Reinforcement learning in sustainable energy and electric systems: a survey
یادگیری تقویتی در سیستم های انرژی پایدار و الکتریکی: یک نظرسنجی-2020
The dynamic nature of sustainable energy and electric systems can vary significantly along with the en- vironment and load change, and they represent the features of multivariate, high complexity and uncer- tainty of the nonlinear system. Moreover, the integration of intermittent renewable energy sources and energy consumption behaviours of households introduce more uncertainty into sustainable energy and electric systems. The operation, control and decision-making in such an environment definitely require increasing intelligence and flexibility in the control and optimization to ensure the quality of service of sustainable energy and electric systems. Reinforcement learning is a wide class of optimal control strate- gies that uses estimating value functions from experience, simulation, or search to learn in highly dy- namic, stochastic environment. The interactive context enables reinforcement learning to develop strong learning ability and high adaptability. Reinforcement learning does not require the use of the model of system dynamics, which makes it suitable for sustainable energy and electric systems with complex non- linearity and uncertainty. The use of reinforcement learning in sustainable energy and electric systems will certainly change the traditional energy utilization mode and bring more intelligence into the system. In this survey, an overview of reinforcement learning, the demand for reinforcement learning in sustain- able energy and electric systems, reinforcement learning applications in sustainable energy and electric systems, and future challenges and opportunities will be explicitly addressed.
Keywords: Reinforcement learning | Sustainable energy and electric systems | Deep reinforcement learning | Power system | Integrated energy system
Regional integrated energy system energy management in an industrial park considering energy stepped utilization
مدیریت انرژی سیستم انرژی یکپارچه منطقه ای در یک پارک صنعتی با توجه به استفاده پله ای از انرژی -2020
There are multiple energy demands in industrial parks. The industrial park’s energy system includes a variety of energy sources and energy-consuming equipment, with diverse load types and high reliability requirements for power supplies. And the situation of low energy utilization rates, unreasonable energy structures, great peak-to-valley power differences and the environment pollution needs to be improved. The application of multi-energy complementary regional integrated energy systems (RIES) can improve the performance of the industrial parks. Considering reasonable correspondence between the energy supply and demand in RIES, this paper proposes an RIES energy management strategy based on energy stepped utilization to further minimize the daily cost and make full use of the energy. Additionally, the piecewise linear model of gas turbine is established considering a part load ratio. According to the grade demands, the heat loads are divided into high-grade, middle-grade and low-grade heat loads and the load models are respectively established. The scenario reduction method is used to obtain typical scenarios in order to describe the randomness of weather factors. Finally, the simulation analysis shows that the proposed energy management method for the RIES can arrange the combination of gas turbines and output of devices more flexibly, and a more economical scheduling plan can be provided by this method. The high-grade and middle-grade energy are not only supplied to corresponding loads, but also can be converted into low-grade energy. Additionally, the stability and energy efficiency of the system are improved with the application of this strategy.
Keywords: Regional integrated energy system | Stepped utilization of energy | Mixed integer linear programming | Industrial park | Economic dispatching