Socio-technical smart grid optimization via decentralized charge control of electric vehicles

Abstract

The penetration of electric vehicles becomes a catalyst for the sustainability of Smart Cities. However, unregulated battery charging remains a challenge causing high energy costs, power peaks or even blackouts. This paper studies this challenge from a socio-technical perspective: social dynamics such as the participation in demand-response programs, the discomfort experienced by alternative suggested vehicle usage times and even the fairness in terms of how equally discomfort is experienced among the population are highly intertwined with Smart Grid reliability. To address challenges of such a socio-technical nature, this paper introduces a fully decentralized and participatory learning mechanism for privacy-preserving coordinated charging control of electric vehicles that regulates three Smart Grid socio-technical aspects: (i) reliability, (ii) discomfort and (iii) fairness. In contrast to related work, a novel autonomous software agent exclusively uses local knowledge to generate energy demand plans for its vehicle that encode different battery charging regimes. Agents interact to learn and make collective decisions of which plan to execute so that power peaks and energy cost are reduced system-wide. Evaluation with real-world data confirms the improvement of drivers' comfort and fairness using the proposed planning method, while this improvement is assessed in terms of reliability and 1 Stampfenbachstrasse 48, 8092,cost reduction under a varying number of participating vehicles. These findings have a significant relevance and impact for power utilities and system operator on designing more reliable and socially responsible Smart Grids with high penetration of electric vehicles.

(So) Big Data and the transformation of the city

“…Citizens' participation in bottom-up sharing economies of smart cities can contribute to several sustainability goals of the United Nations [61]. Three application scenarios are On the left: a tree structure with the analytical steps already computed are shown; in the center, the geographic layers selected on the tree are shown; on the right, the panel where data analytical tools are listed studied: (i) residential energy management, (ii) charging management of electric vehicles to improve the smart grid reliability, and (iii) managing the utilization of shared bikes to improve the load balancing of bike sharing stations [96,98]. Sharing economies in the aforementioned application scenarios face a foundational challenge of aligning individual (citizens) and collective (system/city) objectives.…”

Holarchic structures for decentralized deep learning: a performance analysis

“…The bike sharing dataset 6 of the Hubway bike sharing system 7 in Paris is used to generate a varying number of plans of size 98 for each agent based on the unique historic trips performed by each user. Therefore, the plans represent the trip profiles of the users and they contain the number of incoming/outgoing bike changes made by each user in every station [37]. The local cost of each plan is defined by the likelihood of a user to not perform a trip instructed in the plan [38].…”

“…Four plans per agent with size 1440 are generated by extracting the vehicle utilization using the historical data and then computing the state of charge by redistributing the charging times over different time slots. The methodology is outlined in detail in earlier work [37]. The local cost of each plan is measured by the likelihood of the vehicle utilization during the selected charging times.…”

Structural Self-Adaptation for Decentralized Pervasive Intelligence

“…These options are resource consumption or production plans that are used for resource scheduling and allocation. For instance, a plan p can represent when a user charges its electric vehicle [6], the household energy demand over time, or the bike sharing stations from which a user picks up a bike or leaves one [2]. In practice, plans are sequences of real values.…”

“…7 A third real-world dataset is made available [33]. It concerns the charging power consumption of electric vehicles and the planning methodology is introduced in earlier work [6]. This paper focuses on the synthetic, energy and bicycle datasets due to space limitations.…”