This paper proposes a novel framework for home energy management (HEM) based on reinforcement learning in achieving efficient home-based demand response (DR). The concerned hour-ahead energy consumption scheduling problem is duly formulated as a finite Markov decision process (FMDP) with discrete time steps. To tackle this problem, a data-driven method based on neural network (NN) and Q-learning algorithm is developed, which achieves superior performance on cost-effective schedules for HEM system. Specifically, real data of electricity price and solar photovoltaic (PV) generation are timely processed for uncertainty prediction by extreme learning machine (ELM) in the rolling time windows. The scheduling decisions of the household appliances and electric vehicles (EVs) can be subsequently obtained through the newly developed framework, of which the objective is dual, i.e. to minimize the electricity bill as well as the DR induced dissatisfaction. Simulations are performed on a residential house level with multiple home appliances, an EV and several PV panels. The test results demonstrate the effectiveness of the proposed data-driven based HEM framework.

Smart cities employ technology and data to increase efficiencies, economic development, sustainability, and life quality for citizens in urban areas. Inevitably, clean technologies promote smart cities development including for energy, transportation and health. The smart city concept is ambitious and is being refined with standards. Standards are used to help with regulating how smart cities function and contributing to define a smart city. Smart cities must be officially recognized by national and international authorities and organizations in order to promote societal advancement. There are many research and review articles on smart cities. However, technical standards are seldom discussed in the current literature. This review firstly presents the study of smart city definitions and domain. The well-known smart city standards will be presented to better recognize the smart city concept. Well-defined standards allow meaningful comparisons among smart cities implementation. How smart city initiatives make a city smarter and improve the quality of life will be discussed for various countries. This review highlights that technical standards are important for smart cities implementation. This paper serves as a guide to the most recent developments of smart cities standards.

Surplus electricity energy from renewable sources can be efficiently utilized by converting it into other forms of energy in the integrated energy system (IES). Local electricity energy sharing can be realized through effective dispatching and independent transaction between producers and consumers. This features the merits on energy consumption and operational cost reduction. In this paper, a novel energy scheduling regime is proposed for the electricity-hydrogen-heat IES clusters under a peer-to-peer (P2P) electricity and heat energy transaction structure. To instantly control the robustness of the scheduling decisions, a weighted MPC strategy is newly proposed for online decision-makings. Furthermore, an adaptive alternating direction method of multipliers (ADMM) with varying penalties algorithm that can effectively preserve prosumer privacy is proposed, which enables the operators to coordinate various parties in the multi-energy microgrids. Extensive case studies based on a typical testing system are carried out, of which the simulation results demonstrate the effectiveness of the proposed scheduling regime and suggest potential for practical application.

High penetration of wind energy in the modern power system exposes the need of smoothing the fluctuating output power in an effective and conducive way. In this context, this paper proposes two novel control strategies that utilize the self-capability of permanent magnet synchronous generator based wind turbine to realize power smoothing. The first strategy pursues to offer power smoothing support via simultaneous utilization of DC-link voltage control, rotor speed control and pitch angle control. The second control strategy seeks to coordinate the three concerned individual control schemes in a hierarchical manner, where the power smoothing tasks are allocated to individual control modules or their combinations dynamically in line with WT's operation status. Both two strategies are able to provide power smoothing support by fully exploiting wind turbine's self-capability, whereas the second strategy has the merits on 1) reducing the activation frequency of pitch angle control, and 2) enhancing wind energy harvesting. Case studies of the proposed control strategies are carried out to compare and verify their effectiveness in achieving power smoothing.

Given the ever-increased penetration of wind power generation in today's power systems, wind farms tend to operate in a dispatchable way to a certain extent by actively fulfilling dispatch orders from system operators. This paper is focused on the challenging issue of coordinating the interactive wind turbines in a wind farm, which are influenced by non-negligible wake effect, to efficiently respond to external dispatch order. To achieve this, a novel control strategy is proposed by 1) effectively allocating power regulation task to individual wind turbines; and 2) utilizing the existing resources (i.e. rotational kinetic energy and pitching capability) of wind turbine to satisfy the dispatch order efficiently and reliably. Extensive case studies on both constant and variable wind speed conditions are carried out to demonstrate the effectiveness of the proposed control strategy. As a comparison, simulations results based on uniform load sharing strategy are also presented. It is exhibited that our proposed strategy has better control performance in terms of total energy harvesting and pitching activation frequency.