Distributed machine learning for energy trading in electric distribution system of the future

Machine Learning (ML) has seen a great potential to solve many power system problems along with its transition into Smart Grid. Specifically, electric distribution systems have witnessed a rapid integration of distributed energy resources (DERs), including photovoltaic (PV) panels, electric vehicles (EV), and smart appliances, etc. Electricity consumers, equipped with such DERs and advanced metering/sensing/computing devices, are becoming self-interested prosumers who can behave more actively for their electric energy consumption. In this paper, the potential of distributed ML in solving the energy trading problem among prosumers of a future electric distribution system - building DC grid cell, is explored, while considering the limited computation, communication, and data privacy issues of the edge entities. A fully distributed energy trading framework based on ML is proposed to optimize the load and price prediction accuracy and energy trading efficiency. Computation resource allocation, communication schemes, ML task scheduling, as well as user sensitive data preserving issues in the distributed ML framework are addressed with consideration of all the economic and physical constraints of the electric distribution systems.     

P2P模式下产消者交易模型建立与仿真验证

随着新电改环境下售电侧放开,越来越多的产消者资源愿意参与到电力市场中以减少自身的用电开支,如何在P2P（peer-to-peer）交易模式下制定产消者购售电模型成为一个亟待解决的问题。首先,以含光伏（photovoltaic, PV）,微型燃气轮机和固定负荷资源组成的多个产消者集群为研究对象,建立了产消者资源约束模型。其次,采用拉格朗日对偶分解原理和次梯度法以产消者运行成本最小为目标制定了基于P2P市场交易模式的产消者购售电计划。在保证用户的信息安全的同时实现了产消者之间的P2P电能共享。最后通过算例验证了所提策略的合理性和有效性。     

局域能源市场多产消者P2P交易框架设计

随着局域能源市场中分布式能源的大量接入和电力系统运行方式的逐渐转变,具有电能生产/消费行为的产消者得到了广泛关注与研究。在此背景下,为提高小规模能源在局域能源市场中的就地消纳能力,设计了一种面向局域能源市场中多产消者的点对点(P2P)日前市场交易框架。在局域能源市场建立了P2P市场交易平台,并对产消者的基本特征进行了归纳分析,提出了典型的产消者组合类型;在产消者层面,采用供给函数均衡模型对产消者竞价行为进行建模,确立了含多产消者的P2P交易平台参与局域能源市场交易;采用连续双边拍卖机制对产消者之间进行P2P匹配,并确定交易过程中的拍卖价格和交易价格。最后,通过算例验证了所提P2P交易框架的有效性。     

Novel economic modelling of a peer-to-peer electricity market with the inclusion of distributed energy storage—The possible case of a more robust and better electricity grid

Current electricity distribution systems allow prosumers to sell their surplus electricity back to the Distributed Network Operator (DNO). The export tariffs at which these sell-backs take place are considerably lower than the feed-in tariffs, offering little incentive to prosumers to sell their surplus energy. A peer-to-peer (P2P) electricity market where consumers and prosumers can interact by selling and buying energy between them at a premium rate that is lower than the standard feed-in tariffs but higher than the export tariffs is proposed. Such a system was modelled to process transactions every 20 s, and a simulation tool was created to obtain the total daily money flows between a consumer-prosumer pair. The inclusion of a Distributed Storage System (DSS) is also considered in the modelled system and simulation. The simulation results showed that the inclusion of a DSS is always beneficial for all parties in economic terms: consumers could save up to 6.4 % on the cost of their electricity while prosumers could save up to 49.1 %. A DSS could generate an income flow for the DNO of up to 6.9p/day per each consumer-prosumer pair.     

基于集中-分散交易机制的多产消者两阶段鲁棒优化模型

针对产消者参与电力市场交易过程中的不确定性,提出一种多产消者两阶段鲁棒集中-分散交易模型.考虑产消者之间可进行点对点分散交易,建立多产消者集中-分散市场交易模型;考虑光伏出力不确定性对交易策略的影响,构建多产消者两阶段鲁棒市场交易模型;采用Nash谈判法实现多产消者合作剩余的公平分配.仿真算例验证了所建模型的有效性.     

