A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems

The new generation of artificial intelligence (AI), called AI 2.0, has recently become a research focus. Data‐driven AI 2.0 will accelerate the development of smart energy and electric power system (Smart EEPS). In AI 2.0, machine learning (ML) forms a typical representative algorithm category used to achieve predictions and judgments by analyzing and learning from massive amounts of historical and synthetic data to help people make optimal decisions. ML has preliminarily been applied to the Smart Grid (SG) and Energy Internet (EI) fields, which are important Smart EEPS representatives. AI 2.0, especially ML, is undergoing a critical period of rapid development worldwide and will play an essential role in Smart EEPS. In this context, this study, combined with the emerging SG and EI technologies, takes the typical representative of AI 2.0—ML—as the research objective and reviews its research status in the operation, optimization, control, dispatching, and management of SG and EI. The paper focuses on introducing and summarizing the mainstream uses of seven representative ML methods, including reinforcement learning, deep learning, transfer learning, parallel learning, hybrid learning, adversarial learning, and ensemble learning, in the SG and EI fields. In this survey, we begin with an introduction to these seven types of ML methods and then systematically review their applications in Smart EEPS. Finally, we discuss ML development under the big data thinking and offer a prospect for the future development of AI 2.0 and ML in Smart EEPS. We conduct this survey intended to arouse the interest and excitement of experts and scholars in the EEPS industry and to look ahead to efforts that jointly promote the rapid development of AI 2.0 in the Smart EEPS field.     

Energy use, cost and CO2 emissions of electric cars

We examine efficiency, costs and greenhouse gas emissions of current and future electric cars (EV), including the impact from charging EV on electricity demand and infrastructure for generation and distribution.Uncoordinated charging would increase national peak load by 7% at 30% penetration rate of EV and household peak load by 54%, which may exceed the capacity of existing electricity distribution infrastructure. At 30% penetration of EV, off-peak charging would result in a 20% higher, more stable base load and no additional peak load at the national level and up to 7% higher peak load at the household level. Therefore, if off-peak charging is successfully introduced, electric driving need not require additional generation capacity, even in case of 100% switch to electric vehicles.GHG emissions from electric driving depend most on the fuel type (coal or natural gas) used in the generation of electricity for charging, and range between 0 g km⁻¹ (using renewables) and 155 g km⁻¹ (using electricity from an old coal-based plant). Based on the generation capacity projected for the Netherlands in 2015, electricity for EV charging would largely be generated using natural gas, emitting 35-77 g CO_2 eq km⁻¹.We find that total cost of ownership (TCO) of current EV are uncompetitive with regular cars and series hybrid cars by more than 800 € year⁻¹. TCO of future wheel motor PHEV may become competitive when batteries cost 400 € kWh⁻¹, even without tax incentives, as long as one battery pack can last for the lifespan of the vehicle. However, TCO of future battery powered cars is at least 25% higher than of series hybrid or regular cars. This cost gap remains unless cost of batteries drops to 150 € kWh⁻¹ in the future. Variations in driving cost from charging patterns have negligible influence on TCO.GHG abatement costs using plug-in hybrid cars are currently 400-1400 € tonne⁻¹ CO_2 eq and may come down to −100 to 300 € tonne⁻¹. Abatement cost using battery powered cars are currently above 1900 € tonne⁻¹ and are not projected to drop below 300-800 € tonne⁻¹.     

Robust controller design of heat pump and plug-in hybrid electric vehicle for frequency control in a smart microgrid based on specified-structure mixed H2/H∞ control technique

This paper proposes a new robust controller design of heat pump (HP) and plug-in hybrid electric vehicle (PHEV) for frequency control in a smart microgrid (MG) system with wind farm. The intermittent power generation from wind farm causes severe frequency fluctuation in the MG. To alleviate frequency fluctuation, the smart control of power consumption of HP and the power charging of PHEV in the customer side can be performed. The controller structure of HP and PHEV is a proportional integral derivative (PID) with single input. To enhance the performance and robustness against system uncertainties of the designed controller, the particle swarm optimization based-mixed H₂/H_∞ control is applied to design the PID controllers of HP and PHEV. Simulation studies confirm the superior robustness and frequency control effect of the proposed HP and PHEV controllers in comparison to the conventional controller.     

Regulatory framework and business models for charging plug-in electric vehicles: Infrastructure,agents, and commercial relationships

Electric vehicles (EVs) present efficiency and environmental advantages over conventional transportation. It is expected that in the next decade this technology will progressively penetrate the market. The integration of plug-in electric vehicles in electric power systems poses new challenges in terms of regulation and business models. This paper proposes a conceptual regulatory framework for charging EVs. Two new electricity market agents, the EV charging manager and the EV aggregator, in charge of developing charging infrastructure and providing charging services are introduced. According to that, several charging modes such as EV home charging, public charging on streets, and dedicated charging stations are formulated. Involved market agents and their commercial relationships are analysed in detail. The paper elaborates the opportunities to formulate more sophisticated business models for vehicle-to-grid applications under which the storage capability of EV batteries is used for providing peak power or frequency regulation to support the power system operation. Finally penetration phase dependent policy and regulatory recommendations are given concerning time-of-use pricing, smart meter deployment, stable and simple regulation for reselling energy on private property, roll-out of public charging infrastructure as well as reviewing of grid codes and operational system procedures for interactions between network operators and vehicle aggregators.