Dataset for "Coordination Mechanisms for Electric Vehicle Aggregators"

This dataset supports Chapters 7 and 9 in the PhD thesis titled "Coordination Mechanisms for Electric Vehicle Aggregators". The data supporting the other chapters has been previously published with the following independent DOIs:- Dataset for "Coordination and payment mechanisms for electric vehicle aggregators" article DOI: 10.5258/SOTON/D0339 - Dataset for "Coordination of Electric Vehicle Aggregators: A Coalitional Approach" DOI: 10.5258/SOTON/D0413 - Dataset for "Fair Online Allocation of Perishable Goods and its Application to Electric Vehicle Charging" DOI: 10.5258/SOTON/D0926In more detail, this dataset contains: - Chapter 7. Strategic Manipulation of Decentralised Optimisation AlgorithmsGiven the rapid rise of electric vehicles (EVs) worldwide, and the ambitious targets set for the near future, the management of large EV fleets must be seen as a priority. Specifically, we study a scenario where EV charging is managed through self-interested EV aggregators who compete in the day-ahead market in order to purchase the electricity needed to meet their clients' requirements. With the aim of reducing electricity costs and lowering the impact on electricity markets, a centralised bidding coordination framework has been proposed in the literature employing a coordinator. In order to improve privacy and limit the need for the coordinator, we propose a reformulation of the coordination framework as a decentralised algorithm, employing the Alternating Direction Method of Multipliers (ADMM). However, given the self-interested nature of the aggregators, they can deviate from the algorithm in order to reduce their energy costs. Hence, we study the strategic manipulation of the ADMM algorithm and, in doing so, describe and analyse different possible attack vectors and propose a mathematical framework to quantify and detect manipulation. Importantly, this detection framework is not limited the considered EV scenario and can be applied to general ADMM algorithms. Finally, we test the proposed decentralised coordination and manipulation detection algorithms in realistic scenarios using real market and driver data from Spain. Our empirical results show that the decentralised algorithm's convergence to the optimal solution can be effectively disrupted by manipulative attacks achieving convergence to a different non-optimal solution which benefits the attacker. With respect to the detection algorithm, results indicate that it achieves very high accuracies and significantly outperforms a naive benchmark.- Chapter 9. Forecasting Residual Supply Curves We study the prediction of residual supply curves in day-ahead electricity markets, an essential ingredient for the application of bidding strategies. To this end, we apply neural network models, more specifically multilayer perceptrons, and forecast the residual supply curves for each of the twenty-four hours of the next day. In more detail, we consider both intra- and inter-hour models, and also incorporate exogenous explanatory variables such as wind generation and total demand forecasts. We present empirical results using real data from the Spanish day-ahead market and show that our models outperform previous models in the literature, achieving up to 58.028% performance increase from the naive benchmark, compared to the previous 7.805% reported in the literature. Moreover, we find that inter-hour models achieve up to 6.028% performance increase when compared to intra-hour models.

本数据集支持题为《电动汽车聚合体协调机制》的博士论文的第7章与第9章。支撑该论文其余章节的数据集已通过以下独立数字对象标识符（DOI）提前发表：
- 《电动汽车聚合体协调与支付机制》论文对应数据集，DOI: 10.5258/SOTON/D0339
- 《电动汽车聚合体协调：一种联盟方法》论文对应数据集，DOI: 10.5258/SOTON/D0413
- 《易腐品公平在线分配及其在电动汽车充电中的应用》论文对应数据集，DOI: 10.5258/SOTON/D0926

本数据集详细内容如下：
- 第7章：去中心化优化算法的策略性操纵
随着全球电动汽车（EV）保有量快速攀升，且近期设定了宏伟发展目标，大型电动汽车车队的管理已成为一项优先级任务。具体而言，我们研究了一种由自利型电动汽车聚合体管理电动汽车充电的场景：此类聚合体参与日前电力市场，以采购满足其客户用电需求所需的电力。为降低用电成本并减轻对电力市场的冲击，现有文献中已提出一种借助协调者的集中式投标协调框架。为提升隐私性并减少对协调者的依赖，我们提出将该协调框架重构为一种去中心化算法，即交替方向乘子法（Alternating Direction Method of Multipliers，ADMM）。然而，由于聚合体具有自利属性，它们可能偏离算法以降低自身能源成本。因此，我们针对ADMM算法的策略性操纵展开研究，在此过程中描述并分析了多种潜在攻击向量，并提出了一个可量化与检测操纵行为的数学框架。值得注意的是，该检测框架并不局限于本次研究的电动汽车场景，可推广应用于通用ADMM算法。最后，我们使用来自西班牙的真实市场与驾驶员出行数据，在真实场景中对所提出的去中心化协调与操纵检测算法进行了测试与验证。我们的实证结果表明，操纵性攻击可有效破坏去中心化算法向最优解的收敛过程，使其收敛至另一非最优解，从而为攻击者带来收益。就检测算法而言，实验结果显示其准确率极高，且显著优于简单基准模型。
- 第9章：剩余供给曲线预测
我们研究了日前电力市场中的剩余供给曲线预测问题，该问题是投标策略落地应用的核心要素。为此，我们采用神经网络模型，更具体地说是多层感知器，对次日24个时段的剩余供给曲线分别进行预测。更详细地说，我们同时考量了时段内与时期间两种模型，并纳入了风电出力、总需求预测等外生解释变量。我们使用西班牙日前电力市场的真实数据开展实证研究，结果表明我们的模型优于现有文献中的同类模型，相较于简单基准模型的性能提升可达58.028%，而此前文献中报告的最高提升仅为7.805%。此外，我们发现时期间模型相较于时段内模型的性能提升可达6.028%。