Valuation of distributed energy resources in active distribution networks

In concert with the transformation of conventional passive power distribution system, distributed energy resources (DERs) have progressively become participants in the provision of electricity services in active distribution networks (ADNs). In this paper, we propose a systematic valuation process to quantify the value of DERs in the ADN context. The paper first provides comprehensive insights into the impacts of DERs on ADN and the society as a whole. Given the technological, locational, and temporal diversity of DERs, a two-part scheme is developed to value and compensate DER portfolios proposed by customers and independent third parties. In particular, DERs are valued for their benefits and costs in both short and long terms. An integrated resource planning model is formulated to quantify the value of a given DER portfolio to be installed, where bi-level optimization techniques are applied to coordinate decisions on ADN planning and operations. In order to determine the short-term operation benefits of the DER portfolio on a continuous basis, a retail market operation model is developed based on peer-to-peer energy transactions among prosumers, when the impacts of DERs on ADN operations are monetized by distribution locational marginal prices. It is finally concluded in the paper that the proposed valuation scheme will not only contribute to the proactive investment of DERs in ADN but also help enhance the role of DERs in offering affordable, reliable, resilient and sustainable electricity services to customers.     

基于模型预测控制的能源产消者端对端交易策略

新能源政策市场化无补贴发展背景下,为保障分布式光伏资源的消纳,须探索有效的市场机制,发挥用户调动灵活性资源的主动性。端对端(Peer-to-Peer, P2P)能源交易作为本地电力消费者和生产者间直接能源交易模式,有利于局部区域功率平衡。采用连续双向拍卖市场机制,提出基于模型预测控制的P2P市场交易策略。针对储能参与后的产消者电量投标决策问题,利用模型预测控制滚动优化储能的充放电功率,指导市场主体的电量投标。在此基础上,将具有学习能力的增强零信息策略作为报价方法,实现各主体的自主决策。辽西某区域电网算例结果表明：所提方法能够有效调动市场主体的积极性,指导其投标行为,进一步增加个体收益,提高配网接纳分布式光伏的能力。     

含分布式电源P2P交易的社区微网运营机制

随着越来越多的分布式电源通过微网接入配电网,在微网中开展基于分布式交易机制的新能源交易可以有效提高分布式主体的效益,促进新能源的投资建设。文章构造可交易能源系统在社区微网运营中的应用场景,建立适合含有分布式电源和储能的社区微网用户之间的P2P交易模型。微网用户可以在P2P市场中对需求或多余电量以按报价支付的方式交易,将交易形成智能合约,存储在分布式网络中并自动执行。最后用实际微网的仿真算例验证新能源分布式交易对社区微网中所有用户效益的促进作用。     

基于二级聚集式的端对端电力交易控制策略

为更好地实现端对端电力交易,提出了二级聚集式控制策略。该策略只需一个数据监测点和从监测点到产消者的单向通信就能够实现端对端电力交易。其中,第一级控制采用带约束的非线性优化,以最小化社区微电网电费为目标,第二级控制采用基于规则的实时控制策略。通过仿真算例验证了控制策略的有效性,并对比分析了在社区微电网中采用集中式和分布式蓄电池对电能损耗及电费的影响。     

Rooftop solar adoption among populations and markets outside the US and Europe–A case from Pakistan

With substantial decrease in the cost of renewable energy technologies (RETs), governments around the world stepped up efforts to transform the ways energy is produced, and the manners it is consumed. Focusing on attainment of SDG-7 through clean energy transition, the aim has been to achieve energy security as well as energy equity while reducing dependence on energy imports. Although ongoing technological breakthroughs and maturity offers promising opportunities, many developing nations are grappling with intertwined socioeconomic dynamics and policy prioritization. Under the resource-constrained financial situation, Government of Pakistan adopted prosumers’ approach to harness year-round available solar energy. Regulatory measures were accordingly instituted, and the electricity distribution companies (DISCOs) were instructed to facilitate people in becoming prosumers. The adoption rates were however well short of the desired outcomes. Besides cultural and socioeconomic dynamics, human interaction with technology, and their level of awareness about related policy parameters play critical role in the technology adoption. In part, this realization led Institute of Policy Studies (IPS) Pakistan to conduct a survey on the consumers’ willingness for taking up the prosumers’ role and, on the parameters contributing to their decision e.g., economic conditions, energy quality and reliability, relevant government policies, and their level of awareness about going solar. Utilizing data from the IPS survey, this study explored the linkage between consumers’ inclination to install solar energy systems and their awareness about solar photovoltaics (PV) technology, the cost factor and relevant government policies. The study revealed significant correlation between target populace’s awareness level and their willingness to become prosumers, highlighting the need for taking policy measures to enhance public awareness on relevant aspects of roof-top solar (RTS) for their due contribution towards sustainable energy solutions in Pakistan.     

