• Energy Research

Internet of Things (IoT) technology provides the necessary foundation and support for smart city water management. To address the challenge of river pollution prevention and flood control requirements in the urban river system, this article proposes a data-driven model to carry out the optimal operation scheduling of water diversion and drainage pumping stations in the presence of the complex hydrometeorological constraints. The proposed solution in the model predictive control (MPC) framework first adopts the long short-term memory (LSTM) network through supervised learning from IoT data to simulate and predict the river flow dynamics and the water quality. Consequently, the optimal scheduling of controllable pumping stations to minimize the operational cost (e.g., the flocculant consumption) can be formulated as a stochastic optimization problem, while meeting the river flood control and water quality constraints. The particle swarm optimization (PSO) algorithm is further used to solve the above unit commitment (UC) optimization problem and obtain the optimal operational schedules of the water pumping units (e.g., startup time and working periods). The performance of the proposed optimal water pumping scheduling solution is evaluated through a field case study of the urban river diversion system and the numerical results clearly confirm its effectiveness and improved economic performance compared to the existing benchmark solution.

Abstract The current power systems are undergoing a rapid transition towards their more active, flexible, and intelligent counterpart smart grid, which brings about tremendous challenges in many domains, e.g., integration of various distributed renewable energy sources, cyberspace security, demand-side management, and decision-making of system planning and operation. The fulfillment of advanced functionalities in the smart grid firmly relies on the underlying information and communication infrastructure, and the efficient handling of a massive amount of data generated from various sources, e.g., smart meters, phasor measurement units, and various forms of sensors. In this paper, a comprehensive survey of over 200 recent publications is conducted to review the state-of-the-art practices and proposals of machine learning techniques and discuss the trend in a wide range of smart grid application domains. This study demonstrates the increasing interest and rapid expansion in the use of machine learning techniques to successfully address the technical challenges of the smart grid from various aspects. It is also revealed that some issues still remain open and worth further research efforts, such as the high-performance data processing and analysis for intelligent decision-making in large-scale complex multi-energy systems, lightweight machine learning-based solutions, and so forth. Moreover, the future perspectives of utilizing advanced computing and communication technologies, e.g., edge computing, ubiquitous internet of things and 5G wireless networks, in the smart grid are also highlighted. To the best of our knowledge, this is the first review of machine learning-driven solutions covering almost all the smart grid application domains. Machine learning will be one of the major drivers of future smart electric power systems, and this study can provide a preliminary foundation for further exploration and development of related knowledge and insights.

Abstract The intelligent decision making of multi-energy management in a microgrid is a non-trivial task due to the intermittent and stochastic nature of highly penetrated renewable energy sources and demand. To address such a challenge, the energy management system often adopts the prediction based day-ahead energy scheduling and real-time energy dispatch to optimally coordinate the operation of dispatchable components, e.g., battery-based energy storage and thermal units. This paper presents an adaptive optimal fuzzy logic based energy management solution to develop appropriate day-ahead fuzzy rules for real-time energy dispatch adaptively in the presence of operational uncertainties. The solution determines the optimal fuzzy inference system (e.g., the membership function shape and the inference rules set) based on the predicted information over a certain period through a novel offline meta-heuristic optimization algorithm. The real-time energy dispatch based on the obtained optimal fuzzy logic rules can be further carried out to meet the various operational criteria, e.g., minimal power fluctuation and operational cost. The proposed solution is extensively evaluated through simulation experiments in comparison with two existing approaches: the online rule-based dispatch method and the meta-heuristic optimization-based offline scheduling method. The numerical results demonstrate the superior performance of the proposed energy management solution.

The paradigm of the Internet of Things (IoT) and cloud-edge computing plays a significant role in future smart grids. The data-driven solution integrating the artificial intelligence functionalities brings novel methods to address the nontrivial task of economic dispatch in microgrids in the presence of uncertainties of renewable generations and loads. This article proposes a learning-based decision-making framework for the economic energy dispatch of an islanding microgrid based on the cloud-edge computing architecture. Cloud resources are utilized to solve the optimal dispatch decision sequences over historical operating patterns. It can be considered as a sample labeling process for the supervised training that can implement the complex mapping of input–output space through an advanced machine learning model. Then, the well-trained model can be adopted locally at edge computing devices keeping the long-term parameters unchanged for implement the real-time microgrid energy dispatch. The key benefit of the proposed solution is that it effectively avoids the prediction of multiple stochastic variables and the design of sophisticated regulation strategies or reward policy functions for real-time dispatch. The solution is extensively assessed through simulation experiments by the use of real data measurements for a set of operational scenarios and the numerical results validate the effectiveness and benefit of the proposed algorithmic solution.