Short-term load forecasting is a prerequisite for achieving intra-day energy management and optimal scheduling in integrated energy systems. Its prediction accuracy directly affects the stability and economy of the system during operation. To improve the accuracy of short-term load forecasting, this paper proposes a multi-load forecasting method for integrated energy systems based on the Isolation Forest and dynamic orbit algorithm. First, a high-dimensional data matrix is constructed using the sliding window technique and the outliers in the high-dimensional data matrix are identified using Isolation Forest. Next, the hidden abnormal data within the time series are analyzed and repaired using the dynamic orbit algorithm. Then, the correlation analysis of the multivariate load and its weather data is carried out by the AR method and MIC method, and the high-dimensional feature matrix is constructed. Finally, the prediction values of the multi-load are generated based on the TCN-MMoL multi-task training network. Simulation analysis is conducted using the load data from a specific integrated energy system. The results demonstrate the proposed model’s ability to significantly improve load forecasting accuracy, thereby validating the correctness and effectiveness of this forecasting approach.

Accurate regional demand forecasting supports reliable operation of urban electric vehicle (EV) charging networks. However, public charging demand exhibits spatial heterogeneity, multi-scale periodicity, and uncertainty. This paper proposes Urban-CSTPNet, a multi-relational spatio-temporal probabilistic forecasting framework. Five semantically explicit graphs represent geographical adjacency, spatial distance, historical demand correlation, pricing-pattern similarity, and static regional attributes. Sample-level time-conditioned graph gating fuses these relations using historical demand states and calendar context. Independent recent, daily, and weekly branches capture short-term variation, daily repetition, and weekly regularity, and are combined through temporal gating. The model produces multiple conditional quantiles and applies horizon-specific conformalized quantile regression using an independent calibration set. Experiments on the Shenzhen UrbanEV dataset at 1, 3, 6, 12, and 24 h horizons achieve a mean absolute error (MAE) of 60.44, root mean squared error (RMSE) of 192.44, and Pinball Loss of 16.96. These values are 11.51%, 6.04%, and 9.50% lower than those of ST-MGF-Q. For calibrated 90% intervals, the prediction interval coverage probability (PICP), prediction interval normalized average width (PINAW), and Interval Score are 0.9024, 0.0175, and 349.60. Results confirm improved forecasting accuracy, probabilistic quality, and empirical interval reliability.