基于主从博弈的含电动汽车虚拟电厂协调调度

电动汽车作为配电网中最为重要的主动负荷,其充电优化管理成为目前售电侧开放下的重点研究领域之一。而虚拟电厂作为电网分布式能源管理的重要解决方案,其传统定义侧重于在发电侧聚合小容量分布式能源以提高可再生能源在电网中的消纳程度。结合售电侧开放下的电力市场改革需求,文中提出以虚拟电厂作为售电实体参与电动汽车充电管理的协调调度优化模型。在能量市场交易模型中,虚拟电厂作为分布式能源与电动汽车的聚合代理商参与电力市场电能申报与交易;在主从博弈模型中,虚拟电厂通过主从博弈制定合理的售电价格引导电动汽车的有序充电入网,并通过协调调度集中整合优化分布式能源。算例分析表明,通过虚拟电厂的集中优化管理可以有效实现分布式能源与电动汽车的能源互补并提升整体运行经济性。     

基于交互能源机制的产消者能量管理方法

光伏等可再生能源在配电网中渗透率不断提高使得负荷侧由单一的用电形式向着兼具发、用电双重特性的产消者资源转变。随着产消者以个体形式参与电力市场的意愿不断增强,传统以用户购电为主的集中式电力市场交易模式已不能满足市场参与者的需求。为了提高分布式能源的接入比例,提高灵活可控的产消者主体经济性,文章根据交互能源机制中常见的弱中心化和去中心化市场交易框架建立了以产消者用电成本最小为目标的市场交易模型和产消者能量管理策略。最后,基于算例对比分析传统电力市场交易模式和文章所提的两种交互能源机制,证明了所提的两种交互能源机制的合理性和有效性。     

支持现货市场的分布式电力交易机制设计与实现

伴随电力体制改革的不断深入和分布式能源的大量接入,电力现货交易的商业模式正在被不断探索,亟需提出新的交易机制来适应新的商业模式。首先,基于去中心化的思想设计了一种适用于日内现货市场的分布式电力交易机制,激励产消者根据自身实际发电能力或用电情况发起实时的点对点交易需求,就近与周边产消者用户直接进行交易。然后,应用区块链技术以智能合约的形式规定交易规则,明确产消者的权利与义务。最后,结合智能电表与智能终端搭建具有两层互操作层的分布式电力交易平台,多信息融合通信,支撑交易自动出清与结算。提出的分布式电力交易机制可实现产消者点对点多边竞价交易,鼓励产消者合理申报交易需求,实现能源的高效分配、合理利用。     

适应分布式发电交易的分散式电力市场探讨

随着可再生能源发电技术的成熟及安装运行成本的不断降低,分布式发电得到了快速的发展,并由此产生了大量的电力产消者。然而分布式发电由于容量小、波动性大、分布零散等特点,并不适合参与现行的电力市场。针对此问题,文中结合国外电力零售市场研究和中国分布式电力交易的实际情况提出了一种配电网层面下的分散式电力市场模式,并分别从市场定义、参与主体、交易方式、时间尺度、出清方式等方面进行了分散式电力市场的框架设计。然后,针对分散式电力市场交易平台难以建立的问题,研究了将区块链技术应用于分散式电力市场构建的可行性及交易实现流程。最后,分别从政策法规和市场建设要点2个方面分析了构建分散式电力市场需要注意的问题。     

基于区块链和动态定价模型的微电网P2P能源交易

微电网之间的能源贸易可以减少对公用大电网的依赖。研究了基于区块链的微电网对等能源交易,微电网中的消费者和生产者不需要第三方就可以交易能源,在提出的模型中引入了滞期费机制,构建动态定价模型,使微电网优化能源消耗并最大程度地减少电费,并为微电网提供了足够的能量。仿真结果验证了所提模型的有效性。     

