No description available.

The main topic of the paper is on-line filtering for non-Gaussian dynamic (state space) models by approximate computation of the first two posterior moments using efficient numerical integration. Based on approximating the prior of the state vector by a normal density, we prove that the posterior moments of the state vector are related to the posterior moments of the linear predictor in a simple way. For the linear predictor Gauss-Hermite integration is carried out with automatic reparametrization based on an approximate posterior mode filter. We illustrate how further topics in applied state space modelling such as estimating hyperparameters, computing model likelihoods and predictive residuals, are managed by integration-based Kalman-filtering. The methodology derived in the paper is applied to on-line monitoring of ecological time series and filtering for small count data. (author's abstract) / Series: Forschungsberichte / Institut für Statistik

小泉時期全力支援美國小布希總統的全球反恐戰爭，透過強化美日同盟，成功提升日本在美日同盟的功能與角色，朝向正常國家之路邁進。小泉每年參拜靖國神社興起了日本的民族主義，但也造成了中日關係的惡化，進而加深了日本在加入聯合國安理會常任理事國上的難度，也成為中國大規模反日運動的導火線。在中日關係上，從二戰後就一直存在著歷史上的仇恨問題，以及地緣政治因素，中日兩國在領土紛爭及資源分配等政治經濟的議題上，始終有著既合作又競爭的複雜關係。小泉時期因為911反恐浪潮強化了追隨美國路線，使得美日間友好關係展現了前所未有的高潮，同時也使中日關係產生了前所未有的「政冷經熱」的詭異現象。 本文認為，小泉的追隨美國路線的外交政策或是在推動正常國家政策上，必然會對造成中日關係上的影響，但是在推動正常國家政策上中國的支持又不可或缺，進而日本需要調整對中政策才能達成目標。小泉時期的追隨美國路線，係以什麼基準考量推動對中政策？其對中政策又如何去影響中日關係？中日關係的變化是否又會對日本的對中政策有所改變？值得我們深加研究。 / During the Koizumi administration, Japan's normalized country policies strongly supported George W. Bush's Global War on Terror to increase its role in the U.S.-Japan alliance. In addition, Koizumi also made the formal visit to the Yasukuni Shrine every year and raised Japanese nationalism. Together, these acts have contributed to the deterioration of Sino-Japanese relations, deepened the difficulty of Japan's accession to the United Nations Security Council permanent members, and become the main cause of China's large-scale anti-Japanese movement. Since World War II, Sino-Japanese relations have been characterized by historical hatred and geopolitical factors. In territorial disputes, resource allocation, and other political and economic issues, China and Japan always have a complex relationship with both cooperation and competition. During the Koizumi period, Japan's pro-American policy was strengthened due to the wave of anti-terrorism following 911, which lead to an unprecedented climax in U.S.-Japan friendship. Meanwhile, Sino-Japanese relations experienced an unprecedented and strong phenomenon of "Cold Politics-Hot Economics." Koizumi's pro-American foreign policy or Normalization policy has significantly influenced Sino-Japanese relations. To promote normalization, however, China's support is also indispensable to Japan. Thus, Japan needs to adjust its policy to achieve its goals. This research explores the basis through which the Koizumi administration evaluate its China policy under a pro-American foreign policy guideline. How Japan's China policy influences Sino-Japanese relations and whether the change in Sino-Japanese relations will then change Japan's China policy are also worth our further discussions.

No description available.

In an electric power system, there will always be an electric balance. Nevertheless, System Operators (SOs) often uses the term imbalance. Here, the term imbalance refers to the difference between trades and real-time measurements. This thesis defines the term imbalance and develops a framework helping SOs in finding better decisions controlling these imbalances.  Imbalances are controlled by many decisions made at various stages before real-time. A decision can be to increase the flexibility in production and consumption. However, this is not the only decision affecting real-time balancing operation. Other decisions are grid code requirements, such as ramp rates of HVDC and generation; balancing market structure, such as imbalance fees and trading period lengths; and the strategies used in the system-operational dispatch. The purpose of this thesis is to create a new possibility for SO to find decisions improving the balancing operation.  In order to find and compare decisions, the thesis develops a framework that evaluates many different decisions made at various stages before real-time. The framework consists of the following. First, it develops an intra-hour model using multi-bidding zone data from a historical time-period; able to capture the normal state frequency and active power dynamics. The model creates high-resolution data from low-resolution measurements using several data-processing methods. The uncertainty from the historical time-period is re-created using many sub-models with different input data, time-scales and activation times of reserves. Secondly, the framework validates the model and identifies system parameters based on simulated frequencies and frequency measurements in the normal state operation. Finally; new decisions' are modelled, tested, and evaluated on their impact on selected targets supporting corporate missions of the SOs. The goal of the framework is that it should be able to find better decisions for balancing operation but also that it should be applicable for real and large power systems. To verify this, the framework is tested on a synchronous area containing 11 bidding zones in northern Europe. Results show that the framework can be validated and trusted. Three new decisions, made at various stages before real time, have been modelled, tested and evaluated. The modelled decisions were (i) lower ramp rates for generation, (ii) increased capacities for automatic reserves, and (iii) a new strategy for the system-operational dispatch. One implication of applying the balancing evaluation framework on data from July 2015 is that all tested decisions improve several selected targets supporting the corporate missions of the SOs.  The conclusion is that the balancing framework is useful as a simulation tool in helping SOs in finding more efficient decisions for transmission system balancing operation. / <p>QC 20180116</p>