In this work, energy time series forecasting competitions from the Schneider Company, the Kaggle Online platform, and the American society ASHRAE were considered. These competitions include power generation and building energy consumption forecasts. The datasets used in these competitions are based on reliable and real sensor records. In addition, exogenous variables are accurately added to the dataset. All of these ensure the richness of the information contained in the dataset, which is crucial for energy management. Therefore, (1) We choose to study forecast models suitable for energy management on these energy datasets; (2) Forecast models including popular algorithm structures such as neural network models and ensemble models. In addition, as an innovation, we introduce the Explainable AI method (SHAP) to explain models with excellent performance indicators, thereby strengthening its trust and transparency; (3) The results show that the performance of the integrated model in these competitions is more stable and efficient, and in the integrated model, the advantages of LightGBM are more obvious; (4) Through the interpretation of SHAP, we found that the lagging characteristics of the building area and target variables are important features.

The network effect gains demand-side economies of scale that have a significant impact on profit, price and demand in business. The paper presents a supply chain model with duopolistic competition in terms of decentralized and centralized decision making processes that consider the network effect. First, by establishing the differential equation of network size that is a function of the network investment, the paper presents the supply chain model with dynamic competition. Then, in order to maximize the supply chain profit, the optimal value of the optimal strategy is obtained by solving the differential game. The optimal value of the optimal policy about wholesale production, retail price and effort rate is obtained. In results, in the first stage of network cycle, the profits of supply chain system with centralized decision is lower than that with decentralized decision-making, but with the passage of time, the profits will be phased in over decentralized decision situation with the greater gap.

An iterative algorithm for enumeration of partitions of a finite multiset into subsets of a given cardinality is described. A multiset is a set that includes multiple elements, so each element is included in the multiset a given number of times. The cardinality of a multiset is equal to the sum of the multiplicities of all its elements. All subsets in the partition are distinguishable. If the partition into subsets is specified in such a way that the cardinalities of some subsets are the same, it is considered that these are different subsets. An order relation is given on partitions. The algorithm enumerates the partitions of the original multiset into subsets of a given cardinality in ascending order. The next partition is calculated from the previous one. This structure of the algorithm allows you to set the initial and final partitions, between which the enumeration is carried out. This makes it possible to divide the enumeration into parts and perform calculations in parallel on different devices. The consistency of the algorithm was tested in practice using a computer with a dual-core processor. When performing calculations in parallel threads, the full enumeration is performed almost twice as fast.

Climate change has become one of the most pressing global challenges, with carbon dioxide CO2 emissions being key driver of this phenomenon. Understanding the factors influencing CO2 emissions is critical for achieving sustainable development and mitigating the impacts of climate change. This research explores the relationships between CO2 emissions and various economic, social, environmental, energy and technological factors using dataset covering 107 countries from 2000 to 2020. Employing stepwise multiple, non-spatial fixed-effects panel model and spatial regression model, the research incorporates GDP per capita, population density, renewable energy share, and primary energy consumption, with all computations performed using Python and R. By addressing data challenges such as skewness and variability, this research aims to provide a comprehensive understanding of the dynamics of carbon emissions and their determinants. The findings contribute to ongoing discussions on sustainable energy transitions and global efforts to combat climate change, offering insights that can inform policy design and implementation.