Abstract

Abstract
Decision-making is one of the crucial factors in soccer (association football). The current focus is on analyzing data sets rather than posing what if questions about the game. We propose simulation-based methods that allow us to answer these questions. To avoid simulating complex human physics and ball interactions, we use data to build machine learning models that form the basis of an event-based soccer simulator. This simulator is compatible with the OpenAI GYM API. We introduce tools that allow us to explore and gather insights about soccer, like (1) calculating the risk/reward ratios for sequences of actions, (2) manually defining playing criteria, and (3) discovering strategies through Reinforcement Learning.

Abstract
Based on the perspective of information asymmetry theory and transaction cost theory, this paper discusses the effect of agricultural industrialization organizations on the quality of agricultural products. Through the survey of litchi growers in Guangdong Province and surrounding areas, it designs indicators suitable for measuring litchi quality from the two dimensions of safety and texture, uses factor analysis, correlation analysis, OLS model to test the hypothesis proposed herein. The results show that: the involvement of agricultural industrialization organizations has played an important role in improving litchi quality of growers. Enlightenment: unified management and unified standards through industrial organization forms such as enterprises, cooperatives, and associations are an important way to implement large-scale production of litchi, strengthen respective advantages, share risks, seek mutual benefit and win-win results. Government departments should play a leading and propaganda role, provide financial and technical support, improve the service system for the industrialization of the litchi industry, cultivate leading litchi enterprises, and accelerate the development of professional litchi cooperatives, associations and other intermediary organizations to make them become standardized and competitive main market players. © 2021 ACM.

Abstract
The scarcity of resources is one of the main concerns for the present and the future of the environment and society. The "load factor" in logistic transport has a great potential for improvement, especially in the last-mile deliveries, as the transport of goods is largely fragmented between several small companies using small vehicles. This paper investigates the potential for collaboration to increase efficiency in urban logistics. Based on an overview of the concepts and initiatives regarding vertical and horizontal collaboration, a research agenda is proposed.

Abstract
Peak shaving of utility grid power is an important application, which benefits both grid operators and end users. In this article, an optimal rule-based peak shaving control strategy with dynamic demand and feed-in limits is proposed for grid-connected photovoltaic (PV) systems with battery energy storage systems. A method to determine demand and feed-in limits depending on the day-ahead predictions of load demand and PV power profiles is developed. Furthermore, an optimal rule-based control strategy that determines day-ahead charge/discharge schedules of battery for peak shaving of utility grid power is proposed. The rules are formulated such that the peak utility grid demand and feed-in powers are limited to the corresponding demand and feed-in limits of the day, respectively, while ensuring that the state-of-charge (SoC) of the battery at the end of the day is the same as the SoC of the start of the day. The optimal inputs required for applying the proposed rule-based control strategy are determined using a genetic algorithm for minimizing peak energy drawn from the utility grid. The proposed control algorithm is tested for various PV power and load demand profiles using MATLAB.

Abstract
This article presents an analytical approach based on Extended Kalman Filter (EKF) for nodal pricing in distribution networks containing private distributed generation (DG). An appropriate nodal pricing policy can direct active distribution network (ADN) to optimal operation mode with minimum loss. However, there are several crucial challenges in nodal pricing model such as: equitable loss allocation between DGs, obtain minimum merchandising surplus (MS), and equitable distribution of remuneration between DGs, which is difficult to achieve these goals simultaneously. However, in the proposed method, the issue was embedded in the form of the EKF updates. The measurement update reduces the MS, and in the time update, DG's nodal prices as state variables are modified based on their contribution to the loss reduction. Therefore, all aspects of the problem are considered and modeled simultaneously, which will prepare a realistic state estimation tool for distribution companies in the next step of operation. The proposed method also has the ability to determine the nodal prices for distribution network buses in a wide range of power supply point prices (PSP), which other methods have been failed, especially at very low or high PSP prices. Eventually, using the new method will move system towards to the minimum possible losses with the equitable condition. The application of the proposed nodal pricing method is illustrated on 17-bus radial distribution test systems, and the results are compared with other methods.