本数据集包含随时间变化的电力负荷消耗（单位：kWh）多变量时间序列数据。数据能够反映不同用电主体之间的相关性、日/周周期性负荷变化规律以及能源需求随时间变化的动态特征。变量按客户编号顺序命名（客户0-320），各列对应一个用电对象，行对应时间戳。相较同类数据集，本数据集时间跨度长、周期性规律明显、用户间相关结构丰富，主要应用于能源调度场景下的负荷预测、系统状态建模、多变量时序特征提取、预测模型泛化能力验证及人机协同求解平台功能测试。
", "ds_source": "本数据集基于论文中的博弈模型通过计算机仿真生成。
", "ds_process_way": "采用Pandas对数据进行读取、表格化整理、时间索引构建、缺失值处理和变量维度对齐，剔除长期无用电记录的客户，整理为\"时间戳×用电客户\"的二维CSV表格；采用NumPy进行数组计算、矩阵运算和归一化处理（Z-score标准化）。
", "ds_quality": "满足相应论文中博弈模型的建模条件
", "ds_acq_start_time": null, "ds_acq_end_time": null, "ds_acq_place": "无特别要求", "ds_acq_lon_east": null, "ds_acq_lat_south": null, "ds_acq_lon_west": null, "ds_acq_lat_north": null, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "open-access", "ds_total_size": 95581762, "ds_files_count": 0, "ds_format": "CSV", "ds_space_res": "", "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "0fd2c06c-64d5-49dc-8483-0d973a40a0cf.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "结合论文中博弈模型使用。", "ds_from_station": "", "organization_id": "9ecaaa78-39e9-411e-9f24-274e12aa643f", "ds_serv_man": "陈都鑫", "ds_serv_phone": "18915917083", "ds_serv_mail": "chendx@seu.edu.cn", "doi_value": "", "subject_codes": [ "410" ], "quality_level": 0, "publish_time": "2026-07-09 10:58:25", "last_updated": "2026-07-09 10:58:25", "protected": false, "protected_to": "2028-06-30 00:00:00", "lang": "zh", "cstr": "", "i18n": { "en": { "title": "", "ds_format": "CSV", "ds_source": "This dataset is generated through computer simulation based on the game model presented in the paper.", "ds_quality": "Meet the modeling conditions of the game model in the corresponding paper", "ds_ref_way": "", "ds_abstract": "This dataset comprises multivariate time-series data representing electricity load consumption (in kWh) over time. It captures the correlations between different electricity consumers, daily and weekly cyclical load patterns, and the dynamic nature of energy demand. Variables are labeled by customer ID (Customer 0–320), with columns representing individual consumers and rows corresponding to timestamps. Compared to similar datasets, this dataset features an extensive time span, distinct cyclical patterns, and rich inter-user correlation structures; it is primarily intended for applications such as load forecasting in energy scheduling, system state modeling, multivariate time-series feature extraction, validation of forecasting model generalization, and functional testing of human-machine collaborative problem-solving platforms.", "ds_time_res": "", "ds_acq_place": "No special requirements", "ds_space_res": "", "ds_projection": "", "ds_process_way": "Using Pandas to read data, organize it into tables, construct time indexes, handle missing values, and align variable dimensions, removing customers with long-term records of no electricity use, and organizing it into a two-dimensional CSV table with \"timestamp x electricity customer\"; Use NumPy for array calculations, matrix operations, and normalization (Z-score normalization).", "ds_ref_instruction": "Use in conjunction with the game model presented in the paper." } }, "submit_center_id": "ncdc", "data_level": 0, "recommendation_value": 0, "license_type": "https://creativecommons.org/licenses/by/4.0/", "doi_reg_from": "reg_local", "cstr_reg_from": "reg_local", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "belong_to_nieer": false, "ds_topic_tags": [ "电力负荷", "负荷预测", "能源调度" ], "ds_subject_tags": [ "工程与技术科学基础学科" ], "ds_class_tags": [], "ds_locus_tags": [], "ds_time_tags": [], "ds_contributors": [ { "true_name": "陈都鑫", "email": "chendx@seu.edu.cn", "work_for": "东南大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "陈都鑫", "email": "chendx@seu.edu.cn", "work_for": "东南大学", "country": "中国" } ], "ds_managers": [ { "true_name": "陈都鑫", "email": "chendx@seu.edu.cn", "work_for": "东南大学", "country": "中国" } ], "category": "其他" }