the benefits obtained by the DR into power system.

Introduction

CSEEJPESThe articles published in this journal will focus on advanced concepts, technologies, methodologies and practices associated with all aspects concerning power and energy systems...
more...

CSEEJPES WeixinWelcome to follow our Wechat Official Account (CSEEJPES2015)