Abstract:
PROBLEM TO BE SOLVED: To obtain analytically and with high accuracy the caching hit ratio of a caching system. SOLUTION: This system is a caching hit ratio estimation system estimating the caching hit ratio of a caching system which performs the caching of the data for access accessed from a demand origin system. This system is provided with an access request arrival frequency acquiring part which acquires an average arrival frequency measured about an access request to each data for access, an access request arrival probability density function generating part which generates an access request arrival probability density function that is a probability density function of an arrival time interval of access requests to the data for access based on the average arrival frequency of the access request to each data for access, and a caching hit ratio estimation function generating part which generates the estimation function of the caching hit ratio of each data for access based on access demand arrival probability density functions of a plurality of data for access. COPYRIGHT: (C)2006,JPO&NCIPI
Abstract:
PROBLEM TO BE SOLVED: To provide a method and an apparatus for estimating a hit rate which accurately estimates a rate of hitting at a session data cache 12 associated with a Web application on a Web server 10 in a running state while avoiding the increase of overhead. SOLUTION: The method comprises steps for; calculating a quitting probability pl, an average μ and a distribution σ 2 of a deliberate time and a hit rate r for a session data cache 12 which is associated with the Web application based on a counter of the Web server 10; and defining pl α , μ α , σ 2 α and an average of α for the readout number of each group of the session data. A calculation formula setting apparatus 21 sets a formula of f(α)=α for calculating a fixed point including pl, μ, σ 2 , r, pl α , μ α , and σ 2 α . A means 22 for retrieving a true value which retrieves a value close to the true value of α based on a formula f(α)=α. An estimating means 23 estimates r α based on the α which has been retrieved. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
PROBLEM TO BE SOLVED: To adjust server's loads caused by requests and to steadily set the controlled loads without stopping service provision by the server. SOLUTION: Requests transmitted to the sever 2 are temporarily stored in a queue 4, the requests existing in the queue or requests generated by a false client 5 when no request exists in the queue are successively transferred to the server 2 at prescribed timing to control server's loads caused by the requests. In this case, timing at which requests to be transferred to the server 2 arrive at the server 2 at fixed arrival time interval distribution is adopted as the prescribed timing. Such a timing is determined on the basis of random numbers generated from a random number generator 6 at prescribed probability distribution. COPYRIGHT: (C)2005,JPO&NCIPI
Abstract:
PROBLEM TO BE SOLVED: To enlarge wiring interval and width while adopting a free angle wiring by selecting a wire to be shaped, generating an arc-shaped prohibition region from an obstacle containing a terminal and a wiring prohibition region other than the terminal, and obtaining the shortest path for avoiding the passage of the generated prohibition region. SOLUTION: One wire to be shaped from a phase wiring to a physical wiring is selected (Step 12). Then, an obstacle for viewing it is specified (Step 14). Then, an area within an arc with an interval that becomes a given number of times larger than a gap that at least need to be provided between a wiring to be shaped and a selected obstacle is set to a selected obstacle as a prohibition region (Step 18). Then, the physical wiring of the wiring to be shaped is determined using the shortest path so that the prohibition region cannot be passed (Step 22).
Abstract:
To solve combined scheduling of two different slab sequences by a rational technique. [Solution] A two-dimensional grid graph having a direct slab sequence as a first dimension and an inventory slab sequence as a second dimension is prepared by processing of a computer as a data structure represented on a memory or a hard disk drive of the computer. A processing program of the computer generates two child nodes corresponding to a direct slab and an inventory slab, in each node of the two-dimensional graph according to a predetermined algorithm. By defining an appropriate weighting function, the processing program of the computer weights edges between nodes in the two-dimensional grid graph. After forming the weighted graph on a storage device of the computer such as the memory or the hard disk drive, the processing program of the computer calculates a path from a start point to an end point as a shortest path search problem such as known Dijkstra's algorithm.
Abstract:
Merged scheduling of two different slab lines is solved by a rational technique. By computer processing, a grid-shaped two-dimensional graph with a direct slab line as a first dimension and a stock slab line as a second dimension is prepared as a data structure represented in a memory or hard disk drive of a computer. A computer processing program generates two child nodes for the direct slab and the stock slab in each node of the two-dimensional graph in accordance with a predetermined algorithm. By defining an appropriate weighting factor, edges between nodes of the grid-shaped two-dimensional graph are weighted. When a weighted graph is formed in a storage device of the computer such as the memory or hard disk drive of the computer, the computer processing program finds a path from a starting point to an ending point as a shortest path search problem such as an already known Dijkstra's method.