基于区块链技术的光伏产消者集群定价博弈

随着具有源荷二重属性的产消者占比日益提高,如何建立适合产消者的有效交易机制,激励其能源消纳是目前亟待解决的问题。针对该问题,提出区块链技术下的产消者与运营商的集群交易模型,将区块链技术量化到产消者的用电行为上。考虑到产消者集群内各主体独立,电价制定和电量调度存在先后次序,采取Stackelberg博弈理论寻求最优交互策略,并通过区块链更新求解过程中的交互信息。仿真结果表明：通过制定内部电价,能够提升集群内的光伏自消纳水平,同时在区块链技术下聚合优化集群内资源,可以有效提高产消者的用电效益与运营商的收益。进一步,结合光伏上网电价退坡政策,再次验证了所提模型的有效性。     

考虑需求侧灵活性资源的区域电能共享市场模型

提出考虑需求侧灵活性资源、用于区域电能共享市场的双侧竞拍机制,市场内包含分布式太阳能产消者和消费者。假设所有产消者和消费者形成的代理商拥有灵活的可按需求响应利用的聚合电动汽车和储能设备。首先,采用鲁棒虚拟电池模型描述价格激励下聚合电动汽车灵活性,实现可靠经济地扩大储能容量。然后,代理商在区域电能共享中设置最优的储能系统充放电计划,降低用电成本。之后,将管理好的产消者和消费者用于市场,为计算双侧竞拍市场的现货价格,所有区域产消者和消费者采用非合作博弈。提出迭代算法用于出清市场和最小化供需电能不确定性。最后,以区域内10个代理商为例,验证描述需求侧灵活性资源的虚拟电池模型和区域电能共享市场模型有效性。     

基于主从博弈的新型城镇配电系统产消者竞价策略

随着能源互联技术的发展以及售电侧市场的逐步放开,新型城镇配电系统在优化运行和交易模式上呈现多能协同、交易开放的特征。新型城镇配电系统的电力零售交易机制被重新定义,产消者通过非合作竞争上报最优竞标曲线获取最大售电收益,电网公共服务企业收取过网费并提供保底供电服务,用户可基于实时电价与激励政策参与需求响应降低用电成本。在此背景下,充分考虑配电网内多角色的主动参与以及运营商的经济调度要求,建立一种基于主从动态博弈理论的产消者非合作竞价双层模型。以改进的IEEE 33节点配电网为算例,采用改进粒子群优化算法与CPLEX求解器相结合的方法,求得该主从博弈模型的均衡解。仿真结果表明,该策略可以在保证电网公共服务企业和用户利益基础上实现产消者利润最大化,为新型城镇电力零售市场的交易模式提供参考。     

A Consortium Blockchain-Enabled Double Auction Mechanism for Peer-to-Peer Energy Trading among Prosumers

This paper investigates a double auction-based peer-to-peer (P2P) energy trading market for a community of renewable prosumers with private information on reservation price and quantity of energy to be traded. A novel competition padding auction (CPA) mechanism for P2P energy trading is proposed to address the budget deficit problem while holding the advantages of the widely-used Vickrey-Clarke-Groves mechanism. To illustrate the theoretical properties of the CPA mechanism, the sufficient conditions are identified for a truth-telling equilibrium with a budget surplus to exist, while further proving its asymptotical economic efficiency. In addition, the CPA mechanism is implemented through consortium blockchain smart contracts to create safer, faster, and larger P2P energy trading markets. The proposed mechanism is embedded into blockchain consensus protocols for high consensus efficiency, and the budget surplus of the CPA mechanism motivates the prosumers to manage the blockchain. Case studies are carried out to show the effectiveness of the proposed method.     

考虑端对端交易与预测误差的配电网实时能量平衡策略

端对端(peer-to-peer, P2P)交易下产消者发电具有较强的波动性和不确定性，其实时发电情况往往与日前计划存在偏差。针对采用连续双向拍卖机制(continuous double auction, CDA)的P2P交易下产消者出现的实时不平衡问题，提出了一种考虑P2P交易时序特征的本地能量平衡策略。系统运营商(system operator, SO)利用模型预测控制方法，以总体平衡成本最小为目标，考虑了SO和平衡服务提供方的成本效益约束，建立基于日前P2P能量市场和实时平衡市场协调运行机制的本地能量平衡策略模型。在实时平衡市场中，SO从责任方收取的补偿费用于从服务提供方购买灵活性平衡服务。仿真结果表明，平衡服务提供方帮助平衡了本地78%的实时不平衡电量。与电网平衡策略相比，本地化的实时平衡市场成本是电网平衡成本的三分之一。同时保障了平衡服务提供方及SO的收益，促进光伏能源消纳，利于P2P交易市场长久发展。