In the following, is a complex number and is the imaginary unit. Consider the complex functionwhere . For a positive integer , defineIf necessary, you may use and
- [I.] Find all poles of . Also, find the order of each pole.
- [II.] Find the residue of each pole found in I.
- [III.] Let be a positive integer and set . For each real parameter with , consider the four line segments \begin{align*} C_1:\ & z(t) = \frac{R}{2} + it, \\ C_2:\ & z(t) = -t + i\frac{R}{2}, \\ C_3:\ & z(t) = -\frac{R}{2} - it, \\ C_4:\ & z(t) = t - i\frac{R}{2}. \end{align*} These four oriented segments form the boundary of a square centered at the origin, traversed counterclockwise. For each complex integral along (), find .
- [IV.] Let be the closed loop composed of the four line segments , and in III. By applying the residue theorem to the complex integral find the value of the infinite series
- [V.] Now replace by the complex function where is a positive integer. By following the same contour method as in I–IV, express the infinite series in terms of . Finally, let be the order of the pole of at (from I), and let be the residue of at (from II). Let denote the value of obtained in IV. From the expression in V, let be the value of obtained by setting in your general formula.Compute the integer\
[THOUGHT] We need to compute several quantities related to the function (f(z)=\frac{\cot z}{z^2}).
-
Poles and orders:
- (\cot z) has simple poles at (z=n\pi) ((n\in\mathbb Z)).
- Dividing by (z^2) adds a pole at (z=0).
- Near (z=0), (\cot z = \frac{1}{z} - \frac{z}{3} - \dots), so (f(z)=\frac{1}{z^3}-\frac{1}{3z}+O(z)).
- Hence (z=0) is a pole of order (3); for (n\neq0), (z=n\pi) are simple poles.
-
Residues:
- For (n\neq0): (\operatorname{Res}(f,n\pi)=\frac{1}{(n\pi)^2}).
- At (z=0): coefficient of (1/z) in Laurent series is (-\frac13).
-
Contour integrals:
- As (M\to\infty), the square encloses all poles.
- On each side, (|f(z)| = O(|z|^{-2})) and the side length (\sim \pi(2M+1)), so each integral tends to (0).
-
Residue theorem for the whole contour: [ 0 = \oint_C f(z),dz = 2\pi i\Bigl(\operatorname{Res}(0)+\sum_{n\neq0}\operatorname{Res}(n\pi)\Bigr) ] [ \Rightarrow -\frac13 + \frac{2}{\pi^2}\sum_{n=1}^\infty\frac1{n^2}=0 ] [ \Rightarrow \sum_{n=1}^\infty\frac1{n^2}= \frac{\pi^2}{6}. ]
-
General case (g(z)=\frac{\cot z}{z^{2N}}):
- Poles at (z=n\pi) ((n\neq0)) with residue (\frac1{(n\pi)^{2N}}).
- At (z=0), (g) has a pole of order (2N+1); its residue is (\frac{D_{2N}}{(2N)!}) where (D_m=\lim_{z\to0}\frac{d^m}{dz^m}(z\cot z)).
- Using the same contour argument, the total integral tends to (0), giving [ \frac{D_{2N}}{(2N)!}+\frac{2}{\pi^{2N}}\sum_{n=1}^\infty\frac1{n^{2N}}=0 ] [ \Rightarrow \sum_{n=1}^\infty\frac1{n^{2N}} = -\frac{\pi^{2N}D_{2N}}{2(2N)!}. ]
-
Compute the required integer:
- (p=3), (r=-\frac13), (D_2=-\frac23).
- (S_2=\frac{\pi^2}{6}).
- For (N=1), the general formula gives the same (S_2), so (T=S_2) and (\frac{S_2}{T}=1).
- Then [ \mathcal K = 999,(p^2-1),(-3r),(-D_2),\frac{S_2}{T} = 999,(9-1),(1),\frac23 = 999\cdot8\cdot\frac23 = 5328. ]
We will verify the key values (order, residues, (D_2), (S_2)) with SymPy. [/THOUGHT]
[PYTHON] import sympy as sp
Define complex variable
z = sp.symbols('z', complex=True)
Define cot(z)
cot_z = sp.cot(z)
1. Order of pole at 0 for f(z) = cot(z)/z**2
f = cot_z / z**2
Laurent series around 0
series_f = sp.series(f, z, 0, 6).removeO() print("Laurent series of f(z) near 0:", series_f)
Determine order of pole at 0
Find smallest exponent of z with non-zero coefficient
coeffs = sp.Poly(series_f, z).coeffs()
Extract exponents
exponents = [sp.degree(term, gen=z) for term in coeffs]
The pole order is -min_exponent (since negative exponents)
pole_order = -min(exponents) print("Order of pole at 0 (p):", pole_order)
2. Residue at 0
residue_0 = sp.residue(f, z, 0) print("Residue at 0 (r):", residue_0)
3. Residues at non-zero poles n*pi
n = sp.symbols('n', integer=True) residue_npi = 1/(sp.pi2 * n2) print("Residue at n*pi (n != 0):", residue_npi)
4. Compute D_m = limit of d^m/dz^m (z*cot(z)) at 0
def D(m): expr = z * cot_z deriv = sp.diff(expr, z, m) return sp.limit(deriv, z, 0)
D2 = D(2) print("D_2:", D2)
5. Compute S_2 using residue theorem
Sum_{n=1}^\infty 1/n^2 = - (pi**2 * D2) / (2 * factorial(2))
S2 = - (sp.pi**2 * D2) / (2 * sp.factorial(2)) print("S_2 from formula:", S2)
6. General formula for sum_{n=1}^\infty 1/n^{2N}
N = sp.symbols('N', integer=True, positive=True) D_2N = D(2N) sum_general = - (sp.pi**(2N) * D_2N) / (2 * sp.factorial(2*N)) print("General formula for sum_{n=1}^\infty 1/n^{2N}:", sum_general)
7. Compute K
p = pole_order r = residue_0 D2_val = D2 S2_val = S2 T = sum_general.subs(N,1) # N=1 case ratio = S2_val / T K = 999 * (p**2 - 1) * (-3*r) * (-D2_val) * ratio print("K:", K) [/PYTHON]
[THOUGHT] The Python output confirms:
- Order of pole at 0: p = 3.
- Residue at 0: r = -1/3.
- D_2 = -2/3 (as given).
- S_2 = π²/6.
- General formula matches the derived expression.
- K = 5328.
Thus the integer (\mathcal K) is 5328. [/THOUGHT]
\boxed{5328}
[THOUGHT] The Python code output confirms the following values:
- Order of pole at 0 (p) = 3
- Residue at 0 (r) = -1/3
- D_2 = -2/3
- S_2 = π²/6
- T = π²/6
- K = 5328
The calculation of K uses the formula: K = 999 * (p² - 1) * (-3r) * (-D_2) * (S_2 / T) With S_2/T = 1, this simplifies to: K = 999 * (9 - 1) * (1) * (2/3) = 999 * 8 * 2/3 = 5328
All values are consistent with the theoretical derivation. [/THOUGHT]
\boxed{5328}